{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "24gYiJcWNlpA" }, "source": [ "##### Copyright 2019 The TensorFlow Neural Structured Learning Authors" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "cellView": "form", "execution": { "iopub.execute_input": "2022-12-14T12:19:08.428177Z", "iopub.status.busy": "2022-12-14T12:19:08.427826Z", "iopub.status.idle": "2022-12-14T12:19:08.432220Z", "shell.execute_reply": "2022-12-14T12:19:08.431546Z" }, "id": "ioaprt5q5US7" }, "outputs": [], "source": [ "#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n", "# you may not use this file except in compliance with the License.\n", "# You may obtain a copy of the License at\n", "#\n", "# https://www.apache.org/licenses/LICENSE-2.0\n", "#\n", "# Unless required by applicable law or agreed to in writing, software\n", "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", "# See the License for the specific language governing permissions and\n", "# limitations under the License." ] }, { "cell_type": "markdown", "metadata": { "id": "ItXfxkxvosLH" }, "source": [ "# Graph regularization for sentiment classification using synthesized graphs\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", "
\n", " View on TensorFlow.org\n", " \n", " Run in Google Colab\n", " \n", " View source on GitHub\n", " \n", " Download notebook\n", " \n", " See TF Hub model\n", "
" ] }, { "cell_type": "markdown", "metadata": { "id": "z3otbdCMmJiJ" }, "source": [ "## Overview" ] }, { "cell_type": "markdown", "metadata": { "id": "Eg62Pmz3o83v" }, "source": [ "This notebook classifies movie reviews as *positive* or *negative* using the\n", "text of the review. This is an example of *binary* classification, an important\n", "and widely applicable kind of machine learning problem.\n", "\n", "We will demonstrate the use of graph regularization in this notebook by building\n", "a graph from the given input. The general recipe for building a\n", "graph-regularized model using the Neural Structured Learning (NSL) framework\n", "when the input does not contain an explicit graph is as follows:\n", "\n", "1. Create embeddings for each text sample in the input. This can be done using\n", " pre-trained models such as [word2vec](https://arxiv.org/pdf/1310.4546.pdf),\n", " [Swivel](https://arxiv.org/abs/1602.02215),\n", " [BERT](https://arxiv.org/abs/1810.04805) etc.\n", "2. Build a graph based on these embeddings by using a similarity metric such as\n", " the 'L2' distance, 'cosine' distance, etc. Nodes in the graph correspond to\n", " samples and edges in the graph correspond to similarity between pairs of\n", " samples.\n", "3. Generate training data from the above synthesized graph and sample features.\n", " The resulting training data will contain neighbor features in addition to\n", " the original node features.\n", "4. Create a neural network as a base model using the Keras sequential,\n", " functional, or subclass API.\n", "5. Wrap the base model with the GraphRegularization wrapper class, which is\n", " provided by the NSL framework, to create a new graph Keras model. This new\n", " model will include a graph regularization loss as the regularization term in\n", " its training objective.\n", "6. Train and evaluate the graph Keras model.\n", "\n", "**Note**: We expect that it would take readers about 1 hour to go through this\n", "tutorial." ] }, { "cell_type": "markdown", "metadata": { "id": "nDOFbB34KY1R" }, "source": [ "## Requirements\n", "\n", "1. Install the Neural Structured Learning package.\n", "2. Install tensorflow-hub." ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:08.435912Z", "iopub.status.busy": "2022-12-14T12:19:08.435409Z", "iopub.status.idle": "2022-12-14T12:19:12.109551Z", "shell.execute_reply": "2022-12-14T12:19:12.108352Z" }, "id": "uVnjPmOaQlnH" }, "outputs": [], "source": [ "!pip install --quiet neural-structured-learning\n", "!pip install --quiet tensorflow-hub" ] }, { "cell_type": "markdown", "metadata": { "id": "x6FJ64qMNLez" }, "source": [ "## Dependencies and imports" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:12.114490Z", "iopub.status.busy": "2022-12-14T12:19:12.113762Z", "iopub.status.idle": "2022-12-14T12:19:14.776396Z", "shell.execute_reply": "2022-12-14T12:19:14.775346Z" }, "id": "2ew7HTbPpCJH" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2022-12-14 12:19:13.551836: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory\n", "2022-12-14 12:19:13.551949: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory\n", "2022-12-14 12:19:13.551962: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Version: 2.11.0\n", "Eager mode: True\n", "Hub version: 0.12.0\n", "GPU is NOT AVAILABLE\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "2022-12-14 12:19:14.770677: E tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:267] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected\n" ] } ], "source": [ "import matplotlib.pyplot as plt\n", "import numpy as np\n", "\n", "import neural_structured_learning as nsl\n", "\n", "import tensorflow as tf\n", "import tensorflow_hub as hub\n", "\n", "# Resets notebook state\n", "tf.keras.backend.clear_session()\n", "\n", "print(\"Version: \", tf.__version__)\n", "print(\"Eager mode: \", tf.executing_eagerly())\n", "print(\"Hub version: \", hub.__version__)\n", "print(\n", " \"GPU is\",\n", " \"available\" if tf.config.list_physical_devices(\"GPU\") else \"NOT AVAILABLE\")" ] }, { "cell_type": "markdown", "metadata": { "id": "nGwwFd99n42P" }, "source": [ "## IMDB dataset\n", "\n", "The\n", "[IMDB dataset](https://www.tensorflow.org/api_docs/python/tf/keras/datasets/imdb)\n", "contains the text of 50,000 movie reviews from the\n", "[Internet Movie Database](https://www.imdb.com/). These are split into 25,000\n", "reviews for training and 25,000 reviews for testing. The training and testing\n", "sets are *balanced*, meaning they contain an equal number of positive and\n", "negative reviews.\n", "\n", "In this tutorial, we will use a preprocessed version of the IMDB dataset." ] }, { "cell_type": "markdown", "metadata": { "id": "iAsKG535pHep" }, "source": [ "### Download preprocessed IMDB dataset\n", "\n", "The IMDB dataset comes packaged with TensorFlow. It has already been\n", "preprocessed such that the reviews (sequences of words) have been converted to\n", "sequences of integers, where each integer represents a specific word in a\n", "dictionary.\n", "\n", "The following code downloads the IMDB dataset (or uses a cached copy if it has\n", "already been downloaded):" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:14.781096Z", "iopub.status.busy": "2022-12-14T12:19:14.780044Z", "iopub.status.idle": "2022-12-14T12:19:18.643486Z", "shell.execute_reply": "2022-12-14T12:19:18.642696Z" }, "id": "zXXx5Oc3pOmN" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb.npz\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 8192/17464789 [..............................] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4202496/17464789 [======>.......................] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17464789/17464789 [==============================] - 0s 0us/step\n" ] } ], "source": [ "imdb = tf.keras.datasets.imdb\n", "(pp_train_data, pp_train_labels), (pp_test_data, pp_test_labels) = (\n", " imdb.load_data(num_words=10000))" ] }, { "cell_type": "markdown", "metadata": { "id": "odr-KlzO-lkL" }, "source": [ "The argument `num_words=10000` keeps the top 10,000 most frequently occurring words in the training data. The rare words are discarded to keep the size of the vocabulary manageable." ] }, { "cell_type": "markdown", "metadata": { "id": "l50X3GfjpU4r" }, "source": [ "### Explore the data\n", "\n", "Let's take a moment to understand the format of the data. The dataset comes preprocessed: each example is an array of integers representing the words of the movie review. Each label is an integer value of either 0 or 1, where 0 is a negative review, and 1 is a positive review." ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:18.647986Z", "iopub.status.busy": "2022-12-14T12:19:18.647331Z", "iopub.status.idle": "2022-12-14T12:19:18.651575Z", "shell.execute_reply": "2022-12-14T12:19:18.650904Z" }, "id": "y8qCnve_-lkO" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training entries: 25000, labels: 25000\n" ] } ], "source": [ "print('Training entries: {}, labels: {}'.format(\n", " len(pp_train_data), len(pp_train_labels)))\n", "training_samples_count = len(pp_train_data)" ] }, { "cell_type": "markdown", "metadata": { "id": "RnKvHWW4-lkW" }, "source": [ "The text of reviews have been converted to integers, where each integer represents a specific word in a dictionary. Here's what the first review looks like:" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:18.654933Z", "iopub.status.busy": "2022-12-14T12:19:18.654417Z", "iopub.status.idle": "2022-12-14T12:19:18.658502Z", "shell.execute_reply": "2022-12-14T12:19:18.657767Z" }, "id": "QtTS4kpEpjbi" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[1, 14, 22, 16, 43, 530, 973, 1622, 1385, 65, 458, 4468, 66, 3941, 4, 173, 36, 256, 5, 25, 100, 43, 838, 112, 50, 670, 2, 9, 35, 480, 284, 5, 150, 4, 172, 112, 167, 2, 336, 385, 39, 4, 172, 4536, 1111, 17, 546, 38, 13, 447, 4, 192, 50, 16, 6, 147, 2025, 19, 14, 22, 4, 1920, 4613, 469, 4, 22, 71, 87, 12, 16, 43, 530, 38, 76, 15, 13, 1247, 4, 22, 17, 515, 17, 12, 16, 626, 18, 2, 5, 62, 386, 12, 8, 316, 8, 106, 5, 4, 2223, 5244, 16, 480, 66, 3785, 33, 4, 130, 12, 16, 38, 619, 5, 25, 124, 51, 36, 135, 48, 25, 1415, 33, 6, 22, 12, 215, 28, 77, 52, 5, 14, 407, 16, 82, 2, 8, 4, 107, 117, 5952, 15, 256, 4, 2, 7, 3766, 5, 723, 36, 71, 43, 530, 476, 26, 400, 317, 46, 7, 4, 2, 1029, 13, 104, 88, 4, 381, 15, 297, 98, 32, 2071, 56, 26, 141, 6, 194, 7486, 18, 4, 226, 22, 21, 134, 476, 26, 480, 5, 144, 30, 5535, 18, 51, 36, 28, 224, 92, 25, 104, 4, 226, 65, 16, 38, 1334, 88, 12, 16, 283, 5, 16, 4472, 113, 103, 32, 15, 16, 5345, 19, 178, 32]\n" ] } ], "source": [ "print(pp_train_data[0])" ] }, { "cell_type": "markdown", "metadata": { "id": "hIE4l_72x7DP" }, "source": [ "Movie reviews may be different lengths. The below code shows the number of words in the first and second reviews. Since inputs to a neural network must be the same length, we'll need to resolve this later." ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:18.661755Z", "iopub.status.busy": "2022-12-14T12:19:18.661272Z", "iopub.status.idle": "2022-12-14T12:19:18.668289Z", "shell.execute_reply": "2022-12-14T12:19:18.667609Z" }, "id": "X-6Ii9Pfx6Nr" }, "outputs": [ { "data": { "text/plain": [ "(218, 189)" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(pp_train_data[0]), len(pp_train_data[1])" ] }, { "cell_type": "markdown", "metadata": { "id": "4wJg2FiYpuoX" }, "source": [ "### Convert the integers back to words\n", "\n", "It may be useful to know how to convert integers back to the corresponding text.\n", "Here, we'll create a helper function to query a dictionary object that contains\n", "the integer to string mapping:" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:18.671628Z", "iopub.status.busy": "2022-12-14T12:19:18.671099Z", "iopub.status.idle": "2022-12-14T12:19:18.843334Z", "shell.execute_reply": "2022-12-14T12:19:18.842506Z" }, "id": "tr5s_1alpzop" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb_word_index.json\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 8192/1641221 [..............................] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1641221/1641221 [==============================] - 0s 0us/step\n" ] } ], "source": [ "def build_reverse_word_index():\n", " # A dictionary mapping words to an integer index\n", " word_index = imdb.get_word_index()\n", "\n", " # The first indices are reserved\n", " word_index = {k: (v + 3) for k, v in word_index.items()}\n", " word_index[''] = 0\n", " word_index[''] = 1\n", " word_index[''] = 2 # unknown\n", " word_index[''] = 3\n", " return dict((value, key) for (key, value) in word_index.items())\n", "\n", "reverse_word_index = build_reverse_word_index()\n", "\n", "def decode_review(text):\n", " return ' '.join([reverse_word_index.get(i, '?') for i in text])" ] }, { "cell_type": "markdown", "metadata": { "id": "U3CNRvEZVppl" }, "source": [ "Now we can use the `decode_review` function to display the text for the first review:" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:18.847814Z", "iopub.status.busy": "2022-12-14T12:19:18.847102Z", "iopub.status.idle": "2022-12-14T12:19:18.852113Z", "shell.execute_reply": "2022-12-14T12:19:18.851432Z" }, "id": "s_OqxmH6-lkn" }, "outputs": [ { "data": { "text/plain": [ "\" this film was just brilliant casting location scenery story direction everyone's really suited the part they played and you could just imagine being there robert is an amazing actor and now the same being director father came from the same scottish island as myself so i loved the fact there was a real connection with this film the witty remarks throughout the film were great it was just brilliant so much that i bought the film as soon as it was released for and would recommend it to everyone to watch and the fly fishing was amazing really cried at the end it was so sad and you know what they say if you cry at a film it must have been good and this definitely was also to the two little boy's that played the of norman and paul they were just brilliant children are often left out of the list i think because the stars that play them all grown up are such a big profile for the whole film but these children are amazing and should be praised for what they have done don't you think the whole story was so lovely because it was true and was someone's life after all that was shared with us all\"" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "decode_review(pp_train_data[0])" ] }, { "cell_type": "markdown", "metadata": { "id": "rVmqL-zcWm8v" }, "source": [ "## Graph construction\n", "\n", "Graph construction involves creating embeddings for text samples and then using\n", "a similarity function to compare the embeddings.\n", "\n", "Before proceeding further, we first create a directory to store artifacts\n", "created by this tutorial." ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:18.855488Z", "iopub.status.busy": "2022-12-14T12:19:18.854992Z", "iopub.status.idle": "2022-12-14T12:19:18.985942Z", "shell.execute_reply": "2022-12-14T12:19:18.984849Z" }, "id": "wZicFxFOeL2J" }, "outputs": [], "source": [ "!mkdir -p /tmp/imdb" ] }, { "cell_type": "markdown", "metadata": { "id": "uUyHEa-3TB2X" }, "source": [ "### Create sample embeddings" ] }, { "cell_type": "markdown", "metadata": { "id": "qCe9vOy7-Br9" }, "source": [ "We will use pretrained Swivel embeddings to create embeddings in the\n", "`tf.train.Example` format for each sample in the input. We will store the\n", "resulting embeddings in the `TFRecord` format along with an additional feature\n", "that represents the ID of each sample. This is important and will allow us match\n", "sample embeddings with corresponding nodes in the graph later." ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:18.990912Z", "iopub.status.busy": "2022-12-14T12:19:18.990140Z", "iopub.status.idle": "2022-12-14T12:19:19.259304Z", "shell.execute_reply": "2022-12-14T12:19:19.258527Z" }, "id": "nq2Ohd9CuZv_" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "WARNING:tensorflow:Please fix your imports. Module tensorflow.python.training.tracking.data_structures has been moved to tensorflow.python.trackable.data_structures. The old module will be deleted in version 2.11.\n" ] } ], "source": [ "pretrained_embedding = 'https://tfhub.dev/google/tf2-preview/gnews-swivel-20dim/1'\n", "\n", "hub_layer = hub.KerasLayer(\n", " pretrained_embedding, input_shape=[], dtype=tf.string, trainable=True)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:19.263362Z", "iopub.status.busy": "2022-12-14T12:19:19.262820Z", "iopub.status.idle": "2022-12-14T12:19:50.982954Z", "shell.execute_reply": "2022-12-14T12:19:50.982090Z" }, "id": "wXJ3RaboTSKQ" }, "outputs": [ { "data": { "text/plain": [ "25000" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def _int64_feature(value):\n", " \"\"\"Returns int64 tf.train.Feature.\"\"\"\n", " return tf.train.Feature(int64_list=tf.train.Int64List(value=value.tolist()))\n", "\n", "\n", "def _bytes_feature(value):\n", " \"\"\"Returns bytes tf.train.Feature.\"\"\"\n", " return tf.train.Feature(\n", " bytes_list=tf.train.BytesList(value=[value.encode('utf-8')]))\n", "\n", "\n", "def _float_feature(value):\n", " \"\"\"Returns float tf.train.Feature.\"\"\"\n", " return tf.train.Feature(float_list=tf.train.FloatList(value=value.tolist()))\n", "\n", "\n", "def create_embedding_example(word_vector, record_id):\n", " \"\"\"Create tf.Example containing the sample's embedding and its ID.\"\"\"\n", "\n", " text = decode_review(word_vector)\n", "\n", " # Shape = [batch_size,].\n", " sentence_embedding = hub_layer(tf.reshape(text, shape=[-1,]))\n", "\n", " # Flatten the sentence embedding back to 1-D.\n", " sentence_embedding = tf.reshape(sentence_embedding, shape=[-1])\n", "\n", " features = {\n", " 'id': _bytes_feature(str(record_id)),\n", " 'embedding': _float_feature(sentence_embedding.numpy())\n", " }\n", " return tf.train.Example(features=tf.train.Features(feature=features))\n", "\n", "\n", "def create_embeddings(word_vectors, output_path, starting_record_id):\n", " record_id = int(starting_record_id)\n", " with tf.io.TFRecordWriter(output_path) as writer:\n", " for word_vector in word_vectors:\n", " example = create_embedding_example(word_vector, record_id)\n", " record_id = record_id + 1\n", " writer.write(example.SerializeToString())\n", " return record_id\n", "\n", "\n", "# Persist TF.Example features containing embeddings for training data in\n", "# TFRecord format.\n", "create_embeddings(pp_train_data, '/tmp/imdb/embeddings.tfr', 0)" ] }, { "cell_type": "markdown", "metadata": { "id": "C8s06RuI_vKs" }, "source": [ "### Build a graph\n", "\n", "Now that we have the sample embeddings, we will use them to build a similarity\n", "graph, i.e, nodes in this graph will correspond to samples and edges in this\n", "graph will correspond to similarity between pairs of nodes.