{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "5wFF5JFyD2Ki"
   },
   "source": [
    "#### Copyright 2019 The TensorFlow Hub Authors.\n",
    "\n",
    "Licensed under the Apache License, Version 2.0 (the \"License\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-12T12:21:59.258897Z",
     "iopub.status.busy": "2023-05-12T12:21:59.258693Z",
     "iopub.status.idle": "2023-05-12T12:21:59.262275Z",
     "shell.execute_reply": "2023-05-12T12:21:59.261734Z"
    },
    "id": "Uf6NouXxDqGk"
   },
   "outputs": [],
   "source": [
    "# Copyright 2019 The TensorFlow Hub Authors. All Rights Reserved.\n",
    "#\n",
    "# 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",
    "#     http://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.\n",
    "# =============================================================================="
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ORy-KvWXGXBo"
   },
   "source": [
    "# Exploring the TF-Hub CORD-19 Swivel Embeddings\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "MfBg1C5NB3X0"
   },
   "source": [
    "<table class=\"tfo-notebook-buttons\" align=\"left\">\n",
    "  <td>\n",
    "    <a target=\"_blank\" href=\"https://www.tensorflow.org/hub/tutorials/cord_19_embeddings_keras\"><img src=\"https://www.tensorflow.org/images/tf_logo_32px.png\" />View on TensorFlow.org</a>\n",
    "  </td>\n",
    "  <td>\n",
    "    <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/cord_19_embeddings_keras.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
    "  </td>\n",
    "  <td>\n",
    "    <a target=\"_blank\" href=\"https://github.com/tensorflow/hub/blob/master/examples/colab/cord_19_embeddings_keras.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View on GitHub</a>\n",
    "  </td>\n",
    "  <td>\n",
    "    <a href=\"https://storage.googleapis.com/tensorflow_docs/hub/examples/colab/cord_19_embeddings_keras.ipynb\"><img src=\"https://www.tensorflow.org/images/download_logo_32px.png\" />Download notebook</a>\n",
    "  </td>\n",
    "  <td>\n",
    "    <a href=\"https://tfhub.dev/tensorflow/cord-19/swivel-128d/3\"><img src=\"https://www.tensorflow.org/images/hub_logo_32px.png\" />See TF Hub model</a>\n",
    "  </td>\n",
    "</table>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "yI6Mh3-P0_Pk"
   },
   "source": [
    "The CORD-19 Swivel text embedding module from TF-Hub (https://tfhub.dev/tensorflow/cord-19/swivel-128d/3)\n",
    " was built to support researchers analyzing natural languages text related to COVID-19.\n",
    "These embeddings were trained on the titles, authors, abstracts, body texts, and\n",
    "reference titles of articles in the [CORD-19 dataset](https://api.semanticscholar.org/CorpusID:216056360).\n",
    "\n",
    "In this colab we will:\n",
    "- Analyze semantically similar words in the embedding space\n",
    "- Train a classifier on the SciCite dataset using the CORD-19 embeddings\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "gVWOrccw0_Pl"
   },
   "source": [
    "## Setup\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-12T12:21:59.265292Z",
     "iopub.status.busy": "2023-05-12T12:21:59.265072Z",
     "iopub.status.idle": "2023-05-12T12:22:02.386502Z",
     "shell.execute_reply": "2023-05-12T12:22:02.385776Z"
    },
    "id": "Ym2nXOPuPV__"
   },
   "outputs": [],
   "source": [
    "import functools\n",
    "import itertools\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import pandas as pd\n",
    "\n",
    "import tensorflow as tf\n",
    "\n",
    "import tensorflow_datasets as tfds\n",
    "import tensorflow_hub as hub\n",
    "\n",
    "from tqdm import trange"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_VgRRf2I7tER"
   },
   "source": [
    "# Analyze the embeddings\n",
    "\n",
    "Let's start off by analyzing the embedding by calculating and plotting a correlation matrix between different terms. If the embedding learned to successfully capture the meaning of different words, the embedding vectors of semantically similar words should be close together. Let's take a look at some COVID-19 related terms."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-12T12:22:02.390954Z",
     "iopub.status.busy": "2023-05-12T12:22:02.390336Z",
     "iopub.status.idle": "2023-05-12T12:22:08.418543Z",
     "shell.execute_reply": "2023-05-12T12:22:08.417889Z"
    },
    "id": "HNN_9bBKSLHU"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Use the inner product between two embedding vectors as the similarity measure\n",
    "def plot_correlation(labels, features):\n",
    "  corr = np.inner(features, features)\n",
    "  corr /= np.max(corr)\n",
    "  sns.heatmap(corr, xticklabels=labels, yticklabels=labels)\n",
    "\n",
    "# Generate embeddings for some terms\n",
    "queries = [\n",
    "  # Related viruses\n",
    "  'coronavirus', 'SARS', 'MERS',\n",
    "  # Regions\n",
    "  'Italy', 'Spain', 'Europe',\n",
    "  # Symptoms\n",
    "  'cough', 'fever', 'throat'\n",
    "]\n",
    "\n",
    "module = hub.load('https://tfhub.dev/tensorflow/cord-19/swivel-128d/3')\n",
    "embeddings = module(queries)\n",
    "\n",
    "plot_correlation(queries, embeddings)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Bg-PGqtm8B7K"
   },
   "source": [
    "We can see that the embedding successfully captured the meaning of the different terms. Each word is similar to the other words of its cluster (i.e. \"coronavirus\" highly correlates with \"SARS\" and \"MERS\"), while they are different from terms of other clusters (i.e. the similarity between \"SARS\" and \"Spain\" is close to 0).\n",
    "\n",
    "Now let's see how we can use these embeddings to solve a specific task."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "idJ1jFmH7xMa"
   },
   "source": [
    "## SciCite: Citation Intent Classification\n",
    "\n",
    "This section shows how one can use the embedding for downstream tasks such as text classification. We'll use the [SciCite dataset](https://www.tensorflow.org/datasets/catalog/scicite) from TensorFlow Datasets to classify citation intents in academic papers. Given a sentence with a citation from an academic paper, classify whether the main intent of the citation is as background information, use of methods, or comparing results."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-12T12:22:08.458180Z",
     "iopub.status.busy": "2023-05-12T12:22:08.457423Z",
     "iopub.status.idle": "2023-05-12T12:22:09.589555Z",
     "shell.execute_reply": "2023-05-12T12:22:09.588880Z"
    },
    "id": "Ghc-CzT8DDaZ"
   },
   "outputs": [],
   "source": [
    "builder = tfds.builder(name='scicite')\n",
    "builder.download_and_prepare()\n",
    "train_data, validation_data, test_data = builder.as_dataset(\n",
    "    split=('train', 'validation', 'test'),\n",
    "    as_supervised=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-12T12:22:09.593377Z",
     "iopub.status.busy": "2023-05-12T12:22:09.593141Z",
     "iopub.status.idle": "2023-05-12T12:22:09.950440Z",
     "shell.execute_reply": "2023-05-12T12:22:09.949697Z"
    },
    "id": "CVjyBD0ZPh4Z"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>string</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>The finding that BMI is closely related to TBF...</td>\n",
       "      <td>result</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>The average magnitude of the NBR increases wit...</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>It has been reported that NF-κB activation can...</td>\n",
       "      <td>result</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>, 2008; Quraan and Cheyne, 2008; Quraan and Ch...</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5B), but, interestingly, they shared conserved...</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Some investigators have noted an association o...</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>In our previous study, it is documented that b...</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>These subjects have intact cognitive function ...</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Another study reported improved knee function ...</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>C. Data Analysis Transcription Speech samples ...</td>\n",
       "      <td>method</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              string       label\n",
       "0  The finding that BMI is closely related to TBF...      result\n",
       "1  The average magnitude of the NBR increases wit...  background\n",
       "2  It has been reported that NF-κB activation can...      result\n",
       "3  , 2008; Quraan and Cheyne, 2008; Quraan and Ch...  background\n",
       "4  5B), but, interestingly, they shared conserved...  background\n",
       "5  Some investigators have noted an association o...  background\n",
       "6  In our previous study, it is documented that b...  background\n",
       "7  These subjects have intact cognitive function ...  background\n",
       "8  Another study reported improved knee function ...  background\n",
       "9  C. Data Analysis Transcription Speech samples ...      method"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#@title Let's take a look at a few labeled examples from the training set\n",
    "NUM_EXAMPLES =   10#@param {type:\"integer\"}\n",
    "\n",
    "TEXT_FEATURE_NAME = builder.info.supervised_keys[0]\n",
    "LABEL_NAME = builder.info.supervised_keys[1]\n",
    "\n",
    "def label2str(numeric_label):\n",
    "  m = builder.info.features[LABEL_NAME].names\n",
    "  return m[numeric_label]\n",
    "\n",
    "data = next(iter(train_data.batch(NUM_EXAMPLES)))\n",
    "\n",
    "\n",
    "pd.DataFrame({\n",
    "    TEXT_FEATURE_NAME: [ex.numpy().decode('utf8') for ex in data[0]],\n",
    "    LABEL_NAME: [label2str(x) for x in data[1]]\n",
    "})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "65s9UpYJ_1ct"
   },
   "source": [
    "## Training a citaton intent classifier\n",
    "\n",
    "We'll train a classifier on the [SciCite dataset](https://www.tensorflow.org/datasets/catalog/scicite) using Keras.  Let's build a model which use the CORD-19 embeddings with a classification layer on top."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-12T12:22:09.954078Z",
     "iopub.status.busy": "2023-05-12T12:22:09.953688Z",
     "iopub.status.idle": "2023-05-12T12:22:10.528411Z",
     "shell.execute_reply": "2023-05-12T12:22:10.527673Z"
    },
    "id": "yZUclu8xBYlj"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\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": [
      " keras_layer (KerasLayer)    (None, 128)               17301632  \n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                                                 \n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " dense (Dense)               (None, 3)                 387       \n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                                                 \n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=================================================================\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total params: 17302019 (132.00 MB)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Trainable params: 387 (1.51 KB)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Non-trainable params: 17301632 (132.00 MB)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "#@title Hyperparameters { run: \"auto\" }\n",
    "\n",
    "EMBEDDING = 'https://tfhub.dev/tensorflow/cord-19/swivel-128d/3'  #@param {type: \"string\"}\n",
    "TRAINABLE_MODULE = False  #@param {type: \"boolean\"}\n",
    "\n",
    "hub_layer = hub.KerasLayer(EMBEDDING, input_shape=[], \n",
    "                           dtype=tf.string, trainable=TRAINABLE_MODULE)\n",
    "\n",
    "model = tf.keras.Sequential()\n",
    "model.add(hub_layer)\n",
    "model.add(tf.keras.layers.Dense(3))\n",
    "model.summary()\n",
    "model.compile(optimizer='adam',\n",
    "              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
    "              metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "weZKWK-pLBll"
   },
   "source": [
    "## Train and evaluate the model\n",
    "\n",
    "Let's train and evaluate the model to see the performance on the SciCite task"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-12T12:22:10.531643Z",
     "iopub.status.busy": "2023-05-12T12:22:10.531396Z",
     "iopub.status.idle": "2023-05-12T12:23:00.096907Z",
     "shell.execute_reply": "2023-05-12T12:23:00.096188Z"
    },
    "id": "cO1FWkZW2WS9"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 6:48 - loss: 1.3518 - accuracy: 0.1875"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 16/257 [>.............................] - ETA: 0s - loss: 1.2391 - accuracy: 0.2832  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 33/257 [==>...........................] - ETA: 0s - loss: 1.1511 - accuracy: 0.3665"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 50/257 [====>.........................] - ETA: 0s - loss: 1.0873 - accuracy: 0.4306"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 66/257 [======>.......................] - ETA: 0s - loss: 1.0461 - accuracy: 0.4735"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 83/257 [========>.....................] - ETA: 0s - loss: 1.0185 - accuracy: 0.4977"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "100/257 [==========>...................] - ETA: 0s - loss: 0.9951 - accuracy: 0.5203"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "117/257 [============>.................] - ETA: 0s - loss: 0.9724 - accuracy: 0.5414"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "134/257 [==============>...............] - ETA: 0s - loss: 0.9596 - accuracy: 0.5536"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "151/257 [================>.............] - ETA: 0s - loss: 0.9482 - accuracy: 0.5650"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "168/257 [==================>...........] - ETA: 0s - loss: 0.9340 - accuracy: 0.5746"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "185/257 [====================>.........] - ETA: 0s - loss: 0.9192 - accuracy: 0.5858"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "202/257 [======================>.......] - ETA: 0s - loss: 0.9044 - accuracy: 0.5959"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "219/257 [========================>.....] - ETA: 0s - loss: 0.8986 - accuracy: 0.5977"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "236/257 [==========================>...] - ETA: 0s - loss: 0.8867 - accuracy: 0.6058"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "253/257 [============================>.] - ETA: 0s - loss: 0.8769 - accuracy: 0.6135"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 3s 5ms/step - loss: 0.8760 - accuracy: 0.6140 - val_loss: 0.7403 - val_accuracy: 0.7227\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 2/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:23 - loss: 0.8620 - accuracy: 0.5938"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.7541 - accuracy: 0.6801  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.7513 - accuracy: 0.6875"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.7426 - accuracy: 0.6967"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.7395 - accuracy: 0.6939"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.7314 - accuracy: 0.7018"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.7262 - accuracy: 0.7059"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "120/257 [=============>................] - ETA: 0s - loss: 0.7197 - accuracy: 0.7091"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "137/257 [==============>...............] - ETA: 0s - loss: 0.7196 - accuracy: 0.7108"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "154/257 [================>.............] - ETA: 0s - loss: 0.7092 - accuracy: 0.7177"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "171/257 [==================>...........] - ETA: 0s - loss: 0.7049 - accuracy: 0.7195"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "188/257 [====================>.........] - ETA: 0s - loss: 0.6996 - accuracy: 0.7222"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "205/257 [======================>.......] - ETA: 0s - loss: 0.6944 - accuracy: 0.7236"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "222/257 [========================>.....] - ETA: 0s - loss: 0.6923 - accuracy: 0.7242"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "240/257 [===========================>..] - ETA: 0s - loss: 0.6896 - accuracy: 0.7249"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - ETA: 0s - loss: 0.6880 - accuracy: 0.7259"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.6880 - accuracy: 0.7259 - val_loss: 0.6526 - val_accuracy: 0.7555\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 3/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:11 - loss: 0.7175 - accuracy: 0.6562"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.6663 - accuracy: 0.7132  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.6494 - accuracy: 0.7362"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 52/257 [=====>........................] - ETA: 0s - loss: 0.6486 - accuracy: 0.7356"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 69/257 [=======>......................] - ETA: 0s - loss: 0.6308 - accuracy: 0.7536"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 86/257 [=========>....................] - ETA: 0s - loss: 0.6335 - accuracy: 0.7518"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "103/257 [===========>..................] - ETA: 0s - loss: 0.6378 - accuracy: 0.7485"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "120/257 [=============>................] - ETA: 0s - loss: 0.6324 - accuracy: 0.7523"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "137/257 [==============>...............] - ETA: 0s - loss: 0.6303 - accuracy: 0.7546"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "154/257 [================>.............] - ETA: 0s - loss: 0.6265 - accuracy: 0.7553"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "170/257 [==================>...........] - ETA: 0s - loss: 0.6299 - accuracy: 0.7526"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "186/257 [====================>.........] - ETA: 0s - loss: 0.6236 - accuracy: 0.7560"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "203/257 [======================>.......] - ETA: 0s - loss: 0.6223 - 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\b\b\r",
      "219/257 [========================>.....] - ETA: 0s - loss: 0.6211 - accuracy: 0.7586"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "236/257 [==========================>...] - ETA: 0s - loss: 0.6175 - accuracy: 0.7595"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "253/257 [============================>.] - ETA: 0s - loss: 0.6211 - 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\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.6211 - accuracy: 0.7575 - val_loss: 0.6142 - val_accuracy: 0.7598\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 4/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:14 - loss: 0.7404 - accuracy: 0.5938"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.6005 - accuracy: 0.7537  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.6058 - accuracy: 0.7619"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.6244 - accuracy: 0.7531"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.6084 - 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\b\b\r",
      " 84/257 [========>.....................] - ETA: 0s - loss: 0.6053 - accuracy: 0.7571"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "101/257 [==========>...................] - ETA: 0s - loss: 0.6041 - accuracy: 0.7608"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "117/257 [============>.................] - ETA: 0s - loss: 0.6018 - accuracy: 0.7658"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "134/257 [==============>...............] - ETA: 0s - loss: 0.6009 - accuracy: 0.7659"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "151/257 [================>.............] - ETA: 0s - loss: 0.5938 - accuracy: 0.7682"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "167/257 [==================>...........] - ETA: 0s - loss: 0.5956 - accuracy: 0.7657"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "184/257 [====================>.........] - ETA: 0s - loss: 0.5927 - accuracy: 0.7673"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "200/257 [======================>.......] - ETA: 0s - loss: 0.5939 - accuracy: 0.7667"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "217/257 [========================>.....] - ETA: 0s - loss: 0.5905 - 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\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "233/257 [==========================>...] - ETA: 0s - loss: 0.5884 - 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\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "249/257 [============================>.] - ETA: 0s - loss: 0.5846 - 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\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5870 - accuracy: 0.7720 - val_loss: 0.5962 - val_accuracy: 0.7609\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 5/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 2:08 - loss: 0.5937 - 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\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5881 - accuracy: 0.7702  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 33/257 [==>...........................] - ETA: 0s - loss: 0.5773 - accuracy: 0.7841"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 50/257 [====>.........................] - ETA: 0s - loss: 0.5701 - accuracy: 0.7837"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 66/257 [======>.......................] - ETA: 0s - loss: 0.5675 - accuracy: 0.7874"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 83/257 [========>.....................] - ETA: 0s - loss: 0.5643 - accuracy: 0.7873"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "100/257 [==========>...................] - ETA: 0s - loss: 0.5703 - accuracy: 0.7831"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "116/257 [============>.................] - ETA: 0s - loss: 0.5704 - accuracy: 0.7810"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "132/257 [==============>...............] - ETA: 0s - loss: 0.5721 - accuracy: 0.7779"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "148/257 [================>.............] - ETA: 0s - loss: 0.5686 - accuracy: 0.7796"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "164/257 [==================>...........] - ETA: 0s - loss: 0.5687 - accuracy: 0.7803"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "180/257 [====================>.........] - ETA: 0s - loss: 0.5649 - accuracy: 0.7825"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "196/257 [=====================>........] - ETA: 0s - loss: 0.5665 - accuracy: 0.7817"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "212/257 [=======================>......] - ETA: 0s - loss: 0.5709 - accuracy: 0.7774"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "228/257 [=========================>....] - ETA: 0s - loss: 0.5687 - accuracy: 0.7792"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "244/257 [===========================>..] - ETA: 0s - loss: 0.5685 - 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\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 2s 4ms/step - loss: 0.5675 - accuracy: 0.7812 - val_loss: 0.5818 - val_accuracy: 0.7609\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 6/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:36 - loss: 0.4456 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5618 - accuracy: 0.7794  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5435 - accuracy: 0.7904"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.5454 - accuracy: 0.7935"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 