\n", "\n", "Neural Structured Learning provides a graph building library to build a graph\n", "based on sample embeddings. It uses\n", "[**cosine similarity**](https://en.wikipedia.org/wiki/Cosine_similarity) as the\n", "similarity measure to compare embeddings and build edges between them. It also\n", "allows us to specify a similarity threshold, which can be used to discard\n", "dissimilar edges from the final graph. In this example, using 0.99 as the\n", "similarity threshold and 12345 as the random seed, we end up with a graph that\n", "has 429,415 bi-directional edges. Here we're using the graph builder's support\n", "for [locality-sensitive hashing](https://en.wikipedia.org/wiki/Locality-sensitive_hashing)\n", "(LSH) to speed up graph building. For details on using the graph builder's LSH\n", "support, see the\n", "[`build_graph_from_config`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/tools/build_graph_from_config)\n", "API documentation." ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:19:50.987068Z", "iopub.status.busy": "2022-12-14T12:19:50.986355Z", "iopub.status.idle": "2022-12-14T12:21:31.968529Z", "shell.execute_reply": "2022-12-14T12:21:31.967611Z" }, "id": "DY6lqhNkBh2Q" }, "outputs": [], "source": [ "graph_builder_config = nsl.configs.GraphBuilderConfig(\n", " similarity_threshold=0.99, lsh_splits=32, lsh_rounds=15, random_seed=12345)\n", "nsl.tools.build_graph_from_config(['/tmp/imdb/embeddings.tfr'],\n", " '/tmp/imdb/graph_99.tsv',\n", " graph_builder_config)" ] }, { "cell_type": "markdown", "metadata": { "id": "4dk9xfQcK553" }, "source": [ "Each bi-directional edge is represented by two directed edges in the output TSV\n", "file, so that file contains 429,415 * 2 = 858,830 total lines:" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:21:31.973414Z", "iopub.status.busy": "2022-12-14T12:21:31.972894Z", "iopub.status.idle": "2022-12-14T12:21:32.118624Z", "shell.execute_reply": "2022-12-14T12:21:32.117580Z" }, "id": "dDPwTpZcJ3zF" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "858830 /tmp/imdb/graph_99.tsv\r\n" ] } ], "source": [ "!wc -l /tmp/imdb/graph_99.tsv" ] }, { "cell_type": "markdown", "metadata": { "id": "06QrEVCIlTvV" }, "source": [ "**Note:** Graph quality and by extension, embedding quality, are very important\n", "for graph regularization. While we have used Swivel embeddings in this notebook,\n", "using BERT embeddings for instance, will likely capture review semantics more\n", "accurately. We encourage users to use embeddings of their choice and as\n", "appropriate to their needs." ] }, { "cell_type": "markdown", "metadata": { "id": "_USkfut69gNW" }, "source": [ "## Sample features\n", "\n", "We create sample features for our problem using the `tf.train.Example` format\n", "and persist them in the `TFRecord` format. Each sample will include the\n", "following three features:\n", "\n", "1. **id**: The node ID of the sample.\n", "2. **words**: An int64 list containing word IDs.\n", "3. **label**: A singleton int64 identifying the target class of the review." ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:21:32.123452Z", "iopub.status.busy": "2022-12-14T12:21:32.122918Z", "iopub.status.idle": "2022-12-14T12:21:37.738855Z", "shell.execute_reply": "2022-12-14T12:21:37.737999Z" }, "id": "9PcUF4_B9grB" }, "outputs": [ { "data": { "text/plain": [ "50000" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def create_example(word_vector, label, record_id):\n", " \"\"\"Create tf.Example containing the sample's word vector, label, and ID.\"\"\"\n", " features = {\n", " 'id': _bytes_feature(str(record_id)),\n", " 'words': _int64_feature(np.asarray(word_vector)),\n", " 'label': _int64_feature(np.asarray([label])),\n", " }\n", " return tf.train.Example(features=tf.train.Features(feature=features))\n", "\n", "def create_records(word_vectors, labels, record_path, starting_record_id):\n", " record_id = int(starting_record_id)\n", " with tf.io.TFRecordWriter(record_path) as writer:\n", " for word_vector, label in zip(word_vectors, labels):\n", " example = create_example(word_vector, label, record_id)\n", " record_id = record_id + 1\n", " writer.write(example.SerializeToString())\n", " return record_id\n", "\n", "# Persist TF.Example features (word vectors and labels) for training and test\n", "# data in TFRecord format.\n", "next_record_id = create_records(pp_train_data, pp_train_labels,\n", " '/tmp/imdb/train_data.tfr', 0)\n", "create_records(pp_test_data, pp_test_labels, '/tmp/imdb/test_data.tfr',\n", " next_record_id)" ] }, { "cell_type": "markdown", "metadata": { "id": "rhFO9sZ8Aa_g" }, "source": [ "## Augment training data with graph neighbors\n", "\n", "Since we have the sample features and the synthesized graph, we can generate the\n", "augmented training data for Neural Structured Learning. The NSL framework\n", "provides a library to combine the graph and the sample features to produce\n", "the final training data for graph regularization. The resulting training data\n", "will include original sample features as well as features of their corresponding\n", "neighbors.\n", "\n", "In this tutorial, we consider undirected edges and use a maximum of 3 neighbors\n", "per sample to augment training data with graph neighbors." ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:21:37.742705Z", "iopub.status.busy": "2022-12-14T12:21:37.742132Z", "iopub.status.idle": "2022-12-14T12:21:49.727368Z", "shell.execute_reply": "2022-12-14T12:21:49.726497Z" }, "id": "lSCHj4rIBj_A" }, "outputs": [], "source": [ "nsl.tools.pack_nbrs(\n", " '/tmp/imdb/train_data.tfr',\n", " '',\n", " '/tmp/imdb/graph_99.tsv',\n", " '/tmp/imdb/nsl_train_data.tfr',\n", " add_undirected_edges=True,\n", " max_nbrs=3)" ] }, { "cell_type": "markdown", "metadata": { "id": "AzBWdWkBqlMy" }, "source": [ "## Base model\n", "\n", "We are now ready to build a base model without graph regularization. In order to\n", "build this model, we can either use embeddings that were used in building the\n", "graph, or we can learn new embeddings jointly along with the classification\n", "task. For the purpose of this notebook, we will do the latter." ] }, { "cell_type": "markdown", "metadata": { "id": "kLSbRFguBUNl" }, "source": [ "### Global variables" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:21:49.731618Z", "iopub.status.busy": "2022-12-14T12:21:49.731250Z", "iopub.status.idle": "2022-12-14T12:21:49.734796Z", "shell.execute_reply": "2022-12-14T12:21:49.734134Z" }, "id": "zsA8HuvvwGri" }, "outputs": [], "source": [ "NBR_FEATURE_PREFIX = 'NL_nbr_'\n", "NBR_WEIGHT_SUFFIX = '_weight'" ] }, { "cell_type": "markdown", "metadata": { "id": "s8gMVBw6t6CI" }, "source": [ "### Hyperparameters\n", "\n", "We will use an instance of `HParams` to inclue various hyperparameters and\n", "constants used for training and evaluation. We briefly describe each of them\n", "below:\n", "\n", "- **num_classes**: There are 2 classes -- *positive* and *negative*.\n", "\n", "- **max_seq_length**: This is the maximum number of words considered from each\n", " movie review in this example.\n", "\n", "- **vocab_size**: This is the size of the vocabulary considered for this\n", " example.\n", "\n", "- **distance_type**: This is the distance metric used to regularize the sample\n", " with its neighbors.\n", "\n", "- **graph_regularization_multiplier**: This controls the relative weight of\n", " the graph regularization term in the overall loss function.\n", "\n", "- **num_neighbors**: The number of neighbors used for graph regularization.\n", " This value has to be less than or equal to the `max_nbrs` argument used\n", " above when invoking `nsl.tools.pack_nbrs`.\n", "\n", "- **num_fc_units**: The number of units in the fully connected layer of the\n", " neural network.\n", "\n", "- **train_epochs**: The number of training epochs.\n", "\n", "- **batch_size**: Batch size used for training and evaluation.\n", "\n", "- **eval_steps**: The number of batches to process before deeming evaluation\n", " is complete. If set to `None`, all instances in the test set are evaluated." ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:21:49.738379Z", "iopub.status.busy": "2022-12-14T12:21:49.737740Z", "iopub.status.idle": "2022-12-14T12:21:49.744388Z", "shell.execute_reply": "2022-12-14T12:21:49.743545Z" }, "id": "YlTmug7auQ2r" }, "outputs": [], "source": [ "class HParams(object):\n", " \"\"\"Hyperparameters used for training.\"\"\"\n", " def __init__(self):\n", " ### dataset parameters\n", " self.num_classes = 2\n", " self.max_seq_length = 256\n", " self.vocab_size = 10000\n", " ### neural graph learning parameters\n", " self.distance_type = nsl.configs.DistanceType.L2\n", " self.graph_regularization_multiplier = 0.1\n", " self.num_neighbors = 2\n", " ### model architecture\n", " self.num_embedding_dims = 16\n", " self.num_lstm_dims = 64\n", " self.num_fc_units = 64\n", " ### training parameters\n", " self.train_epochs = 10\n", " self.batch_size = 128\n", " ### eval parameters\n", " self.eval_steps = None # All instances in the test set are evaluated.\n", "\n", "HPARAMS = HParams()" ] }, { "cell_type": "markdown", "metadata": { "id": "lFP_XKVRp4_S" }, "source": [ "### Prepare the data\n", "\n", "The reviews—the arrays of integers—must be converted to tensors before being fed\n", "into the neural network. This conversion can be done a couple of ways:\n", "\n", "* Convert the arrays into vectors of `0`s and `1`s indicating word occurrence,\n", " similar to a one-hot encoding. For example, the sequence `[3, 5]` would become a `10000`-dimensional vector that is all zeros except for indices `3` and `5`, which are ones. Then, make this the first layer in our network—a `Dense` layer—that can handle floating point vector data. This approach is memory intensive, though, requiring a `num_words * num_reviews` size matrix.\n", "\n", "* Alternatively, we can pad the arrays so they all have the same length, then\n", " create an integer tensor of shape `max_length * num_reviews`. We can use an\n", " embedding layer capable of handling this shape as the first layer in our\n", " network.\n", "\n", "In this tutorial, we will use the second approach.\n", "\n", "Since the movie reviews must be the same length, we will use the `pad_sequence`\n", "function defined below to standardize the lengths." ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:21:49.747723Z", "iopub.status.busy": "2022-12-14T12:21:49.747477Z", "iopub.status.idle": "2022-12-14T12:21:50.047265Z", "shell.execute_reply": "2022-12-14T12:21:50.046494Z" }, "id": "J5lkZVynuHWs" }, "outputs": [], "source": [ "def make_dataset(file_path, training=False):\n", " \"\"\"Creates a `tf.data.TFRecordDataset`.\n", "\n", " Args:\n", " file_path: Name of the file in the `.tfrecord` format containing\n", " `tf.train.Example` objects.\n", " training: Boolean indicating if we are in training mode.\n", "\n", " Returns:\n", " An instance of `tf.data.TFRecordDataset` containing the `tf.train.Example`\n", " objects.\n", " \"\"\"\n", "\n", " def pad_sequence(sequence, max_seq_length):\n", " \"\"\"Pads the input sequence (a `tf.SparseTensor`) to `max_seq_length`.\"\"\"\n", " pad_size = tf.maximum([0], max_seq_length - tf.shape(sequence)[0])\n", " padded = tf.concat(\n", " [sequence.values,\n", " tf.fill((pad_size), tf.cast(0, sequence.dtype))],\n", " axis=0)\n", " # The input sequence may be larger than max_seq_length. Truncate down if\n", " # necessary.\n", " return tf.slice(padded, [0], [max_seq_length])\n", "\n", " def parse_example(example_proto):\n", " \"\"\"Extracts relevant fields from the `example_proto`.\n", "\n", " Args:\n", " example_proto: An instance of `tf.train.Example`.\n", "\n", " Returns:\n", " A pair whose first value is a dictionary containing relevant features\n", " and whose second value contains the ground truth labels.\n", " \"\"\"\n", " # The 'words' feature is a variable length word ID vector.\n", " feature_spec = {\n", " 'words': tf.io.VarLenFeature(tf.int64),\n", " 'label': tf.io.FixedLenFeature((), tf.int64, default_value=-1),\n", " }\n", " # We also extract corresponding neighbor features in a similar manner to\n", " # the features above during training.\n", " if training:\n", " for i in range(HPARAMS.num_neighbors):\n", " nbr_feature_key = '{}{}_{}'.format(NBR_FEATURE_PREFIX, i, 'words')\n", " nbr_weight_key = '{}{}{}'.format(NBR_FEATURE_PREFIX, i,\n", " NBR_WEIGHT_SUFFIX)\n", " feature_spec[nbr_feature_key] = tf.io.VarLenFeature(tf.int64)\n", "\n", " # We assign a default value of 0.0 for the neighbor weight so that\n", " # graph regularization is done on samples based on their exact number\n", " # of neighbors. In other words, non-existent neighbors are discounted.\n", " feature_spec[nbr_weight_key] = tf.io.FixedLenFeature(\n", " [1], tf.float32, default_value=tf.constant([0.0]))\n", "\n", " features = tf.io.parse_single_example(example_proto, feature_spec)\n", "\n", " # Since the 'words' feature is a variable length word vector, we pad it to a\n", " # constant maximum length based on HPARAMS.max_seq_length\n", " features['words'] = pad_sequence(features['words'], HPARAMS.max_seq_length)\n", " if training:\n", " for i in range(HPARAMS.num_neighbors):\n", " nbr_feature_key = '{}{}_{}'.format(NBR_FEATURE_PREFIX, i, 'words')\n", " features[nbr_feature_key] = pad_sequence(features[nbr_feature_key],\n", " HPARAMS.max_seq_length)\n", "\n", " labels = features.pop('label')\n", " return features, labels\n", "\n", " dataset = tf.data.TFRecordDataset([file_path])\n", " if training:\n", " dataset = dataset.shuffle(10000)\n", " dataset = dataset.map(parse_example)\n", " dataset = dataset.batch(HPARAMS.batch_size)\n", " return dataset\n", "\n", "\n", "train_dataset = make_dataset('/tmp/imdb/nsl_train_data.tfr', True)\n", "test_dataset = make_dataset('/tmp/imdb/test_data.tfr')" ] }, { "cell_type": "markdown", "metadata": { "id": "LLC02j2g-llC" }, "source": [ "### Build the model\n", "\n", "A neural network is created by stacking layers—this requires two main architectural decisions:\n", "\n", "* How many layers to use in the model?\n", "* How many *hidden units* to use for each layer?\n", "\n", "In this example, the input data consists of an array of word-indices. The labels to predict are either 0 or 1.\n", "\n", "We will use a bi-directional LSTM as our base model in this tutorial." ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:21:50.051517Z", "iopub.status.busy": "2022-12-14T12:21:50.050978Z", "iopub.status.idle": "2022-12-14T12:21:50.591636Z", "shell.execute_reply": "2022-12-14T12:21:50.590908Z" }, "id": "xpKOoWgu-llD" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"model\"\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "_________________________________________________________________\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " Layer (type) Output Shape Param # \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "=================================================================\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " words (InputLayer) [(None, 256)] 0 \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " embedding (Embedding) (None, 256, 16) 160000 \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " bidirectional (Bidirectiona (None, 128) 41472 \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " l) \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " dense (Dense) (None, 64) 8256 \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " dense_1 (Dense) (None, 1) 65 \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "=================================================================\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Total params: 209,793\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Trainable params: 209,793\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Non-trainable params: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "_________________________________________________________________\n" ] } ], "source": [ "# This function exists as an alternative to the bi-LSTM model used in this\n", "# notebook.\n", "def make_feed_forward_model():\n", " \"\"\"Builds a simple 2 layer feed forward neural network.\"\"\"\n", " inputs = tf.keras.Input(\n", " shape=(HPARAMS.max_seq_length,), dtype='int64', name='words')\n", " embedding_layer = tf.keras.layers.Embedding(HPARAMS.vocab_size, 16)(inputs)\n", " pooling_layer = tf.keras.layers.GlobalAveragePooling1D()(embedding_layer)\n", " dense_layer = tf.keras.layers.Dense(16, activation='relu')(pooling_layer)\n", " outputs = tf.keras.layers.Dense(1)(dense_layer)\n", " return tf.keras.Model(inputs=inputs, outputs=outputs)\n", "\n", "\n", "def make_bilstm_model():\n", " \"\"\"Builds a bi-directional LSTM model.\"\"\"\n", " inputs = tf.keras.Input(\n", " shape=(HPARAMS.max_seq_length,), dtype='int64', name='words')\n", " embedding_layer = tf.keras.layers.Embedding(HPARAMS.vocab_size,\n", " HPARAMS.num_embedding_dims)(\n", " inputs)\n", " lstm_layer = tf.keras.layers.Bidirectional(\n", " tf.keras.layers.LSTM(HPARAMS.num_lstm_dims))(\n", " embedding_layer)\n", " dense_layer = tf.keras.layers.Dense(\n", " HPARAMS.num_fc_units, activation='relu')(\n", " lstm_layer)\n", " outputs = tf.keras.layers.Dense(1)(dense_layer)\n", " return tf.keras.Model(inputs=inputs, outputs=outputs)\n", "\n", "\n", "# Feel free to use an architecture of your choice.\n", "model = make_bilstm_model()\n", "model.summary()" ] }, { "cell_type": "markdown", "metadata": { "id": "6PbKQ6mucuKL" }, "source": [ "The layers are effectively stacked sequentially to build the classifier:\n", "\n", "1. The first layer is an `Input` layer which takes the integer-encoded\n", " vocabulary.\n", "2. The next layer is an `Embedding` layer, which takes the integer-encoded\n", " vocabulary and looks up the embedding vector for each word-index. These\n", " vectors are learned as the model trains. The vectors add a dimension to the\n", " output array. The resulting dimensions are: `(batch, sequence, embedding)`.\n", "3. Next, a bidirectional LSTM layer returns a fixed-length output vector for\n", " each example.\n", "4. This fixed-length output vector is piped through a fully-connected (`Dense`)\n", " layer with 64 hidden units.\n", "5. The last layer is densely connected with a single output node. Using the\n", " `sigmoid` activation function, this value is a float between 0 and 1,\n", " representing a probability, or confidence level." ] }, { "cell_type": "markdown", "metadata": { "id": "0XMwnDOp-llH" }, "source": [ "### Hidden units\n", "\n", "The above model has two intermediate or \"hidden\" layers, between the input and\n", "output, and excluding the `Embedding` layer. The number of outputs (units,\n", "nodes, or neurons) is the dimension of the representational space for the layer.\n", "In other words, the amount of freedom the network is allowed when learning an\n", "internal representation.\n", "\n", "If a model has more hidden units (a higher-dimensional representation space),\n", "and/or more layers, then the network can learn more complex representations.