67/257 [======>.......................] - ETA: 0s - loss: 0.5376 - accuracy: 0.7938"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 84/257 [========>.....................] - ETA: 0s - loss: 0.5452 - accuracy: 0.7909"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "100/257 [==========>...................] - ETA: 0s - loss: 0.5464 - accuracy: 0.7887"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "116/257 [============>.................] - ETA: 0s - loss: 0.5422 - accuracy: 0.7893"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "133/257 [==============>...............] - ETA: 0s - loss: 0.5467 - accuracy: 0.7881"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "150/257 [================>.............] - ETA: 0s - loss: 0.5468 - accuracy: 0.7892"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "167/257 [==================>...........] - ETA: 0s - loss: 0.5410 - accuracy: 0.7932"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "184/257 [====================>.........] - ETA: 0s - loss: 0.5444 - accuracy: 0.7906"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "201/257 [======================>.......] - ETA: 0s - loss: 0.5457 - accuracy: 0.7904"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "218/257 [========================>.....] - ETA: 0s - loss: 0.5519 - accuracy: 0.7880"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "235/257 [==========================>...] - ETA: 0s - loss: 0.5511 - accuracy: 0.7874"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "252/257 [============================>.] - ETA: 0s - loss: 0.5540 - accuracy: 0.7860"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5553 - accuracy: 0.7856 - val_loss: 0.5755 - val_accuracy: 0.7675\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 7/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:17 - loss: 0.5275 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5177 - accuracy: 0.8107  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 33/257 [==>...........................] - ETA: 0s - loss: 0.5358 - accuracy: 0.8049"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 49/257 [====>.........................] - ETA: 0s - loss: 0.5355 - accuracy: 0.8042"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 66/257 [======>.......................] - ETA: 0s - loss: 0.5412 - accuracy: 0.7988"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 83/257 [========>.....................] - ETA: 0s - loss: 0.5449 - accuracy: 0.7941"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "100/257 [==========>...................] - ETA: 0s - loss: 0.5379 - accuracy: 0.7959"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "117/257 [============>.................] - ETA: 0s - loss: 0.5370 - accuracy: 0.7949"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "134/257 [==============>...............] - ETA: 0s - loss: 0.5345 - accuracy: 0.7938"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "150/257 [================>.............] - ETA: 0s - loss: 0.5381 - accuracy: 0.7919"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "166/257 [==================>...........] - ETA: 0s - loss: 0.5448 - accuracy: 0.7895"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "183/257 [====================>.........] - ETA: 0s - loss: 0.5430 - accuracy: 0.7905"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "199/257 [======================>.......] - ETA: 0s - loss: 0.5428 - accuracy: 0.7885"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "216/257 [========================>.....] - ETA: 0s - loss: 0.5427 - accuracy: 0.7898"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "233/257 [==========================>...] - ETA: 0s - loss: 0.5444 - accuracy: 0.7901"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "250/257 [============================>.] - ETA: 0s - loss: 0.5450 - accuracy: 0.7893"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5461 - accuracy: 0.7889 - val_loss: 0.5697 - val_accuracy: 0.7707\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 8/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:15 - loss: 0.4263 - 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\b\b\b\r",
      " 18/257 [=>............................] - ETA: 0s - loss: 0.5350 - accuracy: 0.8003  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 35/257 [===>..........................] - ETA: 0s - loss: 0.5359 - accuracy: 0.8045"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 52/257 [=====>........................] - ETA: 0s - loss: 0.5319 - accuracy: 0.8035"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 70/257 [=======>......................] - ETA: 0s - loss: 0.5496 - accuracy: 0.7924"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 88/257 [=========>....................] - ETA: 0s - loss: 0.5445 - accuracy: 0.7962"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "106/257 [===========>..................] - ETA: 0s - loss: 0.5439 - accuracy: 0.7954"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "123/257 [=============>................] - ETA: 0s - loss: 0.5429 - accuracy: 0.7932"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "140/257 [===============>..............] - ETA: 0s - loss: 0.5372 - accuracy: 0.7949"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "158/257 [=================>............] - ETA: 0s - loss: 0.5353 - accuracy: 0.7969"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "176/257 [===================>..........] - ETA: 0s - loss: 0.5369 - accuracy: 0.7942"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "194/257 [=====================>........] - ETA: 0s - loss: 0.5354 - accuracy: 0.7959"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "212/257 [=======================>......] - ETA: 0s - loss: 0.5404 - accuracy: 0.7932"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "230/257 [=========================>....] - ETA: 0s - loss: 0.5387 - accuracy: 0.7946"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "248/257 [===========================>..] - ETA: 0s - loss: 0.5384 - accuracy: 0.7944"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5394 - accuracy: 0.7934 - val_loss: 0.5633 - val_accuracy: 0.7762\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 9/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:18 - loss: 0.5482 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5094 - 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\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5344 - accuracy: 0.8088"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.5479 - accuracy: 0.8015"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.5615 - accuracy: 0.7932"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.5569 - accuracy: 0.7930"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.5526 - accuracy: 0.7926"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.5486 - accuracy: 0.7915"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "136/257 [==============>...............] - ETA: 0s - loss: 0.5464 - accuracy: 0.7904"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "153/257 [================>.............] - ETA: 0s - loss: 0.5442 - accuracy: 0.7906"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "170/257 [==================>...........] - ETA: 0s - loss: 0.5419 - accuracy: 0.7915"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "187/257 [====================>.........] - ETA: 0s - loss: 0.5417 - accuracy: 0.7909"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "204/257 [======================>.......] - ETA: 0s - loss: 0.5398 - accuracy: 0.7926"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "221/257 [========================>.....] - ETA: 0s - loss: 0.5375 - accuracy: 0.7933"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "238/257 [==========================>...] - ETA: 0s - loss: 0.5346 - accuracy: 0.7958"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "255/257 [============================>.] - ETA: 0s - loss: 0.5341 - accuracy: 0.7956"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5339 - accuracy: 0.7955 - val_loss: 0.5620 - val_accuracy: 0.7773\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 10/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 2:27 - loss: 0.6734 - accuracy: 0.6875"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5636 - accuracy: 0.7831  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5147 - accuracy: 0.8024"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.5174 - accuracy: 0.8027"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.5132 - accuracy: 0.8038"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.5116 - accuracy: 0.8048"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.5146 - accuracy: 0.8048"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.5228 - accuracy: 0.7996"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "136/257 [==============>...............] - ETA: 0s - loss: 0.5201 - accuracy: 0.8006"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "153/257 [================>.............] - ETA: 0s - loss: 0.5181 - accuracy: 0.8033"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "170/257 [==================>...........] - ETA: 0s - loss: 0.5221 - accuracy: 0.8013"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "187/257 [====================>.........] - ETA: 0s - loss: 0.5246 - accuracy: 0.7998"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "204/257 [======================>.......] - ETA: 0s - loss: 0.5300 - accuracy: 0.7963"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "221/257 [========================>.....] - ETA: 0s - loss: 0.5292 - accuracy: 0.7950"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "238/257 [==========================>...] - ETA: 0s - loss: 0.5278 - accuracy: 0.7953"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "255/257 [============================>.] - ETA: 0s - loss: 0.5288 - accuracy: 0.7951"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 2s 4ms/step - loss: 0.5294 - accuracy: 0.7950 - val_loss: 0.5582 - val_accuracy: 0.7740\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 11/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:18 - loss: 0.5308 - accuracy: 0.7812"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5484 - 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\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5361 - accuracy: 0.7849"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.5193 - accuracy: 0.7966"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.5192 - accuracy: 0.7987"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.5066 - accuracy: 0.8029"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.5061 - accuracy: 0.8036"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.5123 - accuracy: 0.7999"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "136/257 [==============>...............] - ETA: 0s - loss: 0.5254 - accuracy: 0.7948"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "153/257 [================>.............] - ETA: 0s - loss: 0.5263 - accuracy: 0.7962"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "170/257 [==================>...........] - ETA: 0s - loss: 0.5267 - accuracy: 0.7954"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "187/257 [====================>.........] - ETA: 0s - loss: 0.5320 - accuracy: 0.7911"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "204/257 [======================>.......] - ETA: 0s - loss: 0.5311 - accuracy: 0.7911"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "220/257 [========================>.....] - ETA: 0s - loss: 0.5313 - accuracy: 0.7923"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "237/257 [==========================>...] - ETA: 0s - loss: 0.5272 - accuracy: 0.7946"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "254/257 [============================>.] - ETA: 0s - loss: 0.5254 - accuracy: 0.7954"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5263 - accuracy: 0.7948 - val_loss: 0.5565 - val_accuracy: 