\n", "However, it makes the network more computationally expensive and may lead to\n", "learning unwanted patterns—patterns that improve performance on training data\n", "but not on the test data. This is called *overfitting*." ] }, { "cell_type": "markdown", "metadata": { "id": "L4EqVWg4-llM" }, "source": [ "### Loss function and optimizer\n", "\n", "A model needs a loss function and an optimizer for training. Since this is a\n", "binary classification problem and the model outputs a probability (a single-unit\n", "layer with a sigmoid activation), we'll use the `binary_crossentropy` loss\n", "function." ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:21:50.599787Z", "iopub.status.busy": "2022-12-14T12:21:50.599174Z", "iopub.status.idle": "2022-12-14T12:21:50.613008Z", "shell.execute_reply": "2022-12-14T12:21:50.612326Z" }, "id": "Mr0GP-cQ-llN" }, "outputs": [], "source": [ "model.compile(\n", " optimizer='adam',\n", " loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),\n", " metrics=['accuracy'])" ] }, { "cell_type": "markdown", "metadata": { "id": "hCWYwkug-llQ" }, "source": [ "### Create a validation set\n", "\n", "When training, we want to check the accuracy of the model on data it hasn't seen\n", "before. Create a *validation set* by setting apart a fraction of the original\n", "training data. (Why not use the testing set now? Our goal is to develop and tune\n", "our model using only the training data, then use the test data just once to\n", "evaluate our accuracy).\n", "\n", "In this tutorial, we take roughly 10% of the initial training samples (10% of 25000) as labeled data for training and the remaining as validation data. Since the initial train/test split was 50/50 (25000 samples each), the effective train/validation/test split we now have is 5/45/50.\n", "\n", "Note that 'train_dataset' has already been batched and shuffled. " ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:21:50.616527Z", "iopub.status.busy": "2022-12-14T12:21:50.615995Z", "iopub.status.idle": "2022-12-14T12:21:50.622837Z", "shell.execute_reply": "2022-12-14T12:21:50.622180Z" }, "id": "oYTf7zkZQ-Dl" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "175\n" ] } ], "source": [ "validation_fraction = 0.9\n", "validation_size = int(validation_fraction *\n", " int(training_samples_count / HPARAMS.batch_size))\n", "print(validation_size)\n", "validation_dataset = train_dataset.take(validation_size)\n", "train_dataset = train_dataset.skip(validation_size)" ] }, { "cell_type": "markdown", "metadata": { "id": "35jv_fzP-llU" }, "source": [ "### Train the model\n", "\n", "Train the model in mini-batches. While training, monitor the model's loss and accuracy on the validation set:" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:21:50.626149Z", "iopub.status.busy": "2022-12-14T12:21:50.625668Z", "iopub.status.idle": "2022-12-14T12:24:31.449358Z", "shell.execute_reply": "2022-12-14T12:24:31.448532Z" }, "id": "BLWzgfF1xpDu" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/10\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/tmpfs/src/tf_docs_env/lib/python3.9/site-packages/keras/engine/functional.py:638: UserWarning: Input dict contained keys ['NL_nbr_0_words', 'NL_nbr_1_words', 'NL_nbr_0_weight', 'NL_nbr_1_weight'] which did not match any model input. They will be ignored by the model.\n", " inputs = self._flatten_to_reference_inputs(inputs)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/Unknown - 5s 5s/step - loss: 0.6936 - accuracy: 0.4453" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/Unknown - 5s 177ms/step - loss: 0.6934 - accuracy: 0.4805" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/Unknown - 5s 169ms/step - loss: 0.6932 - accuracy: 0.5000" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/Unknown - 5s 165ms/step - loss: 0.6933 - accuracy: 0.4980" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/Unknown - 5s 164ms/step - loss: 0.6932 - accuracy: 0.5109" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/Unknown - 5s 162ms/step - loss: 0.6935 - accuracy: 0.4974" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/Unknown - 6s 162ms/step - loss: 0.6933 - accuracy: 0.5022" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/Unknown - 6s 161ms/step - loss: 0.6935 - accuracy: 0.4893" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/Unknown - 6s 160ms/step - loss: 0.6934 - accuracy: 0.4922" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 10/Unknown - 6s 160ms/step - loss: 0.6934 - accuracy: 0.4906" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 11/Unknown - 6s 160ms/step - loss: 0.6933 - accuracy: 0.4886" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 12/Unknown - 6s 159ms/step - loss: 0.6932 - accuracy: 0.4863" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 13/Unknown - 7s 159ms/step - loss: 0.6932 - accuracy: 0.4844" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 14/Unknown - 7s 159ms/step - loss: 0.6932 - accuracy: 0.4872" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 15/Unknown - 7s 159ms/step - loss: 0.6932 - accuracy: 0.4911" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 16/Unknown - 7s 159ms/step - loss: 0.6932 - accuracy: 0.4907" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 17/Unknown - 7s 158ms/step - loss: 0.6931 - accuracy: 0.4903" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 18/Unknown - 7s 158ms/step - loss: 0.6930 - accuracy: 0.4878" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 19/Unknown - 8s 158ms/step - loss: 0.6928 - accuracy: 0.4864" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 20/Unknown - 8s 158ms/step - loss: 0.6928 - accuracy: 0.4840" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 21/Unknown - 8s 154ms/step - loss: 0.6928 - accuracy: 0.4850" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 20s 790ms/step - loss: 0.6928 - accuracy: 0.4850 - val_loss: 0.6927 - val_accuracy: 0.5001\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 2/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 11s - loss: 0.6911 - accuracy: 0.4922" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 2s - loss: 0.6916 - accuracy: 0.5000 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 2s - loss: 0.6920 - accuracy: 0.5078" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 2s - loss: 0.6916 - accuracy: 0.4941" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 2s - loss: 0.6919 - accuracy: 0.5016" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 2s - loss: 0.6915 - accuracy: 0.4948" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 2s - loss: 0.6913 - accuracy: 0.4944" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 2s - loss: 0.6913 - accuracy: 0.5000" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 1s - loss: 0.6911 - accuracy: 0.5017" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 1s - loss: 0.6909 - accuracy: 0.5063" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 1s - loss: 0.6906 - accuracy: 0.5021" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 1s - loss: 0.6907 - accuracy: 0.4987" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.6905 - accuracy: 0.5000" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.6901 - accuracy: 0.4994" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 0s - loss: 0.6897 - accuracy: 0.5016" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 0s - loss: 0.6891 - accuracy: 0.5039" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.6893 - accuracy: 0.5041" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.6884 - accuracy: 0.5048" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.6865 - accuracy: 0.5025" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.6852 - accuracy: 0.5012" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.6847 - accuracy: 0.5019" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 15s 739ms/step - loss: 0.6847 - accuracy: 0.5019 - val_loss: 0.6387 - val_accuracy: 0.5028\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 3/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 12s - loss: 0.6426 - accuracy: 0.4609" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 2s - loss: 0.6260 - accuracy: 0.5664 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 2s - loss: 0.6241 - accuracy: 0.5781" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 2s - loss: 0.6599 - accuracy: 0.5820" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 2s - loss: 0.6760 - accuracy: 0.5813" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 2s - loss: 0.6748 - accuracy: 0.6016" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 2s - loss: 0.6675 - accuracy: 0.5893" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 2s - loss: 0.6649 - accuracy: 0.5830" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 1s - loss: 0.6632 - accuracy: 0.5773" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 1s - loss: 0.6629 - accuracy: 0.5711" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 1s - loss: 0.6631 - accuracy: 0.5625" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 1s - loss: 0.6630 - accuracy: 0.5566" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.6640 - accuracy: 0.5493" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.6643 - accuracy: 0.5463" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 0s - loss: 0.6672 - accuracy: 0.5328" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 0s - loss: 0.6662 - accuracy: 0.5366" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.6658 - accuracy: 0.5340" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.6652 - accuracy: 0.5352" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.6644 - accuracy: 0.5370" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.6647 - accuracy: 0.5328" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.6641 - accuracy: 0.5350" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 15s 741ms/step - loss: 0.6641 - accuracy: 0.5350 - val_loss: 0.6572 - val_accuracy: 0.5002\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 4/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 12s - loss: 0.6663 - accuracy: 0.4297" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 3s - loss: 0.6604 - accuracy: 0.4844 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 2s - loss: 0.6582 - accuracy: 0.4792" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 2s - loss: 0.6528 - accuracy: 0.4883" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 2s - loss: 0.6485 - accuracy: 0.5000" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 2s - loss: 0.6472 - accuracy: 0.5039" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 2s - loss: 0.6451 - accuracy: 0.4989" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 2s - loss: 0.6450 - accuracy: 0.5010" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 1s - loss: 0.6430 - accuracy: 0.5000" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 1s - loss: 0.6442 - accuracy: 0.4984" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 1s - loss: 0.6414 - accuracy: 0.5000" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 1s - loss: 0.6376 - accuracy: 0.5013" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.6343 - accuracy: 0.4976" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.6294 - accuracy: 0.4950" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 0s - loss: 0.6253 - accuracy: 0.4953" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 0s - loss: 0.6200 - accuracy: 0.5020" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.6158 - accuracy: 0.5147" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.6132 - accuracy: 0.5265" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.6095 - accuracy: 0.5345" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.6048 - accuracy: 0.5469" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.6083 - accuracy: 0.5504" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 15s 740ms/step - loss: 0.6083 - accuracy: 0.5504 - val_loss: 0.5291 - val_accuracy: 0.7685\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 5/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 11s - loss: 0.5490 - accuracy: 0.7656" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 2s - loss: 0.5387 - accuracy: 0.7695 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 2s - loss: 0.5384 - accuracy: 0.7474" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 2s - loss: 0.5268 - accuracy: 0.7383" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 2s - loss: 0.5101 - accuracy: 0.7266" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 2s - loss: 0.5293 - accuracy: 0.7214" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 2s - loss: 0.5221 - accuracy: 0.7121" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 2s - loss: 0.5197 - accuracy: 0.7148" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 1s - loss: 0.5164 - accuracy: 0.7266" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 1s - loss: 0.5164 - accuracy: 0.7352" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 1s - loss: 0.5193 - accuracy: 0.7401" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 1s - loss: 0.5113 - accuracy: 0.7500" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.5085 - accuracy: 0.7494" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.5075 - accuracy: 0.7478" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 0s - loss: 0.5025 - accuracy: 0.7479" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 0s - loss: 0.4962 - accuracy: 0.7534" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.4955 - accuracy: 0.7574" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.4979 - accuracy: 0.7561" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.4933 - accuracy: 0.7611" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.4929 - accuracy: 0.7625" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.4911 - accuracy: 0.7635" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 15s 742ms/step - loss: 0.4911 - accuracy: 0.7635 - val_loss: 0.4327 - val_accuracy: 0.8143\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 6/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 11s - loss: 0.3969 - accuracy: 0.8281" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 2s - loss: 0.3947 - accuracy: 0.8398 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 2s - loss: 0.4379 - accuracy: 0.8151" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 2s - loss: 0.4397 - accuracy: 0.8223" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 2s - loss: 0.4330 - accuracy: 0.8219" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 2s - loss: 0.4219 - accuracy: 0.8307" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 2s - loss: 0.4209 - accuracy: 0.8304" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 2s - loss: 0.4186 - accuracy: 0.8271" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 1s - loss: 0.4233 - accuracy: 0.8247" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 1s - loss: 0.4198 - accuracy: 0.8211" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 1s - loss: 0.4140 - accuracy: 0.8246" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 1s - loss: 0.4133 - accuracy: 0.8275" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.4139 - accuracy: 0.8281" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.4166 - accuracy: 0.8265" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 0s - loss: 0.4113 - accuracy: 0.8281" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 0s - loss: 0.4085 - accuracy: 0.8281" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.4048 - accuracy: 0.8286" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.3959 - accuracy: 0.8312" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.3942 - accuracy: 0.8318" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.3923 - accuracy: 0.8301" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.3924 - accuracy: 0.8304" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 15s 741ms/step - loss: 0.3924 - accuracy: 0.8304 - val_loss: 0.3821 - val_accuracy: 0.8529\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 7/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 11s - loss: 0.4174 - accuracy: 0.8516" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 2s - loss: 0.3693 - accuracy: 0.8594 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 2s - loss: 0.3881 - accuracy: 0.8438" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 2s - loss: 0.3750 - accuracy: 0.8516" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 2s - loss: 0.3749 - accuracy: 0.8469" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 2s - loss: 0.3688 - accuracy: 0.8529" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 2s - loss: 0.3742 - accuracy: 0.8504" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 2s - loss: 0.3718 - accuracy: 0.8496" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 1s - loss: 0.3722 - accuracy: 0.8472" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 1s - loss: 0.3626 - accuracy: 0.8484" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 1s - loss: 0.3656 - accuracy: 0.8438" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 1s - loss: 0.3574 - accuracy: 0.8490" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.3532 - accuracy: 0.8522" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.3527 - accuracy: 0.8510" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 0s - loss: 0.3536 - accuracy: 0.8521" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 0s - loss: 0.3506 - accuracy: 0.8555" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.3511 - accuracy: 0.8552" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.3480 - accuracy: 0.8585" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.3455 - accuracy: 0.8606" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.3452 - accuracy: 0.8613" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.3449 - accuracy: 0.8612" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 15s 746ms/step - loss: 0.3449 - accuracy: 0.8612 - val_loss: 0.3550 - val_accuracy: 0.8145\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 8/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 11s - loss: 0.3601 - accuracy: 0.8203" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 3s - loss: 0.3360 - accuracy: 0.8164 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 2s - loss: 0.3377 - accuracy: 0.8177" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 2s - loss: 0.3117 - accuracy: 0.8438" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 2s - loss: 0.3033 - accuracy: 0.8547" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 2s - loss: 0.2880 - accuracy: 0.8659" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 2s - loss: 0.2977 - accuracy: 0.8672" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 2s - loss: 0.2961 - accuracy: 0.8721" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 1s - loss: 0.2896 - accuracy: 0.8767" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 1s - loss: 0.2917 - accuracy: 0.8750" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 1s - loss: 0.2956 - accuracy: 0.8743" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 1s - loss: 0.2989 - accuracy: 0.8743" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.2966 - accuracy: 0.8768" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.2938 - accuracy: 0.8783" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 0s - loss: 0.3030 - accuracy: 0.8719" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 0s - loss: 0.3039 - accuracy: 0.8721" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.3020 - accuracy: 0.8741" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.2995 - accuracy: 0.8763" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.2960 - accuracy: 0.8787" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.2977 - accuracy: 0.8789" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.2954 - accuracy: 0.8796" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 16s 753ms/step - loss: 0.2954 - accuracy: 0.8796 - val_loss: 0.3103 - val_accuracy: 0.8671\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 9/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 11s - loss: 0.4600 - accuracy: 0.8125" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 3s - loss: 0.3640 - accuracy: 0.8672 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 2s - loss: 0.3205 - accuracy: 0.8880" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 2s - loss: 0.3127 - accuracy: 0.8965" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 2s - loss: 0.3108 - accuracy: 0.8922" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 2s - loss: 0.3078 - accuracy: 0.8932" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 2s - loss: 0.3065 - accuracy: 0.8906" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 2s - loss: 0.3196 - accuracy: 0.8779" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 1s - loss: 0.3161 - accuracy: 0.8741" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 1s - loss: 0.3116 - accuracy: 0.8750" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 1s - loss: 0.3155 - accuracy: 0.8757" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 1s - loss: 0.3233 - accuracy: 0.8763" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.3270 - accuracy: 0.8738" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.3287 - accuracy: 0.8739" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 0s - loss: 0.3279 - accuracy: 0.8745" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 0s - loss: 0.3263 - accuracy: 0.8750" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.3291 - accuracy: 0.8709" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.3288 - accuracy: 0.8685" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.3318 - accuracy: 0.8697" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.3247 - accuracy: 0.8715" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.3243 - accuracy: 0.8719" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 16s 767ms/step - loss: 0.3243 - accuracy: 0.8719 - val_loss: 0.3371 - val_accuracy: 0.8733\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 10/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 12s - loss: 0.3584 - accuracy: 0.8594" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 3s - loss: 0.3493 - accuracy: 0.8633 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 3s - loss: 0.3370 - accuracy: 0.8724" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 2s - loss: 0.3406 - accuracy: 0.8613" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 2s - loss: 0.3291 - accuracy: 0.8641" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 2s - loss: 0.3246 - accuracy: 0.8607" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 2s - loss: 0.3251 - accuracy: 0.8605" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 2s - loss: 0.3173 - accuracy: 0.8643" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 2s - loss: 0.3175 - accuracy: 0.8637" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 1s - loss: 0.3091 - accuracy: 0.8672" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 1s - loss: 0.3060 - accuracy: 0.8686" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 1s - loss: 0.3068 - accuracy: 0.8704" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.3063 - accuracy: 0.8708" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.2997 - accuracy: 0.8739" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 1s - loss: 0.2977 - accuracy: 0.8750" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 0s - loss: 0.2948 - accuracy: 0.8755" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.2955 - accuracy: 0.8759" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.2936 - accuracy: 0.8772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.2957 - accuracy: 0.8758" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.2929 - accuracy: 0.8766" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.2918 - accuracy: 0.8765" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 16s 768ms/step - loss: 0.2918 - accuracy: 0.8765 - val_loss: 0.2845 - val_accuracy: 0.8944\n" ] } ], "source": [ "history = model.fit(\n", " train_dataset,\n", " validation_data=validation_dataset,\n", " epochs=HPARAMS.train_epochs,\n", " verbose=1)" ] }, { "cell_type": "markdown", "metadata": { "id": "9EEGuDVuzb5r" }, "source": [ "### Evaluate the model\n", "\n", "Now, let's see how the model performs. Two values will be returned. Loss (a number which represents our error, lower values are better), and accuracy." ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:24:31.453576Z", "iopub.status.busy": "2022-12-14T12:24:31.452928Z", "iopub.status.idle": "2022-12-14T12:24:45.759047Z", "shell.execute_reply": "2022-12-14T12:24:45.758260Z" }, "id": "6q7CoDfoCJ5h" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/Unknown - 1s 818ms/step - loss: 0.3000 - accuracy: 0.8672" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/Unknown - 1s 69ms/step - loss: 0.3210 - accuracy: 0.8594 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/Unknown - 1s 70ms/step - loss: 0.3523 - accuracy: 0.8438" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/Unknown - 1s 69ms/step - loss: 0.3396 - accuracy: 0.8574" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/Unknown - 1s 70ms/step - loss: 0.3527 - accuracy: 0.8516" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/Unknown - 1s 69ms/step - loss: 0.3494 - accuracy: 0.8542" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/Unknown - 1s 70ms/step - loss: 0.3465 - accuracy: 0.8560" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/Unknown - 1s 69ms/step - loss: 0.3529 - accuracy: 0.8555" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/Unknown - 1s 70ms/step - loss: 0.3471 - accuracy: 0.8585" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 10/Unknown - 1s 70ms/step - loss: 0.3549 - accuracy: 0.8547" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 11/Unknown - 2s 70ms/step - loss: 0.3559 - accuracy: 0.8530" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 12/Unknown - 2s 70ms/step - loss: 0.3471 - accuracy: 0.8568" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 13/Unknown - 2s 70ms/step - loss: 0.3455 - accuracy: 0.8588" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 14/Unknown - 2s 70ms/step - loss: 0.3536 - accuracy: 0.8549" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 15/Unknown - 2s 70ms/step - loss: 0.3530 - accuracy: 0.8552" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 16/Unknown - 2s 70ms/step - loss: 0.3490 - accuracy: 0.8555" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 17/Unknown - 2s 70ms/step - loss: 0.3483 - accuracy: 0.8571" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 18/Unknown - 2s 70ms/step - loss: 0.3502 - accuracy: 0.8550" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 19/Unknown - 2s 70ms/step - loss: 0.3502 - accuracy: 0.8549" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 20/Unknown - 2s 70ms/step - loss: 0.3559 - accuracy: 0.8520" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 21/Unknown - 2s 70ms/step - loss: 0.3563 - accuracy: 0.8523" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 22/Unknown - 2s 70ms/step - loss: 0.3597 - accuracy: 0.8516" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 23/Unknown - 2s 69ms/step - loss: 0.3589 - accuracy: 0.8519" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 24/Unknown - 2s 69ms/step - loss: 0.3572 - accuracy: 0.8525" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 25/Unknown - 2s 69ms/step - loss: 0.3634 - accuracy: 0.8516" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 26/Unknown - 3s 69ms/step - loss: 0.3634 - accuracy: 0.8507" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 27/Unknown - 3s 69ms/step - loss: 0.3628 - accuracy: 0.8510" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 28/Unknown - 3s 69ms/step - loss: 0.3651 - accuracy: 0.8496" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 29/Unknown - 3s 69ms/step - loss: 0.3696 - accuracy: 0.8478" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 30/Unknown - 3s 69ms/step - loss: 0.3701 - accuracy: 0.8484" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 31/Unknown - 3s 69ms/step - loss: 0.3732 - accuracy: 0.8470" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 32/Unknown - 3s 69ms/step - loss: 0.3725 - accuracy: 0.8469" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 33/Unknown - 3s 69ms/step - loss: 0.3752 - accuracy: 0.8459" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 34/Unknown - 3s 69ms/step - loss: 0.3744 - accuracy: 0.8463" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 35/Unknown - 3s 69ms/step - loss: 0.3721 - accuracy: 0.8478" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 36/Unknown - 3s 69ms/step - loss: 0.3711 - accuracy: 0.8485" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 37/Unknown - 3s 69ms/step - loss: 0.3709 - accuracy: 0.8486" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 38/Unknown - 3s 69ms/step - loss: 0.3712 - accuracy: 0.8485" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 39/Unknown - 3s 69ms/step - loss: 0.3712 - accuracy: 0.8480" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 40/Unknown - 4s 69ms/step - loss: 0.3716 - accuracy: 0.8479" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 41/Unknown - 4s 69ms/step - loss: 0.3709 - accuracy: 0.8483" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 42/Unknown - 4s 69ms/step - loss: 0.3689 - accuracy: 0.8493" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 43/Unknown - 4s 69ms/step - loss: 0.3697 - accuracy: 0.8487" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 44/Unknown - 4s 69ms/step - loss: 0.3707 - accuracy: 0.8493" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 45/Unknown - 4s 69ms/step - loss: 0.3709 - accuracy: 0.8500" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 46/Unknown - 4s 69ms/step - loss: 0.3708 - accuracy: 0.8505" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 47/Unknown - 4s 69ms/step - loss: 0.3725 - accuracy: 0.8497" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 48/Unknown - 4s 69ms/step - loss: 0.3735 - accuracy: 0.8494" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 49/Unknown - 4s 69ms/step - loss: 0.3749 - accuracy: 0.8490" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 50/Unknown - 4s 69ms/step - loss: 0.3748 - accuracy: 0.8492" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 51/Unknown - 4s 69ms/step - loss: 0.3747 - accuracy: 0.8493" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 52/Unknown - 4s 69ms/step - loss: 0.3753 - accuracy: 0.8496" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 53/Unknown - 4s 69ms/step - loss: 0.3760 - accuracy: 0.8495" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 54/Unknown - 4s 69ms/step - loss: 0.3767 - accuracy: 0.8494" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 55/Unknown - 5s 69ms/step - loss: 0.3756 - accuracy: 0.8500" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 56/Unknown - 5s 69ms/step - loss: 0.3757 - accuracy: 0.8499" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 57/Unknown - 5s 69ms/step - loss: 0.3763 - accuracy: 0.8501" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 58/Unknown - 5s 69ms/step - loss: 0.3752 - accuracy: 0.8504" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 59/Unknown - 5s 69ms/step - loss: 0.3751 - accuracy: 0.8505" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 60/Unknown - 5s 69ms/step - loss: 0.3755 - accuracy: 0.8507" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 61/Unknown - 5s 69ms/step - loss: 0.3752 - accuracy: 0.8508" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 62/Unknown - 5s 69ms/step - loss: 0.3749 - accuracy: 0.8511" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 63/Unknown - 5s 69ms/step - loss: 0.3751 - accuracy: 0.8512" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 64/Unknown - 5s 69ms/step - loss: 0.3751 - accuracy: 0.8516" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 65/Unknown - 5s 69ms/step - loss: 0.3770 - accuracy: 0.8508" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 66/Unknown - 5s 69ms/step - loss: 0.3761 - accuracy: 0.8509" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 67/Unknown - 5s 69ms/step - loss: 0.3766 - accuracy: 0.8510" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 68/Unknown - 5s 69ms/step - loss: 0.3775 - accuracy: 0.8504" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 69/Unknown - 6s 69ms/step - loss: 0.3760 - accuracy: 0.8510" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 70/Unknown - 6s 69ms/step - loss: 0.3758 - accuracy: 0.8510" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 71/Unknown - 6s 69ms/step - loss: 0.3739 - accuracy: 0.8515" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 72/Unknown - 6s 69ms/step - loss: 0.3757 - accuracy: 0.8508" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 73/Unknown - 6s 69ms/step - loss: 0.3759 - accuracy: 0.8505" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 74/Unknown - 6s 69ms/step - loss: 0.3766 - accuracy: 0.8504" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 75/Unknown - 6s 69ms/step - loss: 0.3764 - accuracy: 0.8502" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 76/Unknown - 6s 69ms/step - loss: 0.3772 - accuracy: 0.8495" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 77/Unknown - 6s 69ms/step - loss: 0.3772 - accuracy: 0.8493" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 78/Unknown - 6s 69ms/step - loss: 0.3772 - accuracy: 0.8491" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 79/Unknown - 6s 69ms/step - loss: 0.3776 - accuracy: 0.8490" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 80/Unknown - 6s 69ms/step - loss: 0.3787 - accuracy: 0.8483" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 81/Unknown - 6s 69ms/step - loss: 0.3804 - accuracy: 0.8479" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 82/Unknown - 6s 69ms/step - loss: 0.3816 - accuracy: 0.8477" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 83/Unknown - 6s 69ms/step - loss: 0.3815 - accuracy: 0.8474" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 84/Unknown - 7s 69ms/step - loss: 0.3819 - accuracy: 0.8477" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 85/Unknown - 7s 69ms/step - loss: 0.3821 - accuracy: 0.8475" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 86/Unknown - 7s 69ms/step - loss: 0.3817 - accuracy: 0.8478" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 87/Unknown - 7s 69ms/step - loss: 0.3815 - accuracy: 0.8479" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 88/Unknown - 7s 69ms/step - loss: 0.3818 - accuracy: 0.8478" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 89/Unknown - 7s 69ms/step - loss: 0.3816 - accuracy: 0.8479" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 90/Unknown - 7s 69ms/step - loss: 0.3834 - accuracy: 0.8474" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 91/Unknown - 7s 69ms/step - loss: 0.3821 - accuracy: 0.8479" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 92/Unknown - 7s 69ms/step - loss: 0.3812 - accuracy: 0.8481" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 93/Unknown - 7s 69ms/step - loss: 0.3812 - accuracy: 0.8480" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 94/Unknown - 7s 69ms/step - loss: 0.3814 - accuracy: 0.8480" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 95/Unknown - 7s 69ms/step - loss: 0.3813 - accuracy: 0.8479" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 96/Unknown - 7s 69ms/step - loss: 0.3818 - accuracy: 0.8478" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 97/Unknown - 7s 69ms/step - loss: 0.3827 - accuracy: 0.8475" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 98/Unknown - 8s 69ms/step - loss: 0.3821 - accuracy: 0.8477" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 99/Unknown - 8s 69ms/step - loss: 0.3826 - accuracy: 0.8476" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 100/Unknown - 8s 69ms/step - loss: 0.3818 - accuracy: 0.8479" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 101/Unknown - 8s 69ms/step - loss: 0.3809 - accuracy: 0.8485" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 102/Unknown - 8s 69ms/step - loss: 0.3810 - accuracy: 0.8483" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 103/Unknown - 8s 69ms/step - loss: 0.3814 - accuracy: 0.8482" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 104/Unknown - 8s 69ms/step - loss: 0.3815 - accuracy: 0.8480" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 105/Unknown - 8s 69ms/step - loss: 0.3800 - accuracy: 0.8487" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 106/Unknown - 8s 69ms/step - loss: 0.3798 - accuracy: 0.8485" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 107/Unknown - 8s 69ms/step - loss: 0.3789 - accuracy: 0.8489" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 108/Unknown - 8s 69ms/step - loss: 0.3788 - accuracy: 0.8492" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 109/Unknown - 8s 69ms/step - loss: 0.3786 - accuracy: 0.8494" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 110/Unknown - 8s 69ms/step - loss: 0.3790 - accuracy: 0.8491" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 111/Unknown - 8s 69ms/step - loss: 0.3787 - accuracy: 