0.7773\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 12/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:18 - loss: 0.3245 - accuracy: 0.9062"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5020 - accuracy: 0.7960  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5072 - accuracy: 0.8024"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.5040 - accuracy: 0.8051"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.5176 - accuracy: 0.7964"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.5272 - accuracy: 0.7930"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.5279 - accuracy: 0.7932"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.5268 - accuracy: 0.7941"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "136/257 [==============>...............] - ETA: 0s - loss: 0.5261 - accuracy: 0.7941"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "152/257 [================>.............] - ETA: 0s - loss: 0.5249 - accuracy: 0.7946"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "168/257 [==================>...........] - ETA: 0s - loss: 0.5222 - accuracy: 0.7976"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "184/257 [====================>.........] - ETA: 0s - loss: 0.5220 - accuracy: 0.7976"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "201/257 [======================>.......] - ETA: 0s - loss: 0.5245 - accuracy: 0.7946"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "218/257 [========================>.....] - ETA: 0s - loss: 0.5213 - accuracy: 0.7947"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "235/257 [==========================>...] - ETA: 0s - loss: 0.5231 - accuracy: 0.7949"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "251/257 [============================>.] - ETA: 0s - loss: 0.5239 - accuracy: 0.7937"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5233 - accuracy: 0.7941 - val_loss: 0.5547 - val_accuracy: 0.7784\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 13/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:25 - loss: 0.4330 - 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\b\b\b\b\r",
      " 16/257 [>.............................] - ETA: 0s - loss: 0.5284 - accuracy: 0.7852  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 32/257 [==>...........................] - ETA: 0s - loss: 0.5458 - 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\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 48/257 [====>.........................] - ETA: 0s - loss: 0.5325 - accuracy: 0.7884"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 64/257 [======>.......................] - ETA: 0s - loss: 0.5225 - accuracy: 0.7900"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 80/257 [========>.....................] - ETA: 0s - loss: 0.5233 - accuracy: 0.7887"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 96/257 [==========>...................] - ETA: 0s - loss: 0.5238 - accuracy: 0.7871"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "113/257 [============>.................] - ETA: 0s - loss: 0.5286 - accuracy: 0.7887"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "130/257 [==============>...............] - ETA: 0s - loss: 0.5250 - accuracy: 0.7899"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "147/257 [================>.............] - ETA: 0s - loss: 0.5204 - accuracy: 0.7944"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "164/257 [==================>...........] - ETA: 0s - loss: 0.5181 - accuracy: 0.7978"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "181/257 [====================>.........] - ETA: 0s - loss: 0.5154 - accuracy: 0.7977"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "198/257 [======================>.......] - ETA: 0s - loss: 0.5186 - accuracy: 0.7969"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "215/257 [========================>.....] - ETA: 0s - loss: 0.5198 - accuracy: 0.7956"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "232/257 [==========================>...] - ETA: 0s - loss: 0.5209 - accuracy: 0.7951"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "250/257 [============================>.] - ETA: 0s - loss: 0.5192 - accuracy: 0.7962"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5206 - accuracy: 0.7958 - val_loss: 0.5538 - val_accuracy: 0.7740\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 14/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:25 - loss: 0.5623 - accuracy: 0.7812"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.4970 - accuracy: 0.7960  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5127 - accuracy: 0.7895"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.5034 - accuracy: 0.7947"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.5131 - accuracy: 0.7946"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.5158 - accuracy: 0.7923"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.5171 - accuracy: 0.7926"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.5169 - accuracy: 0.7925"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "136/257 [==============>...............] - ETA: 0s - loss: 0.5166 - accuracy: 0.7939"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "153/257 [================>.............] - ETA: 0s - loss: 0.5153 - accuracy: 0.7933"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "170/257 [==================>...........] - ETA: 0s - loss: 0.5162 - accuracy: 0.7932"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "187/257 [====================>.........] - ETA: 0s - loss: 0.5194 - accuracy: 0.7936"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "204/257 [======================>.......] - ETA: 0s - loss: 0.5184 - accuracy: 0.7926"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "221/257 [========================>.....] - ETA: 0s - loss: 0.5174 - accuracy: 0.7941"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "238/257 [==========================>...] - ETA: 0s - loss: 0.5183 - accuracy: 0.7936"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "255/257 [============================>.] - ETA: 0s - loss: 0.5183 - accuracy: 0.7944"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5185 - accuracy: 0.7942 - val_loss: 0.5513 - val_accuracy: 0.7740\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 15/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:20 - loss: 0.5099 - accuracy: 0.7812"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5112 - accuracy: 0.8088  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5373 - accuracy: 0.7914"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.5364 - accuracy: 0.7880"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 69/257 [=======>......................] - ETA: 0s - loss: 0.5254 - accuracy: 0.7921"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 87/257 [=========>....................] - ETA: 0s - loss: 0.5311 - accuracy: 0.7906"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "105/257 [===========>..................] - ETA: 0s - loss: 0.5191 - accuracy: 0.7997"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "122/257 [=============>................] - ETA: 0s - loss: 0.5213 - accuracy: 0.7982"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "139/257 [===============>..............] - ETA: 0s - loss: 0.5174 - accuracy: 0.8024"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "156/257 [=================>............] - ETA: 0s - loss: 0.5174 - accuracy: 0.8017"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "174/257 [===================>..........] - ETA: 0s - loss: 0.5161 - accuracy: 0.8005"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "192/257 [=====================>........] - ETA: 0s - loss: 0.5172 - accuracy: 0.7970"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "210/257 [=======================>......] - ETA: 0s - loss: 0.5146 - accuracy: 0.7978"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "227/257 [=========================>....] - ETA: 0s - loss: 0.5147 - accuracy: 0.7980"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "244/257 [===========================>..] - ETA: 0s - loss: 0.5157 - accuracy: 0.7970"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5164 - accuracy: 0.7968 - val_loss: 0.5509 - val_accuracy: 0.7740\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 16/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:18 - loss: 0.5980 - accuracy: 0.7812"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.6023 - accuracy: 0.7592  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5365 - accuracy: 0.7941"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.5202 - accuracy: 0.8045"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.5214 - accuracy: 0.8033"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.5159 - accuracy: 0.8029"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.5158 - accuracy: 0.8024"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.5157 - accuracy: 0.8009"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "137/257 [==============>...............] - ETA: 0s - loss: 0.5146 - accuracy: 0.7997"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "154/257 [================>.............] - ETA: 0s - loss: 0.5189 - accuracy: 0.7975"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "171/257 [==================>...........] - ETA: 0s - loss: 0.5187 - accuracy: 0.7962"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "189/257 [=====================>........] - ETA: 0s - loss: 0.5178 - accuracy: 0.7958"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "207/257 [=======================>......] - ETA: 0s - loss: 0.5167 - accuracy: 0.7968"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "225/257 [=========================>....] - ETA: 0s - loss: 0.5167 - accuracy: 0.7975"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "242/257 [===========================>..] - ETA: 0s - loss: 0.5159 - accuracy: 0.7970"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5149 - accuracy: 0.7968 - val_loss: 0.5498 - val_accuracy: 0.7784\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 17/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:22 - loss: 0.4863 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5070 - accuracy: 0.7978  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5029 - accuracy: 0.7987"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.4951 - accuracy: 0.8039"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.4976 - accuracy: 0.8019"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.4971 - accuracy: 0.8048"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.4941 - accuracy: 0.8051"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.5008 - accuracy: 0.8030"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "136/257 [==============>...............] - ETA: 0s - loss: 0.5077 - accuracy: 0.7994"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "153/257 [================>.............] - ETA: 0s - loss: 0.5093 - accuracy: 0.7994"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "170/257 [==================>...........] - ETA: 0s - loss: 0.5103 - accuracy: 0.8007"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "187/257 [====================>.........] - ETA: 0s - loss: 0.5073 - accuracy: 0.8018"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "204/257 [======================>.......] - ETA: 0s - loss: 0.5119 - accuracy: 0.8010"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "221/257 [========================>.....] - ETA: 0s - loss: 0.5116 - accuracy: 0.8010"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "238/257 [==========================>...] - ETA: 0s - loss: 0.5131 - accuracy: 0.7998"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "255/257 [============================>.] - ETA: 0s - loss: 0.5132 - accuracy: 0.7988"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5135 - accuracy: 0.7988 - val_loss: 0.5483 - val_accuracy: 0.7762\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 18/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:32 - loss: 0.4830 - 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\b\b\b\r",
      " 18/257 [=>............................] - ETA: 0s - loss: 0.5176 - accuracy: 0.8038  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 35/257 [===>..........................] - ETA: 0s - loss: 0.5199 - accuracy: 0.8027"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 52/257 [=====>........................] - ETA: 0s - loss: 0.5261 - accuracy: 0.8011"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 69/257 [=======>......................] - ETA: 0s - loss: 0.5184 - accuracy: 0.8043"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 86/257 [=========>....................] - ETA: 0s - loss: 0.5150 - accuracy: 0.8023"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "104/257 [===========>..................] - ETA: 0s - loss: 0.5192 - accuracy: 0.7978"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "121/257 [=============>................] - ETA: 0s - loss: 0.5183 - accuracy: 0.7975"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "138/257 [===============>..............] - ETA: 0s - loss: 0.5175 - accuracy: 0.7980"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "155/257 [=================>............] - ETA: 0s - loss: 0.5141 - accuracy: 0.7992"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "173/257 [===================>..........] - ETA: 0s - loss: 0.5104 - accuracy: 0.7990"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "190/257 [=====================>........] - ETA: 0s - loss: 0.5099 - accuracy: 0.7987"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "207/257 [=======================>......] - ETA: 0s - loss: 0.5116 - accuracy: 0.7980"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "224/257 [=========================>....] - ETA: 0s - loss: 0.5130 - accuracy: 0.7981"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "241/257 [===========================>..] - ETA: 0s - loss: 0.5117 - accuracy: 0.7988"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5115 - accuracy: 0.7990 - val_loss: 0.5480 - val_accuracy: 0.7817\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 19/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:17 - loss: 0.6771 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.4967 - accuracy: 0.7996  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5383 - accuracy: 0.7840"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.5287 - accuracy: 0.7941"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.5229 - accuracy: 0.7946"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.5140 - accuracy: 0.8004"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.5118 - accuracy: 0.7978"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.5152 - accuracy: 0.7949"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "136/257 [==============>...............] - ETA: 0s - loss: 0.5164 - accuracy: 0.7932"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "153/257 [================>.............] - ETA: 0s - loss: 0.5201 - accuracy: 0.7925"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "170/257 [==================>...........] - ETA: 0s - loss: 0.5140 - accuracy: 0.7963"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "187/257 [====================>.........] - ETA: 0s - loss: 0.5127 - accuracy: 0.7958"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "204/257 [======================>.......] - ETA: 0s - loss: 0.5123 - accuracy: 0.7952"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "220/257 [========================>.....] - ETA: 0s - loss: 0.5126 - accuracy: 0.7963"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "237/257 [==========================>...] - ETA: 0s - loss: 0.5093 - accuracy: 0.7976"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "254/257 [============================>.] - ETA: 0s - loss: 0.5107 - accuracy: 0.7974"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5101 - accuracy: 0.7980 - val_loss: 0.5489 - val_accuracy: 0.7806\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 20/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:37 - loss: 0.6057 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5027 - accuracy: 0.8088  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5149 - accuracy: 0.8042"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.4983 - accuracy: 0.8076"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.5032 - accuracy: 0.8028"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.5039 - accuracy: 0.8011"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.5144 - accuracy: 0.7981"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "120/257 [=============>................] - ETA: 0s - loss: 0.5197 - accuracy: 0.7945"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "137/257 [==============>...............] - ETA: 0s - loss: 0.5196 - accuracy: 0.7968"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "155/257 [=================>............] - ETA: 0s - loss: 0.5193 - accuracy: 0.7952"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "172/257 [===================>..........] - ETA: 0s - loss: 0.5175 - accuracy: 0.7945"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "188/257 [====================>.........] - ETA: 0s - loss: 0.5126 - accuracy: 0.7962"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "205/257 [======================>.......] - ETA: 0s - loss: 0.5118 - accuracy: 0.7971"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "222/257 [========================>.....] - ETA: 0s - loss: 0.5109 - accuracy: 0.7972"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "240/257 [===========================>..] - ETA: 0s - loss: 0.5064 - accuracy: 0.7997"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5090 - accuracy: 0.7985 - val_loss: 0.5463 - val_accuracy: 0.7849\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 21/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:17 - loss: 0.4808 - 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\b\b\b\r",
      " 18/257 [=>............................] - ETA: 0s - loss: 0.4735 - accuracy: 0.8194  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 36/257 [===>..........................] - ETA: 0s - loss: 0.4824 - accuracy: 0.8082"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 53/257 [=====>........................] - ETA: 0s - loss: 0.4920 - accuracy: 0.7983"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 70/257 [=======>......................] - ETA: 0s - loss: 0.5112 - accuracy: 0.7915"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 88/257 [=========>....................] - ETA: 0s - loss: 0.5078 - accuracy: 0.7940"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "105/257 [===========>..................] - ETA: 0s - loss: 0.5075 - accuracy: 0.7926"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "123/257 [=============>................] - ETA: 0s - loss: 0.5007 - accuracy: 0.7947"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "140/257 [===============>..............] - ETA: 0s - loss: 0.5008 - accuracy: 0.7958"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "158/257 [=================>............] - ETA: 0s - loss: 0.4989 - accuracy: 0.7994"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "175/257 [===================>..........] - ETA: 0s - loss: 0.5042 - accuracy: 0.7986"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "191/257 [=====================>........] - ETA: 0s - loss: 0.5018 - accuracy: 0.8002"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "208/257 [=======================>......] - ETA: 0s - loss: 0.5022 - accuracy: 0.7996"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "225/257 [=========================>....] - ETA: 0s - loss: 0.5023 - accuracy: 0.7994"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "242/257 [===========================>..] - ETA: 0s - loss: 0.5062 - accuracy: 0.7989"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5081 - accuracy: 0.7980 - val_loss: 0.5477 - val_accuracy: 0.7806\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 22/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:19 - loss: 0.4074 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.4832 - accuracy: 0.8143  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.4593 - accuracy: 0.8235"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.4738 - accuracy: 0.8168"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.4757 - accuracy: 0.8157"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.4753 - accuracy: 0.8132"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.4826 - accuracy: 0.8110"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.4885 - accuracy: 0.8083"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "137/257 [==============>...............] - ETA: 0s - loss: 0.4866 - accuracy: 0.8109"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "154/257 [================>.............] - ETA: 0s - loss: 0.4920 - accuracy: 0.8066"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "171/257 [==================>...........] - ETA: 0s - loss: 0.4930 - accuracy: 0.8063"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "189/257 [=====================>........] - ETA: 0s - loss: 0.4971 - accuracy: 0.8047"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "206/257 [=======================>......] - ETA: 0s - loss: 0.5003 - accuracy: 0.8032"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "223/257 [=========================>....] - ETA: 0s - loss: 0.5023 - accuracy: 0.8020"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "241/257 [===========================>..] - ETA: 0s - loss: 0.5032 - accuracy: 0.8017"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5073 - accuracy: 0.7995 - val_loss: 0.5473 - val_accuracy: 0.7817\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 23/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:20 - loss: 0.4764 - 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\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5214 - accuracy: 0.7923  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.4976 - 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\b\r",
      " 50/257 [====>.........................] - ETA: 0s - loss: 0.4964 - accuracy: 0.8056"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 67/257 [======>.......................] - ETA: 0s - loss: 0.4954 - accuracy: 0.8050"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 84/257 [========>.....................] - ETA: 0s - loss: 0.4896 - accuracy: 0.8062"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "101/257 [==========>...................] - ETA: 0s - loss: 0.4937 - accuracy: 0.8038"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "118/257 [============>.................] - ETA: 0s - loss: 0.4898 - accuracy: 0.8053"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "135/257 [==============>...............] - ETA: 0s - loss: 0.4865 - accuracy: 0.8069"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "152/257 [================>.............] - ETA: 0s - loss: 0.4947 - accuracy: 0.8026"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "169/257 [==================>...........] - ETA: 0s - loss: 0.4987 - accuracy: 0.8014"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "186/257 [====================>.........] - ETA: 0s - loss: 0.5015 - accuracy: 0.8006"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "203/257 [======================>.......] - ETA: 0s - loss: 0.5025 - accuracy: 0.7999"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "220/257 [========================>.....] - ETA: 0s - loss: 0.5064 - accuracy: 0.7993"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "237/257 [==========================>...] - ETA: 0s - loss: 0.5068 - accuracy: 0.7985"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "254/257 [============================>.] - ETA: 0s - loss: 0.5072 - accuracy: 0.7976"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5064 - accuracy: 0.7977 - val_loss: 0.5483 - val_accuracy: 0.7817\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 