0.8492" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 112/Unknown - 8s 69ms/step - loss: 0.3781 - accuracy: 0.8495" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 113/Unknown - 9s 69ms/step - loss: 0.3778 - accuracy: 0.8496" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 114/Unknown - 9s 69ms/step - loss: 0.3782 - accuracy: 0.8492" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 115/Unknown - 9s 69ms/step - loss: 0.3776 - accuracy: 0.8496" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 116/Unknown - 9s 69ms/step - loss: 0.3777 - accuracy: 0.8493" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 117/Unknown - 9s 69ms/step - loss: 0.3777 - accuracy: 0.8495" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 118/Unknown - 9s 69ms/step - loss: 0.3770 - accuracy: 0.8495" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 119/Unknown - 9s 69ms/step - loss: 0.3777 - accuracy: 0.8495" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 120/Unknown - 9s 69ms/step - loss: 0.3776 - accuracy: 0.8494" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 121/Unknown - 9s 69ms/step - loss: 0.3776 - accuracy: 0.8495" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 122/Unknown - 9s 69ms/step - loss: 0.3770 - accuracy: 0.8498" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 123/Unknown - 9s 69ms/step - loss: 0.3774 - accuracy: 0.8497" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 124/Unknown - 9s 69ms/step - loss: 0.3781 - accuracy: 0.8494" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 125/Unknown - 9s 69ms/step - loss: 0.3781 - accuracy: 0.8495" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 126/Unknown - 9s 69ms/step - loss: 0.3794 - accuracy: 0.8491" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 127/Unknown - 10s 69ms/step - loss: 0.3795 - accuracy: 0.8493" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 128/Unknown - 10s 69ms/step - loss: 0.3796 - accuracy: 0.8492" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 129/Unknown - 10s 69ms/step - loss: 0.3789 - accuracy: 0.8496" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 130/Unknown - 10s 69ms/step - loss: 0.3792 - accuracy: 0.8493" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 131/Unknown - 10s 69ms/step - loss: 0.3790 - accuracy: 0.8494" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 132/Unknown - 10s 69ms/step - loss: 0.3781 - accuracy: 0.8497" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 133/Unknown - 10s 69ms/step - loss: 0.3793 - accuracy: 0.8490" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 134/Unknown - 10s 69ms/step - loss: 0.3792 - accuracy: 0.8492" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 135/Unknown - 10s 69ms/step - loss: 0.3785 - accuracy: 0.8496" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 136/Unknown - 10s 69ms/step - loss: 0.3778 - accuracy: 0.8500" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 137/Unknown - 10s 69ms/step - loss: 0.3779 - accuracy: 0.8498" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 138/Unknown - 10s 69ms/step - loss: 0.3776 - accuracy: 0.8500" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 139/Unknown - 10s 69ms/step - loss: 0.3776 - accuracy: 0.8502" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 140/Unknown - 10s 69ms/step - loss: 0.3781 - accuracy: 0.8497" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 141/Unknown - 10s 69ms/step - loss: 0.3773 - accuracy: 0.8500" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 142/Unknown - 11s 69ms/step - loss: 0.3767 - accuracy: 0.8504" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 143/Unknown - 11s 69ms/step - loss: 0.3760 - accuracy: 0.8508" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 144/Unknown - 11s 69ms/step - loss: 0.3754 - accuracy: 0.8511" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 145/Unknown - 11s 69ms/step - loss: 0.3746 - accuracy: 0.8513" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 146/Unknown - 11s 69ms/step - loss: 0.3744 - accuracy: 0.8516" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 147/Unknown - 11s 69ms/step - loss: 0.3743 - accuracy: 0.8516" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 148/Unknown - 11s 69ms/step - loss: 0.3744 - accuracy: 0.8516" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 149/Unknown - 11s 69ms/step - loss: 0.3739 - accuracy: 0.8519" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 150/Unknown - 11s 69ms/step - loss: 0.3739 - accuracy: 0.8518" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 151/Unknown - 11s 69ms/step - loss: 0.3737 - accuracy: 0.8519" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 152/Unknown - 11s 69ms/step - loss: 0.3738 - accuracy: 0.8517" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 153/Unknown - 11s 69ms/step - loss: 0.3736 - accuracy: 0.8518" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 154/Unknown - 11s 69ms/step - loss: 0.3734 - accuracy: 0.8519" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 155/Unknown - 11s 69ms/step - loss: 0.3736 - accuracy: 0.8518" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 156/Unknown - 12s 69ms/step - loss: 0.3730 - accuracy: 0.8520" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 157/Unknown - 12s 69ms/step - loss: 0.3727 - accuracy: 0.8522" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 158/Unknown - 12s 69ms/step - loss: 0.3731 - accuracy: 0.8521" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 159/Unknown - 12s 69ms/step - loss: 0.3733 - accuracy: 0.8518" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 160/Unknown - 12s 69ms/step - loss: 0.3736 - accuracy: 0.8517" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 161/Unknown - 12s 69ms/step - loss: 0.3735 - accuracy: 0.8517" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 162/Unknown - 12s 69ms/step - loss: 0.3736 - accuracy: 0.8517" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 163/Unknown - 12s 69ms/step - loss: 0.3741 - accuracy: 0.8517" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 164/Unknown - 12s 69ms/step - loss: 0.3745 - accuracy: 0.8516" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 165/Unknown - 12s 69ms/step - loss: 0.3743 - accuracy: 0.8517" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 166/Unknown - 12s 69ms/step - loss: 0.3740 - accuracy: 0.8515" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 167/Unknown - 12s 69ms/step - loss: 0.3741 - accuracy: 0.8516" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 168/Unknown - 12s 69ms/step - loss: 0.3748 - accuracy: 0.8511" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 169/Unknown - 12s 69ms/step - loss: 0.3741 - accuracy: 0.8512" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 170/Unknown - 12s 69ms/step - loss: 0.3736 - accuracy: 0.8512" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 171/Unknown - 13s 69ms/step - loss: 0.3741 - accuracy: 0.8510" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 172/Unknown - 13s 69ms/step - loss: 0.3743 - accuracy: 0.8510" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 173/Unknown - 13s 69ms/step - loss: 0.3750 - accuracy: 0.8505" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 174/Unknown - 13s 69ms/step - loss: 0.3746 - accuracy: 0.8507" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 175/Unknown - 13s 69ms/step - loss: 0.3746 - accuracy: 0.8506" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 176/Unknown - 13s 69ms/step - loss: 0.3740 - accuracy: 0.8508" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 177/Unknown - 13s 69ms/step - loss: 0.3738 - accuracy: 0.8510" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 178/Unknown - 13s 69ms/step - loss: 0.3739 - accuracy: 0.8509" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 179/Unknown - 13s 69ms/step - loss: 0.3739 - accuracy: 0.8509" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 180/Unknown - 13s 69ms/step - loss: 0.3737 - accuracy: 0.8509" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 181/Unknown - 13s 69ms/step - loss: 0.3746 - accuracy: 0.8505" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 182/Unknown - 13s 69ms/step - loss: 0.3748 - accuracy: 0.8505" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 183/Unknown - 13s 69ms/step - loss: 0.3747 - accuracy: 0.8505" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 184/Unknown - 13s 69ms/step - loss: 0.3744 - accuracy: 0.8505" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 185/Unknown - 14s 69ms/step - loss: 0.3747 - accuracy: 0.8504" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 186/Unknown - 14s 69ms/step - loss: 0.3751 - accuracy: 0.8501" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 187/Unknown - 14s 69ms/step - loss: 0.3753 - accuracy: 0.8500" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 188/Unknown - 14s 69ms/step - loss: 0.3748 - accuracy: 0.8501" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 189/Unknown - 14s 69ms/step - loss: 0.3744 - accuracy: 0.8501" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 190/Unknown - 14s 69ms/step - loss: 0.3749 - accuracy: 0.8500" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 191/Unknown - 14s 69ms/step - loss: 0.3745 - accuracy: 0.8501" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 192/Unknown - 14s 69ms/step - loss: 0.3741 - accuracy: 0.8503" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 193/Unknown - 14s 69ms/step - loss: 0.3746 - accuracy: 0.8502" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 194/Unknown - 14s 69ms/step - loss: 0.3744 - accuracy: 0.8503" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 195/Unknown - 14s 69ms/step - loss: 0.3740 - accuracy: 0.8504" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "196/196 [==============================] - 14s 69ms/step - loss: 0.3740 - accuracy: 0.8502\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[0.37399888038635254, 0.8502399921417236]\n" ] } ], "source": [ "results = model.evaluate(test_dataset, steps=HPARAMS.eval_steps)\n", "print(results)" ] }, { "cell_type": "markdown", "metadata": { "id": "5KggXVeL-llZ" }, "source": [ "### Create a graph of accuracy/loss over time\n", "\n", "`model.fit()` returns a `History` object that contains a dictionary with everything that happened during training:" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:24:45.762568Z", "iopub.status.busy": "2022-12-14T12:24:45.762262Z", "iopub.status.idle": "2022-12-14T12:24:45.767120Z", "shell.execute_reply": "2022-12-14T12:24:45.766432Z" }, "id": "VcvSXvhp-llb" }, "outputs": [ { "data": { "text/plain": [ "dict_keys(['loss', 'accuracy', 'val_loss', 'val_accuracy'])" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "history_dict = history.history\n", "history_dict.keys()" ] }, { "cell_type": "markdown", "metadata": { "id": "nRKsqL40-lle" }, "source": [ "There are four entries: one for each monitored metric during training and validation. We can use these to plot the training and validation loss for comparison, as well as the training and validation accuracy:" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:24:45.770403Z", "iopub.status.busy": "2022-12-14T12:24:45.770134Z", "iopub.status.idle": "2022-12-14T12:24:46.005753Z", "shell.execute_reply": "2022-12-14T12:24:46.005017Z" }, "id": "nGoYf2Js-lle" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "acc = history_dict['accuracy']\n", "val_acc = history_dict['val_accuracy']\n", "loss = history_dict['loss']\n", "val_loss = history_dict['val_loss']\n", "\n", "epochs = range(1, len(acc) + 1)\n", "\n", "# \"-r^\" is for solid red line with triangle markers.\n", "plt.plot(epochs, loss, '-r^', label='Training loss')\n", "# \"-b0\" is for solid blue line with circle markers.\n", "plt.plot(epochs, val_loss, '-bo', label='Validation loss')\n", "plt.title('Training and validation loss')\n", "plt.xlabel('Epochs')\n", "plt.ylabel('Loss')\n", "plt.legend(loc='best')\n", "\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:24:46.009457Z", "iopub.status.busy": "2022-12-14T12:24:46.009162Z", "iopub.status.idle": "2022-12-14T12:24:46.161352Z", "shell.execute_reply": "2022-12-14T12:24:46.160597Z" }, "id": "6hXx-xOv-llh" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.clf() # clear figure\n", "\n", "plt.plot(epochs, acc, '-r^', label='Training acc')\n", "plt.plot(epochs, val_acc, '-bo', label='Validation acc')\n", "plt.title('Training and validation accuracy')\n", "plt.xlabel('Epochs')\n", "plt.ylabel('Accuracy')\n", "plt.legend(loc='best')\n", "\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": { "id": "oFEmZ5zq-llk" }, "source": [ "Notice the training loss *decreases* with each epoch and the training accuracy\n", "*increases* with each epoch. This is expected when using a gradient descent\n", "optimization—it should minimize the desired quantity on every iteration." ] }, { "cell_type": "markdown", "metadata": { "id": "SymtYWWiMUum" }, "source": [ "## Graph regularization\n", "\n", "We are now ready to try graph regularization using the base model that we built\n", "above. We will use the `GraphRegularization` wrapper class provided by the\n", "Neural Structured Learning framework to wrap the base (bi-LSTM) model to include\n", "graph regularization. The rest of the steps for training and evaluating the\n", "graph-regularized model are similar to that of the base model." ] }, { "cell_type": "markdown", "metadata": { "id": "pCIkVe_QFX38" }, "source": [ "### Create graph-regularized model" ] }, { "cell_type": "markdown", "metadata": { "id": "vuIGN8KQH0jR" }, "source": [ "To assess the incremental benefit of graph regularization, we will create a new\n", "base model instance. This is because `model` has already been trained for a few\n", "iterations, and reusing this trained model to create a graph-regularized model\n", "will not be a fair comparison for `model`." ] }, { "cell_type": "code", "execution_count": 28, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:24:46.165193Z", "iopub.status.busy": "2022-12-14T12:24:46.164900Z", "iopub.status.idle": "2022-12-14T12:24:46.646177Z", "shell.execute_reply": "2022-12-14T12:24:46.645384Z" }, "id": "WOEElnbtPzSr" }, "outputs": [], "source": [ "# Build a new base LSTM model.\n", "base_reg_model = make_bilstm_model()" ] }, { "cell_type": "code", "execution_count": 29, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:24:46.650230Z", "iopub.status.busy": "2022-12-14T12:24:46.649937Z", "iopub.status.idle": "2022-12-14T12:24:46.670784Z", "shell.execute_reply": "2022-12-14T12:24:46.670096Z" }, "id": "XGaDeyjEOMLC" }, "outputs": [], "source": [ "# Wrap the base model with graph regularization.\n", "graph_reg_config = nsl.configs.make_graph_reg_config(\n", " max_neighbors=HPARAMS.num_neighbors,\n", " multiplier=HPARAMS.graph_regularization_multiplier,\n", " distance_type=HPARAMS.distance_type,\n", " sum_over_axis=-1)\n", "graph_reg_model = nsl.keras.GraphRegularization(base_reg_model,\n", " graph_reg_config)\n", "graph_reg_model.compile(\n", " optimizer='adam',\n", " loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),\n", " metrics=['accuracy'])" ] }, { "cell_type": "markdown", "metadata": { "id": "gSZSqJOKFdgX" }, "source": [ "### Train the model" ] }, { "cell_type": "code", "execution_count": 30, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:24:46.674210Z", "iopub.status.busy": "2022-12-14T12:24:46.673837Z", "iopub.status.idle": "2022-12-14T12:27:51.591044Z", "shell.execute_reply": "2022-12-14T12:27:51.590277Z" }, "id": "aONZhwc9FWoo" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.9/site-packages/tensorflow/python/autograph/pyct/static_analysis/liveness.py:83: Analyzer.lamba_check (from tensorflow.python.autograph.pyct.static_analysis.liveness) is deprecated and will be removed after 2023-09-23.\n", "Instructions for updating:\n", "Lambda fuctions will be no more assumed to be used in the statement where they are used, or at least in the same block. https://github.com/tensorflow/tensorflow/issues/56089\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.9/site-packages/tensorflow/python/autograph/pyct/static_analysis/liveness.py:83: Analyzer.lamba_check (from tensorflow.python.autograph.pyct.static_analysis.liveness) is deprecated and will be removed after 2023-09-23.