24/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:22 - loss: 0.4104 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.4847 - accuracy: 0.7960  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5162 - accuracy: 0.7812"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.5206 - accuracy: 0.7831"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.5286 - accuracy: 0.7858"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.5181 - accuracy: 0.7912"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.5231 - accuracy: 0.7901"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.5224 - accuracy: 0.7886"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "136/257 [==============>...............] - ETA: 0s - loss: 0.5204 - accuracy: 0.7895"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "153/257 [================>.............] - ETA: 0s - loss: 0.5148 - accuracy: 0.7917"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "170/257 [==================>...........] - ETA: 0s - loss: 0.5118 - accuracy: 0.7928"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "187/257 [====================>.........] - ETA: 0s - loss: 0.5093 - accuracy: 0.7955"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "204/257 [======================>.......] - ETA: 0s - loss: 0.5066 - accuracy: 0.7967"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "221/257 [========================>.....] - ETA: 0s - loss: 0.5063 - accuracy: 0.7961"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "238/257 [==========================>...] - ETA: 0s - loss: 0.5078 - accuracy: 0.7966"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "255/257 [============================>.] - ETA: 0s - loss: 0.5059 - accuracy: 0.7987"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5053 - accuracy: 0.7989 - val_loss: 0.5496 - val_accuracy: 0.7806\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 25/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:19 - loss: 0.4965 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.4983 - accuracy: 0.7904  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.4819 - accuracy: 0.8051"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.4722 - accuracy: 0.8100"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.4860 - accuracy: 0.8047"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.4924 - accuracy: 0.8022"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "103/257 [===========>..................] - ETA: 0s - loss: 0.4931 - accuracy: 0.8010"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "120/257 [=============>................] - ETA: 0s - loss: 0.4980 - accuracy: 0.8008"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "137/257 [==============>...............] - ETA: 0s - loss: 0.4942 - accuracy: 0.8020"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "155/257 [=================>............] - ETA: 0s - loss: 0.4976 - accuracy: 0.8018"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "173/257 [===================>..........] - ETA: 0s - loss: 0.4971 - accuracy: 0.8004"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "191/257 [=====================>........] - ETA: 0s - loss: 0.4989 - accuracy: 0.8015"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "208/257 [=======================>......] - ETA: 0s - loss: 0.5009 - accuracy: 0.8002"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "225/257 [=========================>....] - ETA: 0s - loss: 0.5070 - accuracy: 0.7981"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "242/257 [===========================>..] - ETA: 0s - loss: 0.5057 - accuracy: 0.7991"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5046 - accuracy: 0.7997 - val_loss: 0.5496 - val_accuracy: 0.7849\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 26/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:14 - loss: 0.5508 - accuracy: 0.7812"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5368 - 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\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 33/257 [==>...........................] - ETA: 0s - loss: 0.4871 - accuracy: 0.8087"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 50/257 [====>.........................] - ETA: 0s - loss: 0.4924 - accuracy: 0.8069"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 67/257 [======>.......................] - ETA: 0s - loss: 0.4841 - accuracy: 0.8130"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 84/257 [========>.....................] - ETA: 0s - loss: 0.4906 - accuracy: 0.8106"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "101/257 [==========>...................] - ETA: 0s - loss: 0.4971 - accuracy: 0.8051"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "118/257 [============>.................] - ETA: 0s - loss: 0.5057 - accuracy: 0.7998"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "135/257 [==============>...............] - ETA: 0s - loss: 0.5028 - accuracy: 0.8016"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "152/257 [================>.............] - ETA: 0s - loss: 0.4969 - accuracy: 0.8039"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "168/257 [==================>...........] - ETA: 0s - loss: 0.4992 - accuracy: 0.8026"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "185/257 [====================>.........] - ETA: 0s - loss: 0.5040 - accuracy: 0.7990"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "202/257 [======================>.......] - ETA: 0s - loss: 0.5029 - accuracy: 0.7989"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "219/257 [========================>.....] - ETA: 0s - loss: 0.5031 - accuracy: 0.7991"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "236/257 [==========================>...] - ETA: 0s - loss: 0.5033 - accuracy: 0.8003"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "253/257 [============================>.] - ETA: 0s - loss: 0.5044 - accuracy: 0.8000"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5043 - accuracy: 0.7996 - val_loss: 0.5455 - val_accuracy: 0.7882\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 27/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:25 - loss: 0.5770 - accuracy: 0.7812"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5065 - accuracy: 0.7923  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5128 - accuracy: 0.7877"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.5000 - accuracy: 0.7941"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.5132 - accuracy: 0.7918"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.5175 - accuracy: 0.7904"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.5201 - accuracy: 0.7892"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.5149 - accuracy: 0.7931"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "137/257 [==============>...............] - ETA: 0s - loss: 0.5166 - accuracy: 0.7938"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "154/257 [================>.............] - ETA: 0s - loss: 0.5121 - accuracy: 0.7944"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "171/257 [==================>...........] - ETA: 0s - loss: 0.5084 - accuracy: 0.7966"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "188/257 [====================>.........] - ETA: 0s - loss: 0.5109 - accuracy: 0.7972"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "205/257 [======================>.......] - ETA: 0s - loss: 0.5099 - accuracy: 0.7973"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "222/257 [========================>.....] - ETA: 0s - loss: 0.5087 - accuracy: 0.7973"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "239/257 [==========================>...] - ETA: 0s - loss: 0.5048 - accuracy: 0.7998"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "256/257 [============================>.] - ETA: 0s - loss: 0.5032 - accuracy: 0.8002"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5033 - accuracy: 0.8001 - val_loss: 0.5458 - val_accuracy: 0.7849\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 28/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:21 - loss: 0.5489 - accuracy: 0.6875"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5034 - accuracy: 0.8107  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5011 - accuracy: 0.8097"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.4952 - accuracy: 0.8131"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.4976 - accuracy: 0.8070"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.5096 - accuracy: 0.7989"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.5045 - accuracy: 0.8021"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.5081 - accuracy: 0.7988"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "135/257 [==============>...............] - ETA: 0s - loss: 0.5051 - accuracy: 0.8007"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "151/257 [================>.............] - ETA: 0s - loss: 0.5065 - accuracy: 0.8009"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "168/257 [==================>...........] - ETA: 0s - loss: 0.5065 - accuracy: 0.8000"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "185/257 [====================>.........] - ETA: 0s - loss: 0.5050 - accuracy: 0.8008"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "202/257 [======================>.......] - ETA: 0s - loss: 0.5061 - accuracy: 0.7995"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "219/257 [========================>.....] - ETA: 0s - loss: 0.5074 - accuracy: 0.7984"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "236/257 [==========================>...] - ETA: 0s - loss: 0.5062 - accuracy: 0.8005"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "253/257 [============================>.] - ETA: 0s - loss: 0.5040 - accuracy: 0.8015"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5029 - accuracy: 0.8021 - val_loss: 0.5463 - val_accuracy: 0.7882\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 29/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:21 - loss: 0.2804 - accuracy: 0.9062"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.4432 - accuracy: 0.8254  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.4846 - 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\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.4872 - accuracy: 0.8070"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.4890 - accuracy: 0.8061"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.4963 - accuracy: 0.7985"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "103/257 [===========>..................] - ETA: 0s - loss: 0.5027 - accuracy: 0.8013"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "120/257 [=============>................] - ETA: 0s - loss: 0.4915 - accuracy: 0.8073"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "137/257 [==============>...............] - ETA: 0s - loss: 0.4968 - accuracy: 0.8038"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "154/257 [================>.............] - ETA: 0s - loss: 0.4986 - accuracy: 0.8032"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "171/257 [==================>...........] - ETA: 0s - loss: 0.5012 - accuracy: 0.8015"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "189/257 [=====================>........] - ETA: 0s - loss: 0.4998 - accuracy: 0.8022"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "207/257 [=======================>......] - ETA: 0s - loss: 0.5036 - accuracy: 0.8006"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "224/257 [=========================>....] - ETA: 0s - loss: 0.5052 - accuracy: 0.8011"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "241/257 [===========================>..] - ETA: 0s - loss: 0.5029 - accuracy: 0.8012"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5021 - accuracy: 0.8014 - val_loss: 0.5455 - val_accuracy: 0.7860\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 30/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:20 - loss: 0.3756 - 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\b\b\b\b\r",
      " 18/257 [=>............................] - ETA: 0s - loss: 0.4943 - accuracy: 0.8142  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 36/257 [===>..........................] - ETA: 0s - loss: 0.5203 - accuracy: 0.7934"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 54/257 [=====>........................] - ETA: 0s - loss: 0.5165 - accuracy: 0.8009"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 71/257 [=======>......................] - ETA: 0s - loss: 0.5134 - accuracy: 0.8050"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 89/257 [=========>....................] - ETA: 0s - loss: 0.5075 - accuracy: 0.8030"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "107/257 [===========>..................] - ETA: 0s - loss: 0.5048 - accuracy: 0.8049"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "125/257 [=============>................] - ETA: 0s - loss: 0.5050 - accuracy: 0.8037"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "143/257 [===============>..............] - ETA: 0s - loss: 0.5023 - accuracy: 0.8035"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "161/257 [=================>............] - ETA: 0s - loss: 0.5023 - accuracy: 0.8040"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "179/257 [===================>..........] - ETA: 0s - loss: 0.5014 - accuracy: 0.8025"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "196/257 [=====================>........] - ETA: 0s - loss: 0.4996 - accuracy: 0.8028"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "213/257 [=======================>......] - ETA: 0s - loss: 0.4971 - accuracy: 0.8043"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "230/257 [=========================>....] - ETA: 0s - loss: 0.4989 - accuracy: 0.8037"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "248/257 [===========================>..] - ETA: 0s - loss: 0.4996 - accuracy: 0.8030"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5020 - accuracy: 0.8024 - val_loss: 0.5445 - val_accuracy: 0.7893\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 31/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:22 - loss: 0.2939 - accuracy: 0.9375"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.4732 - accuracy: 0.8254  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.4683 - accuracy: 0.8199"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 52/257 [=====>........................] - ETA: 0s - loss: 0.4694 - accuracy: 0.8191"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 70/257 [=======>......................] - ETA: 0s - loss: 0.4805 - accuracy: 0.8134"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 88/257 [=========>....................] - ETA: 0s - loss: 0.4794 - 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\b\r",
      "105/257 [===========>..................] - ETA: 0s - loss: 0.4792 - accuracy: 0.8113"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "122/257 [=============>................] - ETA: 0s - loss: 0.4817 - accuracy: 0.8089"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "140/257 [===============>..............] - ETA: 0s - loss: 0.4844 - accuracy: 0.8074"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "157/257 [=================>............] - ETA: 0s - loss: 0.4869 - accuracy: 0.8079"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "175/257 [===================>..........] - ETA: 0s - loss: 0.4920 - accuracy: 0.8062"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "193/257 [=====================>........] - ETA: 0s - loss: 0.4905 - accuracy: 0.8059"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "211/257 [=======================>......] - ETA: 0s - loss: 0.4964 - accuracy: 0.8021"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "229/257 [=========================>....] - ETA: 0s - loss: 0.4969 - accuracy: 0.8035"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "246/257 [===========================>..] - ETA: 0s - loss: 0.4996 - accuracy: 0.8023"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5008 - accuracy: 0.8017 - val_loss: 0.5439 - val_accuracy: 0.7849\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 32/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:22 - loss: 0.3428 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.4960 - accuracy: 0.8070  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 33/257 [==>...........................] - ETA: 0s - loss: 0.4997 - accuracy: 0.8068"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 50/257 [====>.........................] - ETA: 0s - loss: 0.5038 - accuracy: 0.8025"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 67/257 [======>.......................] - ETA: 0s - loss: 0.5056 - accuracy: 0.8036"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 84/257 [========>.....................] - ETA: 0s - loss: 0.5016 - accuracy: 0.8036"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "101/257 [==========>...................] - ETA: 0s - loss: 0.5089 - accuracy: 0.7998"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "118/257 [============>.................] - ETA: 0s - loss: 0.5150 - accuracy: 0.7961"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "135/257 [==============>...............] - ETA: 0s - loss: 0.5072 - accuracy: 0.7993"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "152/257 [================>.............] - ETA: 0s - loss: 0.5109 - accuracy: 0.7975"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "170/257 [==================>...........] - ETA: 0s - loss: 0.5073 - accuracy: 0.7996"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "188/257 [====================>.........] - ETA: 0s - loss: 0.5016 - accuracy: 0.8019"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "205/257 [======================>.......] - ETA: 0s - loss: 0.5020 - accuracy: 0.8017"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "222/257 [========================>.....] - ETA: 0s - loss: 0.5015 - accuracy: 0.8017"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "239/257 [==========================>...] - ETA: 0s - loss: 0.5004 - accuracy: 0.8013"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "256/257 [============================>.] - ETA: 0s - loss: 0.5008 - accuracy: 0.8010"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5007 - accuracy: 0.8011 - val_loss: 0.5434 - val_accuracy: 0.7838\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 33/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:20 - loss: 0.6507 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.5120 - accuracy: 0.7960  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.4689 - accuracy: 0.8171"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.4838 - accuracy: 0.8107"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.4900 - accuracy: 0.8065"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.4753 - accuracy: 0.8132"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.4798 - 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\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.4902 - accuracy: 0.8088"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "136/257 [==============>...............] - ETA: 0s - loss: 0.4976 - accuracy: 0.8058"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "153/257 [================>.............] - ETA: 0s - loss: 0.4951 - accuracy: 0.8064"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "170/257 [==================>...........] - ETA: 0s - loss: 0.4971 - accuracy: 0.8053"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "187/257 [====================>.........] - ETA: 0s - loss: 0.4952 - accuracy: 0.8051"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "204/257 [======================>.......] - ETA: 0s - loss: 0.4988 - accuracy: 0.8053"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "221/257 [========================>.....] - ETA: 0s - loss: 0.5014 - accuracy: 0.8025"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "238/257 [==========================>...] - ETA: 0s - loss: 0.4994 - accuracy: 0.8042"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "255/257 [============================>.] - ETA: 0s - loss: 0.4993 - accuracy: 0.8032"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5002 - accuracy: 0.8028 - val_loss: 0.5464 - val_accuracy: 0.7849\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 34/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:17 - loss: 0.4397 - 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\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.4700 - accuracy: 0.8272  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.5070 - accuracy: 0.7960"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 51/257 [====>.........................] - ETA: 0s - loss: 0.4684 - accuracy: 0.8168"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 68/257 [======>.......................] - ETA: 0s - loss: 0.4795 - accuracy: 0.8143"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 85/257 [========>.....................] - ETA: 0s - loss: 0.4903 - accuracy: 0.8066"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "102/257 [==========>...................] - ETA: 0s - loss: 0.4950 - accuracy: 0.8024"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "119/257 [============>.................] - ETA: 0s - loss: 0.4921 - accuracy: 0.8017"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "136/257 [==============>...............] - ETA: 0s - loss: 0.4929 - accuracy: 0.8019"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "153/257 [================>.............] - ETA: 0s - loss: 0.4982 - accuracy: 0.7998"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "170/257 [==================>...........] - ETA: 0s - loss: 0.5004 - accuracy: 0.8002"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "186/257 [====================>.........] - ETA: 0s - loss: 0.5022 - accuracy: 0.8006"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "202/257 [======================>.......] - ETA: 0s - loss: 0.5029 - accuracy: 0.8003"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "218/257 [========================>.....] - ETA: 0s - loss: 0.5023 - accuracy: 0.8010"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "234/257 [==========================>...] - ETA: 0s - loss: 0.5009 - accuracy: 0.8009"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "250/257 [============================>.] - ETA: 0s - loss: 0.5010 - accuracy: 0.8012"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.5000 - accuracy: 0.8019 - val_loss: 0.5480 - val_accuracy: 0.7860\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 35/35\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "  1/257 [..............................] - ETA: 1:36 - loss: 0.7758 - accuracy: 0.6562"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 17/257 [>.............................] - ETA: 0s - loss: 0.4730 - accuracy: 0.8088  "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 34/257 [==>...........................] - ETA: 0s - loss: 0.4940 - accuracy: 0.8070"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 50/257 [====>.........................] - ETA: 0s - loss: 0.4814 - accuracy: 0.8156"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 67/257 [======>.......................] - ETA: 0s - loss: 0.4872 - accuracy: 0.8139"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 83/257 [========>.....................] - ETA: 0s - loss: 0.4965 - accuracy: 0.8053"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 99/257 [==========>...................] - ETA: 0s - loss: 0.5065 - accuracy: 0.7992"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "115/257 [============>.................] - ETA: 0s - loss: 0.5130 - accuracy: 0.7970"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "131/257 [==============>...............] - ETA: 0s - loss: 0.5126 - accuracy: 0.7965"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "147/257 [================>.............] - ETA: 0s - loss: 0.5049 - accuracy: 0.7995"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "163/257 [==================>...........] - ETA: 0s - loss: 0.5015 - accuracy: 0.8018"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "179/257 [===================>..........] - ETA: 0s - loss: 0.5001 - accuracy: 0.8015"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "195/257 [=====================>........] - ETA: 0s - loss: 0.4972 - accuracy: 0.8016"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "211/257 [=======================>......] - ETA: 0s - loss: 0.4986 - accuracy: 0.8002"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "228/257 [=========================>....] - ETA: 0s - loss: 0.5015 - accuracy: 0.8000"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "245/257 [===========================>..] - ETA: 0s - loss: 0.5005 - accuracy: 0.8009"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "257/257 [==============================] - 1s 4ms/step - loss: 0.4992 - accuracy: 0.8014 - val_loss: 0.5447 - val_accuracy: 0.7882\n"