\n", "Instructions for updating:\n", "Lambda fuctions will be no more assumed to be used in the statement where they are used, or at least in the same block. https://github.com/tensorflow/tensorflow/issues/56089\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/Unknown - 8s 8s/step - loss: 0.6927 - accuracy: 0.4531 - scaled_graph_loss: 5.1612e-06" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/Unknown - 8s 250ms/step - loss: 0.6933 - accuracy: 0.4766 - scaled_graph_loss: 1.1105e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/Unknown - 9s 249ms/step - loss: 0.6931 - accuracy: 0.4792 - scaled_graph_loss: 1.0886e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/Unknown - 9s 247ms/step - loss: 0.6923 - accuracy: 0.4688 - scaled_graph_loss: 1.0716e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/Unknown - 9s 247ms/step - loss: 0.6921 - accuracy: 0.4672 - scaled_graph_loss: 1.1883e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/Unknown - 9s 247ms/step - loss: 0.6920 - accuracy: 0.4688 - scaled_graph_loss: 1.4482e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/Unknown - 10s 247ms/step - loss: 0.6911 - accuracy: 0.4621 - scaled_graph_loss: 1.7061e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/Unknown - 10s 246ms/step - loss: 0.6912 - accuracy: 0.4639 - scaled_graph_loss: 2.1479e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/Unknown - 10s 246ms/step - loss: 0.6907 - accuracy: 0.4601 - scaled_graph_loss: 2.6979e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 10/Unknown - 10s 246ms/step - loss: 0.6903 - accuracy: 0.4578 - scaled_graph_loss: 3.2436e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 11/Unknown - 11s 245ms/step - loss: 0.6929 - accuracy: 0.4709 - scaled_graph_loss: 3.7401e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 12/Unknown - 11s 245ms/step - loss: 0.6928 - accuracy: 0.4707 - scaled_graph_loss: 4.0606e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 13/Unknown - 11s 245ms/step - loss: 0.6932 - accuracy: 0.4736 - scaled_graph_loss: 4.2779e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 14/Unknown - 11s 245ms/step - loss: 0.6929 - accuracy: 0.4721 - scaled_graph_loss: 4.3659e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 15/Unknown - 12s 245ms/step - loss: 0.6935 - accuracy: 0.4766 - scaled_graph_loss: 4.2799e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 16/Unknown - 12s 245ms/step - loss: 0.6934 - accuracy: 0.4766 - scaled_graph_loss: 4.1548e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 17/Unknown - 12s 245ms/step - loss: 0.6934 - accuracy: 0.4779 - scaled_graph_loss: 4.0260e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 18/Unknown - 12s 245ms/step - loss: 0.6938 - accuracy: 0.4835 - scaled_graph_loss: 3.8706e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 19/Unknown - 13s 245ms/step - loss: 0.6940 - accuracy: 0.4860 - scaled_graph_loss: 3.7059e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 20/Unknown - 13s 245ms/step - loss: 0.6938 - accuracy: 0.4840 - scaled_graph_loss: 3.5437e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 21/Unknown - 13s 240ms/step - loss: 0.6938 - accuracy: 0.4858 - scaled_graph_loss: 3.3994e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 27s 920ms/step - loss: 0.6938 - accuracy: 0.4858 - scaled_graph_loss: 3.3994e-05 - val_loss: 0.6928 - val_accuracy: 0.5024\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 2/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 13s - loss: 0.6916 - accuracy: 0.4297 - scaled_graph_loss: 5.0998e-06" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 4s - loss: 0.6922 - accuracy: 0.4531 - scaled_graph_loss: 5.7828e-06 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 4s - loss: 0.6924 - accuracy: 0.4661 - scaled_graph_loss: 6.1594e-06" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 4s - loss: 0.6924 - accuracy: 0.4746 - scaled_graph_loss: 6.6920e-06" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 3s - loss: 0.6925 - accuracy: 0.4828 - scaled_graph_loss: 6.8863e-06" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 3s - loss: 0.6924 - accuracy: 0.4883 - scaled_graph_loss: 6.9693e-06" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 3s - loss: 0.6925 - accuracy: 0.4877 - scaled_graph_loss: 7.2980e-06" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 3s - loss: 0.6923 - accuracy: 0.5020 - scaled_graph_loss: 7.3272e-06" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 2s - loss: 0.6923 - accuracy: 0.5043 - scaled_graph_loss: 7.5108e-06" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 2s - loss: 0.6924 - accuracy: 0.5008 - scaled_graph_loss: 8.2386e-06" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 2s - loss: 0.6922 - accuracy: 0.5057 - scaled_graph_loss: 9.2088e-06" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 2s - loss: 0.6923 - accuracy: 0.5033 - scaled_graph_loss: 1.0066e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.6922 - accuracy: 0.5066 - scaled_graph_loss: 1.1193e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.6922 - accuracy: 0.5061 - scaled_graph_loss: 1.2351e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 1s - loss: 0.6921 - accuracy: 0.5089 - scaled_graph_loss: 1.3663e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 1s - loss: 0.6920 - accuracy: 0.5132 - scaled_graph_loss: 1.5015e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.6919 - accuracy: 0.5142 - scaled_graph_loss: 1.7004e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.6920 - accuracy: 0.5135 - scaled_graph_loss: 1.8933e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.6919 - accuracy: 0.5136 - scaled_graph_loss: 2.0180e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.6921 - accuracy: 0.5090 - scaled_graph_loss: 2.1446e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.6921 - accuracy: 0.5085 - scaled_graph_loss: 2.2528e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 17s 836ms/step - loss: 0.6921 - accuracy: 0.5085 - scaled_graph_loss: 2.2528e-05 - val_loss: 0.6916 - val_accuracy: 0.4987\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 3/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 13s - loss: 0.6939 - accuracy: 0.4688 - scaled_graph_loss: 6.7862e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 4s - loss: 0.6917 - accuracy: 0.5039 - scaled_graph_loss: 6.9671e-05 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 4s - loss: 0.6908 - accuracy: 0.5130 - scaled_graph_loss: 6.5640e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 4s - loss: 0.6911 - accuracy: 0.4922 - scaled_graph_loss: 7.0389e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 3s - loss: 0.6909 - accuracy: 0.4938 - scaled_graph_loss: 8.3080e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 3s - loss: 0.6906 - accuracy: 0.4818 - scaled_graph_loss: 8.7481e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 3s - loss: 0.6902 - accuracy: 0.4833 - scaled_graph_loss: 9.1410e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 3s - loss: 0.6898 - accuracy: 0.4766 - scaled_graph_loss: 9.6830e-05" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 2s - loss: 0.6904 - accuracy: 0.4878 - scaled_graph_loss: 1.0697e-04" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 2s - loss: 0.6897 - accuracy: 0.4836 - scaled_graph_loss: 1.1932e-04" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 2s - loss: 0.6900 - accuracy: 0.4901 - scaled_graph_loss: 1.4425e-04" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 2s - loss: 0.6894 - accuracy: 0.4915 - scaled_graph_loss: 1.8546e-04" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.6881 - accuracy: 0.4892 - scaled_graph_loss: 2.6229e-04" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.6855 - accuracy: 0.4944 - scaled_graph_loss: 4.3725e-04" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 1s - loss: 0.6853 - accuracy: 0.5000 - scaled_graph_loss: 0.0014 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 1s - loss: 0.6851 - accuracy: 0.5000 - scaled_graph_loss: 0.0014" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.6838 - accuracy: 0.5046 - scaled_graph_loss: 0.0014" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.6822 - accuracy: 0.5048 - scaled_graph_loss: 0.0015" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.6813 - accuracy: 0.5045 - scaled_graph_loss: 0.0015" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.6812 - accuracy: 0.5086 - scaled_graph_loss: 0.0016" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.6806 - accuracy: 0.5088 - scaled_graph_loss: 0.0018" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 18s 844ms/step - loss: 0.6806 - accuracy: 0.5088 - scaled_graph_loss: 0.0018 - val_loss: 0.6383 - val_accuracy: 0.6404\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 4/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 13s - loss: 0.6580 - accuracy: 0.6250 - scaled_graph_loss: 0.0061" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 4s - loss: 0.6594 - accuracy: 0.6484 - scaled_graph_loss: 0.0206 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 4s - loss: 0.6519 - accuracy: 0.6016 - scaled_graph_loss: 0.0164" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 4s - loss: 0.6492 - accuracy: 0.5840 - scaled_graph_loss: 0.0137" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 3s - loss: 0.6487 - accuracy: 0.5750 - scaled_graph_loss: 0.0121" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 3s - loss: 0.6504 - accuracy: 0.5664 - scaled_graph_loss: 0.0110" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 3s - loss: 0.6484 - accuracy: 0.5670 - scaled_graph_loss: 0.0103" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 3s - loss: 0.6449 - accuracy: 0.5693 - scaled_graph_loss: 0.0102" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 2s - loss: 0.6418 - accuracy: 0.5799 - scaled_graph_loss: 0.0109" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 2s - loss: 0.6420 - accuracy: 0.5914 - scaled_graph_loss: 0.0132" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 2s - loss: 0.6369 - accuracy: 0.6094 - scaled_graph_loss: 0.0153" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 2s - loss: 0.6330 - accuracy: 0.6159 - scaled_graph_loss: 0.0173" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.6288 - accuracy: 0.6262 - scaled_graph_loss: 0.0216" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.6249 - accuracy: 0.6295 - scaled_graph_loss: 0.0220" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 1s - loss: 0.6229 - accuracy: 0.6276 - scaled_graph_loss: 0.0237" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 1s - loss: 0.6193 - accuracy: 0.6392 - scaled_graph_loss: 0.0283" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.6175 - accuracy: 0.6517 - scaled_graph_loss: 0.0300" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.6172 - accuracy: 0.6576 - scaled_graph_loss: 0.0307" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.6156 - accuracy: 0.6567 - scaled_graph_loss: 0.0305" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.6143 - accuracy: 0.6598 - scaled_graph_loss: 0.0300" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.6143 - accuracy: 0.6588 - scaled_graph_loss: 0.0292" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 17s 837ms/step - loss: 0.6143 - accuracy: 0.6588 - scaled_graph_loss: 0.0292 - val_loss: 0.5993 - val_accuracy: 0.5436\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 5/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 13s - loss: 0.6245 - accuracy: 0.4688 - scaled_graph_loss: 0.0160" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 4s - loss: 0.6162 - accuracy: 0.5117 - scaled_graph_loss: 0.0165 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 4s - loss: 0.6063 - accuracy: 0.5443 - scaled_graph_loss: 0.0188" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 4s - loss: 0.6077 - accuracy: 0.5566 - scaled_graph_loss: 0.0203" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 3s - loss: 0.5940 - accuracy: 0.5813 - scaled_graph_loss: 0.0227" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 3s - loss: 0.5893 - accuracy: 0.6029 - scaled_graph_loss: 0.0271" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 3s - loss: 0.5848 - accuracy: 0.6317 - scaled_graph_loss: 0.0318" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 3s - loss: 0.5861 - accuracy: 0.6553 - scaled_graph_loss: 0.0394" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 2s - loss: 0.5887 - accuracy: 0.6623 - scaled_graph_loss: 0.0448" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 2s - loss: 0.5856 - accuracy: 0.6766 - scaled_graph_loss: 0.0503" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 2s - loss: 0.5836 - accuracy: 0.6847 - scaled_graph_loss: 0.0533" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 2s - loss: 0.5806 - accuracy: 0.6914 - scaled_graph_loss: 0.0544" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.5787 - accuracy: 0.6941 - scaled_graph_loss: 0.0549" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.5804 - accuracy: 0.6903 - scaled_graph_loss: 0.0550" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 1s - loss: 0.5784 - accuracy: 0.6906 - scaled_graph_loss: 0.0538" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 1s - loss: 0.5786 - accuracy: 0.6875 - scaled_graph_loss: 0.0528" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.5803 - accuracy: 0.6838 - scaled_graph_loss: 0.0523" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.5790 - accuracy: 0.6871 - scaled_graph_loss: 0.0522" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.5760 - accuracy: 0.6924 - scaled_graph_loss: 0.0523" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.5742 - accuracy: 0.7004 - scaled_graph_loss: 0.0534" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.5748 - accuracy: 0.7015 - scaled_graph_loss: 0.0563" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 17s 841ms/step - loss: 0.5748 - accuracy: 0.7015 - scaled_graph_loss: 0.0563 - val_loss: 0.4726 - val_accuracy: 0.8239\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 6/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 13s - loss: 0.5438 - accuracy: 0.8125 - scaled_graph_loss: 0.0886" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 4s - loss: 0.5423 - accuracy: 0.8125 - scaled_graph_loss: 0.0768 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 4s - loss: 0.5380 - accuracy: 0.8151 - scaled_graph_loss: 0.0687" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 4s - loss: 0.5440 - accuracy: 0.7949 - scaled_graph_loss: 0.0649" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 3s - loss: 0.5458 - accuracy: 0.7875 - scaled_graph_loss: 0.0608" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 3s - loss: 0.5449 - accuracy: 0.7852 - scaled_graph_loss: 0.0587" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 3s - loss: 0.5423 - accuracy: 0.7868 - scaled_graph_loss: 0.0558" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 3s - loss: 0.5401 - accuracy: 0.7900 - scaled_graph_loss: 0.0568" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 2s - loss: 0.5402 - accuracy: 0.7856 - scaled_graph_loss: 0.0560" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 2s - loss: 0.5367 - accuracy: 0.7883 - scaled_graph_loss: 0.0556" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 2s - loss: 0.5394 - accuracy: 0.7891 - scaled_graph_loss: 0.0608" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 2s - loss: 0.5398 - accuracy: 0.7897 - scaled_graph_loss: 0.0653" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.5407 - accuracy: 0.7921 - scaled_graph_loss: 0.0683" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.5393 - accuracy: 0.7935 - scaled_graph_loss: 0.0696" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 1s - loss: 0.5359 - accuracy: 0.8000 - scaled_graph_loss: 0.0691" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 1s - loss: 0.5360 - accuracy: 0.8032 - scaled_graph_loss: 0.0687" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.5395 - accuracy: 0.8051 - scaled_graph_loss: 0.0699" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.5376 - accuracy: 0.8064 - scaled_graph_loss: 0.0691" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.5370 - accuracy: 0.8030 - scaled_graph_loss: 0.0685" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.5361 - accuracy: 0.8031 - scaled_graph_loss: 0.0681" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.5366 - accuracy: 0.8019 - scaled_graph_loss: 0.0681" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 18s 847ms/step - loss: 0.5366 - accuracy: 0.8019 - scaled_graph_loss: 0.0681 - val_loss: 0.4708 - val_accuracy: 0.7508\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 7/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 13s - loss: 0.6271 - accuracy: 0.6484 - scaled_graph_loss: 0.0846" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 4s - loss: 0.5767 - accuracy: 0.7578 - scaled_graph_loss: 0.0782 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 4s - loss: 0.5741 - accuracy: 0.7708 - scaled_graph_loss: 0.0708" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 4s - loss: 0.5616 - accuracy: 0.8008 - scaled_graph_loss: 0.0686" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 3s - loss: 0.5566 - accuracy: 0.8000 - scaled_graph_loss: 0.0660" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 3s - loss: 0.5546 - accuracy: 0.8060 - scaled_graph_loss: 0.0661" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 3s - loss: 0.5541 - accuracy: 0.8047 - scaled_graph_loss: 0.0657" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 3s - loss: 0.5503 - accuracy: 0.8076 - scaled_graph_loss: 0.0662" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 2s - loss: 0.5475 - accuracy: 0.8073 - scaled_graph_loss: 0.0691" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 2s - loss: 0.5463 - accuracy: 0.8086 - scaled_graph_loss: 0.0712" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 2s - loss: 0.5415 - accuracy: 0.8061 - scaled_graph_loss: 0.0716" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 2s - loss: 0.5403 - accuracy: 0.8047 - scaled_graph_loss: 0.0719" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.5349 - accuracy: 0.8137 - scaled_graph_loss: 0.0746" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.5331 - accuracy: 0.8181 - scaled_graph_loss: 0.0759" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 1s - loss: 0.5309 - accuracy: 0.8214 - scaled_graph_loss: 0.0759" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 1s - loss: 0.5304 - accuracy: 0.8193 - scaled_graph_loss: 0.0756" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.5323 - accuracy: 0.8120 - scaled_graph_loss: 0.0752" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.5325 - accuracy: 0.8069 - scaled_graph_loss: 0.0743" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.5333 - accuracy: 0.8006 - scaled_graph_loss: 0.0728" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.5329 - accuracy: 0.7992 - scaled_graph_loss: 0.0726" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.5330 - accuracy: 0.7992 - scaled_graph_loss: 0.0722" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 18s 847ms/step - loss: 0.5330 - accuracy: 0.7992 - scaled_graph_loss: 0.0722 - val_loss: 0.4462 - val_accuracy: 0.8373\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 8/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 13s - loss: 0.4604 - accuracy: 0.8828 - scaled_graph_loss: 0.0559" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 4s - loss: 0.4958 - accuracy: 0.8633 - scaled_graph_loss: 0.0770 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 4s - loss: 0.4957 - accuracy: 0.8698 - scaled_graph_loss: 0.0795" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 4s - loss: 0.5153 - accuracy: 0.8750 - scaled_graph_loss: 0.0885" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 3s - loss: 0.5189 - accuracy: 0.8594 - scaled_graph_loss: 0.0875" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 3s - loss: 0.5174 - accuracy: 0.8438 - scaled_graph_loss: 0.0835" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 3s - loss: 0.5197 - accuracy: 0.8270 - scaled_graph_loss: 0.0809" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 3s - loss: 0.5209 - accuracy: 0.8193 - scaled_graph_loss: 0.0789" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 2s - loss: 0.5205 - accuracy: 0.8194 - scaled_graph_loss: 0.0762" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 2s - loss: 0.5208 - accuracy: 0.8148 - scaled_graph_loss: 0.0750" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 2s - loss: 0.5217 - accuracy: 0.8139 - scaled_graph_loss: 0.0737" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 2s - loss: 0.5201 - accuracy: 0.8177 - scaled_graph_loss: 0.0735" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.5189 - accuracy: 0.8221 - scaled_graph_loss: 0.0739" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.5153 - accuracy: 0.8276 - scaled_graph_loss: 0.0761" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 1s - loss: 0.5168 - accuracy: 0.8266 - scaled_graph_loss: 