     ]
    }
   ],
   "source": [
    "EPOCHS = 35#@param {type: \"integer\"}\n",
    "BATCH_SIZE = 32#@param {type: \"integer\"}\n",
    "\n",
    "history = model.fit(train_data.shuffle(10000).batch(BATCH_SIZE),\n",
    "                    epochs=EPOCHS,\n",
    "                    validation_data=validation_data.batch(BATCH_SIZE),\n",
    "                    verbose=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-12T12:23:00.100619Z",
     "iopub.status.busy": "2023-05-12T12:23:00.100123Z",
     "iopub.status.idle": "2023-05-12T12:23:00.104994Z",
     "shell.execute_reply": "2023-05-12T12:23:00.104444Z"
    },
    "id": "2sKE7kEyLJQZ"
   },
   "outputs": [],
   "source": [
    "from matplotlib import pyplot as plt\n",
    "def display_training_curves(training, validation, title, subplot):\n",
    "  if subplot%10==1: # set up the subplots on the first call\n",
    "    plt.subplots(figsize=(10,10), facecolor='#F0F0F0')\n",
    "    plt.tight_layout()\n",
    "  ax = plt.subplot(subplot)\n",
    "  ax.set_facecolor('#F8F8F8')\n",
    "  ax.plot(training)\n",
    "  ax.plot(validation)\n",
    "  ax.set_title('model '+ title)\n",
    "  ax.set_ylabel(title)\n",
    "  ax.set_xlabel('epoch')\n",
    "  ax.legend(['train', 'valid.'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-12T12:23:00.108056Z",
     "iopub.status.busy": "2023-05-12T12:23:00.107555Z",
     "iopub.status.idle": "2023-05-12T12:23:00.585205Z",
     "shell.execute_reply": "2023-05-12T12:23:00.584541Z"
    },
    "id": "nnQfxevhLKld"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmpfs/tmp/ipykernel_50997/4094752860.py:6: MatplotlibDeprecationWarning: Auto-removal of overlapping axes is deprecated since 3.6 and will be removed two minor releases later; explicitly call ax.remove() as needed.\n",
      "  ax = plt.subplot(subplot)\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x1000 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "display_training_curves(history.history['accuracy'], history.history['val_accuracy'], 'accuracy', 211)\n",
    "display_training_curves(history.history['loss'], history.history['val_loss'], 'loss', 212)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "BjvtOw72Lpyw"
   },
   "source": [
    "## Evaluate the model\n",
    "\n",
    "And 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": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-12T12:23:00.589121Z",
     "iopub.status.busy": "2023-05-12T12:23:00.588607Z",
     "iopub.status.idle": "2023-05-12T12:23:00.937984Z",
     "shell.execute_reply": "2023-05-12T12:23:00.937246Z"
    },
    "id": "y0ExC8D0LX8m"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4/4 - 0s - loss: 0.5376 - accuracy: 0.7897 - 336ms/epoch - 84ms/step\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "loss: 0.538\n",
      "accuracy: 0.790\n"
     ]
    }
   ],
   "source": [
    "results = model.evaluate(test_data.batch(512), verbose=2)\n",
    "\n",
    "for name, value in zip(model.metrics_names, results):\n",
    "  print('%s: %.3f' % (name, value))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "dWp5OWeTL2EW"
   },
   "source": [
    "We can see that the loss quickly decreases while especially the accuracy rapidly increases. Let's plot some examples to check how the prediction relates to the true labels:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-05-12T12:23:00.941415Z",
     "iopub.status.busy": "2023-05-12T12:23:00.940842Z",
     "iopub.status.idle": "2023-05-12T12:23:01.344290Z",
     "shell.execute_reply": "2023-05-12T12:23:01.343600Z"
    },
    "id": "VzHzAOaaOVC0"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "1/1 [==============================] - 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\r",
      "1/1 [==============================] - 0s 124ms/step\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>string</th>\n",
       "      <th>label</th>\n",
       "      <th>prediction</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>The diffraction grating, LED, and split detect...</td>\n",
       "      <td>background</td>\n",
       "      <td>method</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Our ideas are based on a previous paper [4] de...</td>\n",
       "      <td>background</td>\n",
       "      <td>method</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Our finding is consistent with the literature ...</td>\n",
       "      <td>result</td>\n",
       "      <td>result</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Test scores from each of the cognitive domains...</td>\n",
       "      <td>method</td>\n",
       "      <td>method</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>The optimization algorithm was set to maximize...</td>\n",
       "      <td>method</td>\n",
       "      <td>method</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>To quantify the extent of substitution saturat...</td>\n",
       "      <td>method</td>\n",
       "      <td>method</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Examples of gesture control are based on the e...</td>\n",
       "      <td>method</td>\n",
       "      <td>method</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>The identification of these features has been ...</td>\n",
       "      <td>method</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Postulated mechanisms for observed effects of ...</td>\n",
       "      <td>background</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>The right inferior phrenic artery is the most ...</td>\n",
       "      <td>background</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>[8] presented an approach for estimating the t...</td>\n",
       "      <td>background</td>\n",
       "      <td>method</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Similar structures were observed in M10 cells ...</td>\n",
       "      <td>result</td>\n",
       "      <td>method</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Cytotoxic effects of cobalt chloride were repo...</td>\n",
       "      <td>background</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>However, prolonged incubation of latex enzyme ...</td>\n",
       "      <td>background</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>…and travels great distances, resulting in a s...</td>\n",
       "      <td>background</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>The images fused using region selection; MSD, ...</td>\n",
       "      <td>method</td>\n",
       "      <td>method</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>These findings were expected, as EMG activity ...</td>\n",
       "      <td>result</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>The model has been extended to both 2D and 3D ...</td>\n",
       "      <td>method</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Therefore, many authors claim comprehensive nu...</td>\n",
       "      <td>background</td>\n",
       "      <td>method</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Similar to Ab40, IAPP-GI populates an aggregat...</td>\n",
       "      <td>background</td>\n",
       "      <td>background</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               string       label  prediction\n",
       "0   The diffraction grating, LED, and split detect...  background      method\n",
       "1   Our ideas are based on a previous paper [4] de...  background      method\n",
       "2   Our finding is consistent with the literature ...      result      result\n",
       "3   Test scores from each of the cognitive domains...      method      method\n",
       "4   The optimization algorithm was set to maximize...      method      method\n",
       "5   To quantify the extent of substitution saturat...      method      method\n",
       "6   Examples of gesture control are based on the e...      method      method\n",
       "7   The identification of these features has been ...      method  background\n",
       "8   Postulated mechanisms for observed effects of ...  background  background\n",
       "9   The right inferior phrenic artery is the most ...  background  background\n",
       "10  [8] presented an approach for estimating the t...  background      method\n",
       "11  Similar structures were observed in M10 cells ...      result      method\n",
       "12  Cytotoxic effects of cobalt chloride were repo...  background  background\n",
       "13  However, prolonged incubation of latex enzyme ...  background  background\n",
       "14  …and travels great distances, resulting in a s...  background  background\n",
       "15  The images fused using region selection; MSD, ...      method      method\n",
       "16  These findings were expected, as EMG activity ...      result  background\n",
       "17  The model has been extended to both 2D and 3D ...      method  background\n",
       "18  Therefore, many authors claim comprehensive nu...  background      method\n",
       "19  Similar to Ab40, IAPP-GI populates an aggregat...  background  background"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prediction_dataset = next(iter(test_data.batch(20)))\n",
    "\n",
    "prediction_texts = [ex.numpy().decode('utf8') for ex in prediction_dataset[0]]\n",
    "prediction_labels = [label2str(x) for x in prediction_dataset[1]]\n",
    "\n",
    "predictions = [\n",
    "    label2str(x) for x in np.argmax(model.predict(prediction_texts), axis=-1)]\n",
    "\n",
    "\n",
    "pd.DataFrame({\n",
    "    TEXT_FEATURE_NAME: prediction_texts,\n",
    "    LABEL_NAME: prediction_labels,\n",
    "    'prediction': predictions\n",
    "})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "OSGcrkE069_Q"
   },
   "source": [
    "We can see that for this random sample, the model predicts the correct label most of the times, indicating that it can embed scientific sentences pretty well."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "oLE0kCfO5CIA"
   },
   "source": [
    "# What's next?\n",
    "\n",
    "Now that you've gotten to know a bit more about the CORD-19 Swivel embeddings from TF-Hub, we encourage you to participate in the CORD-19 Kaggle competition to contribute to gaining scientific insights from COVID-19 related academic texts.\n",
    "\n",
    "* Participate in the [CORD-19 Kaggle Challenge](https://www.kaggle.com/allen-institute-for-ai/CORD-19-research-challenge)\n",
    "* Learn more about the [COVID-19 Open Research Dataset (CORD-19)](https://api.semanticscholar.org/CorpusID:216056360)\n",
    "* See documentation and more about the TF-Hub embeddings at https://tfhub.dev/tensorflow/cord-19/swivel-128d/3\n",
    "* Explore the CORD-19 embedding space with the [TensorFlow Embedding Projector](http://projector.tensorflow.org/?config=https://storage.googleapis.com/tfhub-examples/tensorflow/cord-19/swivel-128d/3/tensorboard/projector_config.json)"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exploring the TF-Hub CORD-19 Swivel Embeddings",
   "private_outputs": true,
   "provenance": [],
   "toc_visible": true
  },
  "kernelspec": {
   "display_name": "Python 3",
   "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
}