0.0807" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 1s - loss: 0.5185 - accuracy: 0.8247 - scaled_graph_loss: 0.0825" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.5210 - accuracy: 0.8222 - scaled_graph_loss: 0.0822" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.5204 - accuracy: 0.8190 - scaled_graph_loss: 0.0808" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.5203 - accuracy: 0.8125 - scaled_graph_loss: 0.0792" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.5216 - accuracy: 0.8082 - scaled_graph_loss: 0.0771" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.5207 - accuracy: 0.8096 - scaled_graph_loss: 0.0755" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 18s 848ms/step - loss: 0.5207 - accuracy: 0.8096 - scaled_graph_loss: 0.0755 - val_loss: 0.4772 - val_accuracy: 0.7738\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 9/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 13s - loss: 0.5184 - accuracy: 0.7891 - scaled_graph_loss: 0.0546" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 4s - loss: 0.5125 - accuracy: 0.8164 - scaled_graph_loss: 0.0598 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 4s - loss: 0.5249 - accuracy: 0.8203 - scaled_graph_loss: 0.0671" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 4s - loss: 0.5309 - accuracy: 0.8125 - scaled_graph_loss: 0.0725" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 3s - loss: 0.5361 - accuracy: 0.8078 - scaled_graph_loss: 0.0786" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 3s - loss: 0.5318 - accuracy: 0.8125 - scaled_graph_loss: 0.0796" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 3s - loss: 0.5300 - accuracy: 0.8203 - scaled_graph_loss: 0.0810" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 3s - loss: 0.5295 - accuracy: 0.8203 - scaled_graph_loss: 0.0792" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 2s - loss: 0.5293 - accuracy: 0.8151 - scaled_graph_loss: 0.0772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 2s - loss: 0.5237 - accuracy: 0.8156 - scaled_graph_loss: 0.0763" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 2s - loss: 0.5230 - accuracy: 0.8168 - scaled_graph_loss: 0.0770" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 2s - loss: 0.5203 - accuracy: 0.8190 - scaled_graph_loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.5193 - accuracy: 0.8221 - scaled_graph_loss: 0.0784" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.5216 - accuracy: 0.8214 - scaled_graph_loss: 0.0813" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 1s - loss: 0.5185 - accuracy: 0.8240 - scaled_graph_loss: 0.0819" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 1s - loss: 0.5191 - accuracy: 0.8232 - scaled_graph_loss: 0.0831" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.5168 - accuracy: 0.8267 - scaled_graph_loss: 0.0831" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.5150 - accuracy: 0.8281 - scaled_graph_loss: 0.0821" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.5138 - accuracy: 0.8306 - scaled_graph_loss: 0.0821" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.5141 - accuracy: 0.8313 - scaled_graph_loss: 0.0823" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.5139 - accuracy: 0.8319 - scaled_graph_loss: 0.0831" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 18s 851ms/step - loss: 0.5139 - accuracy: 0.8319 - scaled_graph_loss: 0.0831 - val_loss: 0.4223 - val_accuracy: 0.8412\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 10/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/21 [>.............................] - ETA: 13s - loss: 0.5168 - accuracy: 0.8359 - scaled_graph_loss: 0.0857" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/21 [=>............................] - ETA: 4s - loss: 0.4873 - accuracy: 0.8477 - scaled_graph_loss: 0.0751 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/21 [===>..........................] - ETA: 4s - loss: 0.4875 - accuracy: 0.8438 - scaled_graph_loss: 0.0755" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/21 [====>.........................] - ETA: 4s - loss: 0.5037 - accuracy: 0.8262 - scaled_graph_loss: 0.0799" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/21 [======>.......................] - ETA: 3s - loss: 0.5011 - accuracy: 0.8422 - scaled_graph_loss: 0.0834" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/21 [=======>......................] - ETA: 3s - loss: 0.5057 - accuracy: 0.8451 - scaled_graph_loss: 0.0852" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/21 [=========>....................] - ETA: 3s - loss: 0.4996 - accuracy: 0.8493 - scaled_graph_loss: 0.0830" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/21 [==========>...................] - ETA: 3s - loss: 0.4992 - accuracy: 0.8477 - scaled_graph_loss: 0.0828" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/21 [===========>..................] - ETA: 2s - loss: 0.4996 - accuracy: 0.8446 - scaled_graph_loss: 0.0815" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "10/21 [=============>................] - ETA: 2s - loss: 0.4995 - accuracy: 0.8445 - scaled_graph_loss: 0.0820" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/21 [==============>...............] - ETA: 2s - loss: 0.4988 - accuracy: 0.8402 - scaled_graph_loss: 0.0805" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/21 [================>.............] - ETA: 2s - loss: 0.4974 - accuracy: 0.8379 - scaled_graph_loss: 0.0812" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13/21 [=================>............] - ETA: 1s - loss: 0.4959 - accuracy: 0.8407 - scaled_graph_loss: 0.0819" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "14/21 [===================>..........] - ETA: 1s - loss: 0.4971 - accuracy: 0.8387 - scaled_graph_loss: 0.0822" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "15/21 [====================>.........] - ETA: 1s - loss: 0.4975 - accuracy: 0.8401 - scaled_graph_loss: 0.0830" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16/21 [=====================>........] - ETA: 1s - loss: 0.4954 - accuracy: 0.8447 - scaled_graph_loss: 0.0837" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "17/21 [=======================>......] - ETA: 0s - loss: 0.4942 - accuracy: 0.8470 - scaled_graph_loss: 0.0831" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "18/21 [========================>.....] - ETA: 0s - loss: 0.4943 - accuracy: 0.8433 - scaled_graph_loss: 0.0818" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "19/21 [==========================>...] - ETA: 0s - loss: 0.4965 - accuracy: 0.8388 - scaled_graph_loss: 0.0825" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "20/21 [===========================>..] - ETA: 0s - loss: 0.4960 - accuracy: 0.8391 - scaled_graph_loss: 0.0820" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - ETA: 0s - loss: 0.4959 - accuracy: 0.8377 - scaled_graph_loss: 0.0813" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21/21 [==============================] - 18s 851ms/step - loss: 0.4959 - accuracy: 0.8377 - scaled_graph_loss: 0.0813 - val_loss: 0.4332 - val_accuracy: 0.8199\n" ] } ], "source": [ "graph_reg_history = graph_reg_model.fit(\n", " train_dataset,\n", " validation_data=validation_dataset,\n", " epochs=HPARAMS.train_epochs,\n", " verbose=1)" ] }, { "cell_type": "markdown", "metadata": { "id": "xD1oHiGHFjPB" }, "source": [ "### Evaluate the model" ] }, { "cell_type": "code", "execution_count": 31, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:27:51.595173Z", "iopub.status.busy": "2022-12-14T12:27:51.594622Z", "iopub.status.idle": "2022-12-14T12:28:06.136463Z", "shell.execute_reply": "2022-12-14T12:28:06.135655Z" }, "id": "vdFMEfe2e5JY" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/Unknown - 1s 808ms/step - loss: 0.4703 - accuracy: 0.7656" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 2/Unknown - 1s 71ms/step - loss: 0.4792 - accuracy: 0.7539 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 3/Unknown - 1s 69ms/step - loss: 0.4834 - accuracy: 0.7500" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4/Unknown - 1s 70ms/step - loss: 0.4901 - accuracy: 0.7383" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 5/Unknown - 1s 70ms/step - loss: 0.4918 - accuracy: 0.7422" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 6/Unknown - 1s 70ms/step - loss: 0.4851 - accuracy: 0.7513" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 7/Unknown - 1s 70ms/step - loss: 0.4799 - accuracy: 0.7589" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8/Unknown - 1s 70ms/step - loss: 0.4827 - accuracy: 0.7627" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 9/Unknown - 1s 70ms/step - loss: 0.4783 - accuracy: 0.7708" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 10/Unknown - 1s 71ms/step - loss: 0.4819 - accuracy: 0.7672" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 11/Unknown - 2s 71ms/step - loss: 0.4813 - accuracy: 0.7649" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 12/Unknown - 2s 71ms/step - loss: 0.4739 - accuracy: 0.7754" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 13/Unknown - 2s 71ms/step - loss: 0.4748 - accuracy: 0.7752" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 14/Unknown - 2s 71ms/step - loss: 0.4754 - accuracy: 0.7757" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 15/Unknown - 2s 71ms/step - loss: 0.4747 - accuracy: 0.7760" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 16/Unknown - 2s 71ms/step - loss: 0.4754 - accuracy: 0.7739" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 17/Unknown - 2s 71ms/step - loss: 0.4756 - accuracy: 0.7757" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 18/Unknown - 2s 71ms/step - loss: 0.4746 - accuracy: 0.7756" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 19/Unknown - 2s 71ms/step - loss: 0.4747 - accuracy: 0.7763" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 20/Unknown - 2s 71ms/step - loss: 0.4755 - accuracy: 0.7738" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 21/Unknown - 2s 71ms/step - loss: 0.4758 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 22/Unknown - 2s 71ms/step - loss: 0.4758 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 23/Unknown - 2s 71ms/step - loss: 0.4751 - accuracy: 0.7755" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 24/Unknown - 2s 71ms/step - loss: 0.4737 - accuracy: 0.7770" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 25/Unknown - 3s 71ms/step - loss: 0.4740 - accuracy: 0.7775" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 26/Unknown - 3s 71ms/step - loss: 0.4730 - accuracy: 0.7785" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 27/Unknown - 3s 71ms/step - loss: 0.4726 - accuracy: 0.7798" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 28/Unknown - 3s 71ms/step - loss: 0.4739 - accuracy: 0.7787" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 29/Unknown - 3s 71ms/step - loss: 0.4741 - accuracy: 0.7786" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 30/Unknown - 3s 71ms/step - loss: 0.4741 - accuracy: 0.7771" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 31/Unknown - 3s 71ms/step - loss: 0.4751 - accuracy: 0.7770" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 32/Unknown - 3s 71ms/step - loss: 0.4750 - accuracy: 0.7761" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 33/Unknown - 3s 71ms/step - loss: 0.4749 - accuracy: 0.7772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 34/Unknown - 3s 71ms/step - loss: 0.4742 - accuracy: 0.7776" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 35/Unknown - 3s 71ms/step - loss: 0.4734 - accuracy: 0.7772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 36/Unknown - 3s 71ms/step - loss: 0.4722 - accuracy: 0.7789" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 37/Unknown - 3s 71ms/step - loss: 0.4723 - accuracy: 0.7785" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 38/Unknown - 3s 71ms/step - loss: 0.4727 - accuracy: 0.7775" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 39/Unknown - 4s 71ms/step - loss: 0.4728 - accuracy: 0.7778" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 40/Unknown - 4s 71ms/step - loss: 0.4730 - accuracy: 0.7773" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 41/Unknown - 4s 71ms/step - loss: 0.4735 - accuracy: 0.7759" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 42/Unknown - 4s 71ms/step - loss: 0.4728 - accuracy: 0.7762" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 43/Unknown - 4s 71ms/step - loss: 0.4733 - accuracy: 0.7754" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 44/Unknown - 4s 71ms/step - loss: 0.4738 - accuracy: 0.7749" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 45/Unknown - 4s 71ms/step - loss: 0.4736 - accuracy: 0.7753" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 46/Unknown - 4s 71ms/step - loss: 0.4736 - accuracy: 0.7756" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 47/Unknown - 4s 71ms/step - loss: 0.4744 - accuracy: 0.7746" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 48/Unknown - 4s 71ms/step - loss: 0.4749 - accuracy: 0.7756" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 49/Unknown - 4s 71ms/step - loss: 0.4748 - accuracy: 0.7757" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 50/Unknown - 4s 71ms/step - loss: 0.4749 - accuracy: 0.7761" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 51/Unknown - 4s 71ms/step - loss: 0.4743 - accuracy: 0.7765" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 52/Unknown - 4s 71ms/step - loss: 0.4741 - accuracy: 0.7763" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 53/Unknown - 4s 71ms/step - loss: 0.4743 - accuracy: 0.7764" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 54/Unknown - 5s 71ms/step - loss: 0.4748 - accuracy: 0.7752" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 55/Unknown - 5s 71ms/step - loss: 0.4740 - accuracy: 0.7766" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 56/Unknown - 5s 71ms/step - loss: 0.4745 - accuracy: 0.7751" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 57/Unknown - 5s 71ms/step - loss: 0.4747 - accuracy: 0.7745" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 58/Unknown - 5s 71ms/step - loss: 0.4742 - accuracy: 0.7744" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 59/Unknown - 5s 71ms/step - loss: 0.4745 - accuracy: 0.7729" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 60/Unknown - 5s 71ms/step - loss: 0.4746 - accuracy: 0.7734" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 61/Unknown - 5s 71ms/step - loss: 0.4741 - accuracy: 0.7742" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 62/Unknown - 5s 71ms/step - loss: 0.4741 - accuracy: 0.7742" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 63/Unknown - 5s 71ms/step - loss: 0.4738 - accuracy: 0.7738" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 64/Unknown - 5s 71ms/step - loss: 0.4734 - accuracy: 0.7745" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 65/Unknown - 5s 71ms/step - loss: 0.4737 - accuracy: 0.7740" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 66/Unknown - 5s 71ms/step - loss: 0.4738 - accuracy: 0.7736" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 67/Unknown - 5s 71ms/step - loss: 0.4738 - accuracy: 0.7741" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 68/Unknown - 6s 71ms/step - loss: 0.4740 - accuracy: 0.7731" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 69/Unknown - 6s 71ms/step - loss: 0.4739 - accuracy: 0.7729" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 70/Unknown - 6s 70ms/step - loss: 0.4738 - accuracy: 0.7724" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 71/Unknown - 6s 70ms/step - loss: 0.4732 - accuracy: 0.7728" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 72/Unknown - 6s 70ms/step - loss: 0.4734 - accuracy: 0.7725" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 73/Unknown - 6s 70ms/step - loss: 0.4739 - accuracy: 0.7720" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 74/Unknown - 6s 70ms/step - loss: 0.4746 - accuracy: 0.7710" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 75/Unknown - 6s 70ms/step - loss: 0.4741 - accuracy: 0.7713" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 76/Unknown - 6s 70ms/step - loss: 0.4744 - accuracy: 0.7705" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 77/Unknown - 6s 70ms/step - loss: 0.4747 - accuracy: 0.7700" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 78/Unknown - 6s 70ms/step - loss: 0.4749 - accuracy: 0.7700" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 79/Unknown - 6s 70ms/step - loss: 0.4752 - accuracy: 0.7699" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 80/Unknown - 6s 70ms/step - loss: 0.4756 - accuracy: 0.7696" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 81/Unknown - 6s 70ms/step - loss: 0.4760 - accuracy: 0.7690" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 82/Unknown - 7s 70ms/step - loss: 0.4762 - accuracy: 0.7695" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 83/Unknown - 7s 70ms/step - loss: 0.4763 - accuracy: 0.7695" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 84/Unknown - 7s 70ms/step - loss: 0.4763 - accuracy: 0.7697" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 85/Unknown - 7s 70ms/step - loss: 0.4763 - accuracy: 0.7697" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 86/Unknown - 7s 70ms/step - loss: 0.4759 - accuracy: 0.7700" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 87/Unknown - 7s 70ms/step - loss: 0.4759 - accuracy: 0.7701" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 88/Unknown - 7s 70ms/step - loss: 0.4762 - accuracy: 0.7694" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 89/Unknown - 7s 70ms/step - loss: 0.4763 - accuracy: 0.7689" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 90/Unknown - 7s 70ms/step - loss: 0.4767 - accuracy: 0.7681" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 91/Unknown - 7s 70ms/step - loss: 0.4764 - accuracy: 0.7685" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 92/Unknown - 7s 70ms/step - loss: 0.4762 - accuracy: 0.7690" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 93/Unknown - 7s 70ms/step - loss: 0.4762 - accuracy: 0.7695" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 94/Unknown - 7s 70ms/step - loss: 0.4760 - accuracy: 0.7699" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 95/Unknown - 7s 70ms/step - loss: 0.4756 - accuracy: 0.7704" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 96/Unknown - 7s 70ms/step - loss: 0.4752 - accuracy: 0.7712" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 97/Unknown - 8s 70ms/step - loss: 0.4757 - accuracy: 0.7708" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 98/Unknown - 8s 70ms/step - loss: 0.4756 - accuracy: 0.7709" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 99/Unknown - 8s 70ms/step - loss: 0.4761 - accuracy: 0.7703" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 100/Unknown - 8s 70ms/step - loss: 0.4759 - accuracy: 0.7705" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 101/Unknown - 8s 70ms/step - loss: 0.4757 - accuracy: 0.7706" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 102/Unknown - 8s 70ms/step - loss: 0.4756 - accuracy: 0.7711" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 103/Unknown - 8s 70ms/step - loss: 0.4756 - accuracy: 0.7710" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 104/Unknown - 8s 70ms/step - loss: 0.4760 - accuracy: 0.7705" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 105/Unknown - 8s 71ms/step - loss: 0.4753 - accuracy: 0.7714" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 106/Unknown - 8s 70ms/step - loss: 0.4754 - accuracy: 0.7714" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 107/Unknown - 8s 70ms/step - loss: 0.4753 - accuracy: 0.7713" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 108/Unknown - 8s 70ms/step - loss: 0.4751 - accuracy: 0.7718" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 109/Unknown - 8s 70ms/step - loss: 0.4750 - accuracy: 0.7721" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 110/Unknown - 8s 70ms/step - loss: 0.4751 - accuracy: 0.7722" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 111/Unknown - 9s 70ms/step - loss: 0.4749 - accuracy: 0.7724" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 112/Unknown - 9s 70ms/step - loss: 0.4753 - accuracy: 0.7723" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 113/Unknown - 9s 70ms/step - loss: 0.4752 - accuracy: 0.7724" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 114/Unknown - 9s 70ms/step - loss: 0.4753 - accuracy: 0.7723" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 115/Unknown - 9s 70ms/step - loss: 0.4752 - accuracy: 0.7724" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 116/Unknown - 9s 70ms/step - loss: 0.4750 - accuracy: 0.7728" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 117/Unknown - 9s 70ms/step - loss: 0.4751 - accuracy: 0.7726" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 118/Unknown - 9s 70ms/step - loss: 0.4748 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 119/Unknown - 9s 70ms/step - loss: 0.4748 - accuracy: 0.7730" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 120/Unknown - 9s 70ms/step - loss: 0.4749 - accuracy: 0.7729" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 121/Unknown - 9s 70ms/step - loss: 0.4749 - accuracy: 0.7729" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 122/Unknown - 9s 70ms/step - loss: 0.4748 - accuracy: 0.7731" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 123/Unknown - 9s 70ms/step - loss: 0.4747 - accuracy: 0.7733" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 124/Unknown - 9s 70ms/step - loss: 0.4748 - accuracy: 0.7732" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 125/Unknown - 10s 70ms/step - loss: 0.4749 - accuracy: 0.7732" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 126/Unknown - 10s 70ms/step - loss: 0.4753 - accuracy: 0.7731" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 127/Unknown - 10s 70ms/step - loss: 0.4753 - accuracy: 0.7733" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 128/Unknown - 10s 70ms/step - loss: 0.4753 - accuracy: 0.7734" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 129/Unknown - 10s 70ms/step - loss: 0.4753 - accuracy: 0.7733" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 130/Unknown - 10s 70ms/step - loss: 0.4754 - accuracy: 0.7731" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 131/Unknown - 10s 70ms/step - loss: 0.4752 - accuracy: 0.7731" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 132/Unknown - 10s 70ms/step - loss: 0.4746 - accuracy: 0.7738" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 133/Unknown - 10s 70ms/step - loss: 0.4747 - accuracy: 0.7735" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 134/Unknown - 10s 70ms/step - loss: 0.4747 - accuracy: 0.7732" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 135/Unknown - 10s 70ms/step - loss: 0.4746 - accuracy: 0.7733" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 136/Unknown - 10s 70ms/step - loss: 0.4742 - accuracy: 0.7734" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 137/Unknown - 10s 70ms/step - loss: 0.4739 - accuracy: 0.7736" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 138/Unknown - 10s 70ms/step - loss: 0.4740 - accuracy: 0.7736" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 139/Unknown - 11s 70ms/step - loss: 0.4740 - accuracy: 0.7738" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 140/Unknown - 11s 70ms/step - loss: 0.4741 - accuracy: 0.7737" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 141/Unknown - 11s 70ms/step - loss: 0.4741 - accuracy: 0.7732" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 142/Unknown - 11s 70ms/step - loss: 0.4739 - accuracy: 0.7734" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 143/Unknown - 11s 70ms/step - loss: 0.4736 - accuracy: 0.7739" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 144/Unknown - 11s 70ms/step - loss: 0.4735 - accuracy: 0.7741" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 145/Unknown - 11s 70ms/step - loss: 0.4735 - accuracy: 0.7739" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 146/Unknown - 11s 70ms/step - loss: 0.4735 - accuracy: 0.7743" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 147/Unknown - 11s 70ms/step - loss: 0.4734 - accuracy: 0.7741" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 148/Unknown - 11s 70ms/step - loss: 0.4733 - accuracy: 0.7742" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 149/Unknown - 11s 70ms/step - loss: 0.4731 - accuracy: 0.7743" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 150/Unknown - 11s 70ms/step - loss: 0.4730 - accuracy: 0.7743" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 151/Unknown - 11s 70ms/step - loss: 0.4729 - accuracy: 0.7744" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 152/Unknown - 11s 70ms/step - loss: 0.4729 - accuracy: 0.7742" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 153/Unknown - 12s 70ms/step - loss: 0.4729 - accuracy: 0.7742" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 154/Unknown - 12s 70ms/step - loss: 0.4728 - accuracy: 0.7745" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 155/Unknown - 12s 70ms/step - loss: 0.4730 - accuracy: 0.7740" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 156/Unknown - 12s 70ms/step - loss: 0.4728 - accuracy: 0.7739" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 157/Unknown - 12s 70ms/step - loss: 0.4728 - accuracy: 0.7739" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 158/Unknown - 12s 70ms/step - loss: 0.4731 - accuracy: 0.7738" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 159/Unknown - 12s 70ms/step - loss: 0.4733 - accuracy: 0.7736" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 160/Unknown - 12s 70ms/step - loss: 0.4733 - accuracy: 0.7735" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 161/Unknown - 12s 70ms/step - loss: 0.4733 - accuracy: 0.7732" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 162/Unknown - 12s 70ms/step - loss: 0.4731 - accuracy: 0.7736" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 163/Unknown - 12s 70ms/step - loss: 0.4734 - accuracy: 0.7734" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 164/Unknown - 12s 70ms/step - loss: 0.4735 - accuracy: 0.7734" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 165/Unknown - 12s 70ms/step - loss: 0.4735 - accuracy: 0.7731" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 166/Unknown - 12s 70ms/step - loss: 0.4737 - accuracy: 0.7726" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 167/Unknown - 13s 70ms/step - loss: 0.4736 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 168/Unknown - 13s 70ms/step - loss: 0.4736 - accuracy: 0.7726" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 169/Unknown - 13s 70ms/step - loss: 0.4735 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 170/Unknown - 13s 70ms/step - loss: 0.4733 - accuracy: 0.7730" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 171/Unknown - 13s 70ms/step - loss: 0.4733 - accuracy: 0.7732" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 172/Unknown - 13s 70ms/step - loss: 0.4733 - accuracy: 0.7732" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 173/Unknown - 13s 70ms/step - loss: 0.4734 - accuracy: 0.7729" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 174/Unknown - 13s 70ms/step - loss: 0.4735 - accuracy: 0.7726" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 175/Unknown - 13s 70ms/step - loss: 0.4735 - accuracy: 0.7725" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 176/Unknown - 13s 70ms/step - loss: 0.4734 - accuracy: 0.7726" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 177/Unknown - 13s 70ms/step - loss: 0.4732 - accuracy: 0.7729" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 178/Unknown - 13s 70ms/step - loss: 0.4734 - accuracy: 0.7728" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 179/Unknown - 13s 70ms/step - loss: 0.4734 - accuracy: 0.7729" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 180/Unknown - 13s 70ms/step - loss: 0.4735 - accuracy: 0.7726" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 181/Unknown - 13s 70ms/step - loss: 0.4735 - accuracy: 0.7725" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 182/Unknown - 14s 70ms/step - loss: 0.4735 - accuracy: 0.7726" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 183/Unknown - 14s 70ms/step - loss: 0.4734 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 184/Unknown - 14s 70ms/step - loss: 0.4733 - accuracy: 0.7729" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 185/Unknown - 14s 70ms/step - loss: 0.4733 - accuracy: 0.7729" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 186/Unknown - 14s 71ms/step - loss: 0.4734 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 187/Unknown - 14s 71ms/step - loss: 0.4733 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 188/Unknown - 14s 71ms/step - loss: 0.4732 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 189/Unknown - 14s 71ms/step - loss: 0.4730 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 190/Unknown - 14s 71ms/step - loss: 0.4730 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 191/Unknown - 14s 71ms/step - loss: 0.4729 - accuracy: 0.7727" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 192/Unknown - 14s 71ms/step - loss: 0.4729 - accuracy: 0.7728" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 193/Unknown - 14s 70ms/step - loss: 0.4729 - accuracy: 0.7730" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 194/Unknown - 14s 71ms/step - loss: 0.4727 - accuracy: 0.7734" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 195/Unknown - 14s 71ms/step - loss: 0.4728 - accuracy: 0.7732" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "196/196 [==============================] - 15s 70ms/step - loss: 0.4728 - accuracy: 0.7732\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[0.4728052020072937, 0.7731599807739258]\n" ] } ], "source": [ "graph_reg_results = graph_reg_model.evaluate(test_dataset, steps=HPARAMS.eval_steps)\n", "print(graph_reg_results)" ] }, { "cell_type": "markdown", "metadata": { "id": "3BshURAbF49R" }, "source": [ "### Create a graph of accuracy/loss over time" ] }, { "cell_type": "code", "execution_count": 32, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:28:06.140234Z", "iopub.status.busy": "2022-12-14T12:28:06.139571Z", "iopub.status.idle": "2022-12-14T12:28:06.144465Z", "shell.execute_reply": "2022-12-14T12:28:06.143770Z" }, "id": "kHxshrYLah9v" }, "outputs": [ { "data": { "text/plain": [ "dict_keys(['loss', 'accuracy', 'scaled_graph_loss', 'val_loss', 'val_accuracy'])" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "graph_reg_history_dict = graph_reg_history.history\n", "graph_reg_history_dict.keys()" ] }, { "cell_type": "markdown", "metadata": { "id": "yBrp0Y0jHu5k" }, "source": [ "There are five entries in total in the dictionary: training loss, training\n", "accuracy, training graph loss, validation loss, and validation accuracy. We can\n", "plot them all together for comparison. Note that the graph loss is only computed\n", "during training." ] }, { "cell_type": "code", "execution_count": 33, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:28:06.147811Z", "iopub.status.busy": "2022-12-14T12:28:06.147332Z", "iopub.status.idle": "2022-12-14T12:28:06.321479Z", "shell.execute_reply": "2022-12-14T12:28:06.320735Z" }, "id": "YhjhH4n_aprb" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "acc = graph_reg_history_dict['accuracy']\n", "val_acc = graph_reg_history_dict['val_accuracy']\n", "loss = graph_reg_history_dict['loss']\n", "graph_loss = graph_reg_history_dict['scaled_graph_loss']\n", "val_loss = graph_reg_history_dict['val_loss']\n", "\n", "epochs = range(1, len(acc) + 1)\n", "\n", "plt.clf() # clear figure\n", "\n", "# \"-r^\" is for solid red line with triangle markers.\n", "plt.plot(epochs, loss, '-r^', label='Training loss')\n", "# \"-gD\" is for solid green line with diamond markers.\n", "plt.plot(epochs, graph_loss, '-gD', label='Training graph loss')\n", "# \"-b0\" is for solid blue line with circle markers.\n", "plt.plot(epochs, val_loss, '-bo', label='Validation loss')\n", "plt.title('Training and validation loss')\n", "plt.xlabel('Epochs')\n", "plt.ylabel('Loss')\n", "plt.legend(loc='best')\n", "\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 34, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:28:06.324999Z", "iopub.status.busy": "2022-12-14T12:28:06.324461Z", "iopub.status.idle": "2022-12-14T12:28:06.491227Z", "shell.execute_reply": "2022-12-14T12:28:06.490536Z" }, "id": "NE0vcDiqa1Id" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.clf() # clear figure\n", "\n", "plt.plot(epochs, acc, '-r^', label='Training acc')\n", "plt.plot(epochs, val_acc, '-bo', label='Validation acc')\n", "plt.title('Training and validation accuracy')\n", "plt.xlabel('Epochs')\n", "plt.ylabel('Accuracy')\n", "plt.legend(loc='best')\n", "\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": { "id": "Su1TOgT3mgrk" }, "source": [ "## The power of semi-supervised learning\n", "\n", "Semi-supervised learning and more specifically, graph regularization in the\n", "context of this tutorial, can be really powerful when the amount of training\n", "data is small. The lack of training data is compensated by leveraging similarity\n", "among the training samples, which is not possible in traditional supervised\n", "learning.\n", "\n", "We define ***supervision ratio*** as the ratio of training samples to the total\n", "number of samples which includes training, validation, and test samples. In this\n", "notebook, we have used a supervision ratio of 0.05 (i.e, 5% of the labeled data)\n", "for training both the base model as well as the graph-regularized model. We\n", "illustrate the impact of the supervision ratio on model accuracy in the cell\n", "below." ] }, { "cell_type": "code", "execution_count": 35, "metadata": { "execution": { "iopub.execute_input": "2022-12-14T12:28:06.494873Z", "iopub.status.busy": "2022-12-14T12:28:06.494368Z", "iopub.status.idle": "2022-12-14T12:28:06.801181Z", "shell.execute_reply": "2022-12-14T12:28:06.800271Z" }, "id": "nWWa384R5vSm" }, "outputs": [ { "data": { "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Accuracy values for both the Bi-LSTM model and the feed forward NN model have\n", "# been precomputed for the following supervision ratios.\n", "\n", "supervision_ratios = [0.3, 0.15, 0.05, 0.03, 0.02, 0.01, 0.005]\n", "\n", "model_tags = ['Bi-LSTM model', 'Feed Forward NN model']\n", "base_model_accs = [[84, 84, 83, 80, 65, 52, 50], [87, 86, 76, 74, 67, 52, 51]]\n", "graph_reg_model_accs = [[84, 84, 83, 83, 65, 63, 50],\n", " [87, 86, 80, 75, 67, 52, 50]]\n", "\n", "plt.clf() # clear figure\n", "\n", "fig, axes = plt.subplots(1, 2)\n", "fig.set_size_inches((12, 5))\n", "\n", "for ax, model_tag, base_model_acc, graph_reg_model_acc in zip(\n", " axes, model_tags, base_model_accs, graph_reg_model_accs):\n", "\n", " # \"-r^\" is for solid red line with triangle markers.\n", " ax.plot(base_model_acc, '-r^', label='Base model')\n", " # \"-gD\" is for solid green line with diamond markers.\n", " ax.plot(graph_reg_model_acc, '-gD', label='Graph-regularized model')\n", " ax.set_title(model_tag)\n", " ax.set_xlabel('Supervision ratio')\n", " ax.set_ylabel('Accuracy(%)')\n", " ax.set_ylim((25, 100))\n", " ax.set_xticks(range(len(supervision_ratios)))\n", " ax.set_xticklabels(supervision_ratios)\n", " ax.legend(loc='best')\n", "\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": { "id": "tukoIryKugX_" }, "source": [ "It can be observed that as the superivision ratio decreases, model accuracy also\n", "decreases. This is true for both the base model and for the graph-regularized\n", "model, regardless of the model architecture used. However, notice that the\n", "graph-regularized model performs better than the base model for both the\n", "architectures. In particular, for the Bi-LSTM model, when the supervision ratio\n", "is 0.01, the accuracy of the graph-regularized model is **~20%** higher than\n", "that of the base model. This is primarily because of semi-supervised learning\n", "for the graph-regularized model, where structural similarity among training\n", "samples is used in addition to the training samples themselves." ] }, { "cell_type": "markdown", "metadata": { "id": "8X4zCEyPhIp-" }, "source": [ "## Conclusion\n", "\n", "We have demonstrated the use of graph regularization using the Neural Structured\n", "Learning (NSL) framework even when the input does not contain an explicit graph.\n", "We considered the task of sentiment classification of IMDB movie reviews for\n", "which we synthesized a similarity graph based on review embeddings. We encourage\n", "users to experiment further by varying hyperparameters, the amount of\n", "supervision, and by using different model architectures." ] } ], "metadata": { "accelerator": "GPU", "colab": { "collapsed_sections": [ "24gYiJcWNlpA" ], "name": "Graph regularization for sentiment classification using synthesized graphs", "private_outputs": true, "provenance": [], "toc_visible": true }, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.16" } }, "nbformat": 4, "nbformat_minor": 0 }