{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "MhoQ0WE77laV" }, "source": [ "##### Copyright 2018 The TensorFlow Authors." ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "cellView": "form", "execution": { "iopub.execute_input": "2020-09-23T00:11:56.326519Z", "iopub.status.busy": "2020-09-23T00:11:56.325854Z", "iopub.status.idle": "2020-09-23T00:11:56.328403Z", "shell.execute_reply": "2020-09-23T00:11:56.327903Z" }, "id": "_ckMIh7O7s6D" }, "outputs": [], "source": [ "#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n", "# you may not use this file except in compliance with the License.\n", "# You may obtain a copy of the License at\n", "#\n", "# https://www.apache.org/licenses/LICENSE-2.0\n", "#\n", "# Unless required by applicable law or agreed to in writing, software\n", "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", "# See the License for the specific language governing permissions and\n", "# limitations under the License." ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "cellView": "form", "execution": { "iopub.execute_input": "2020-09-23T00:11:56.332000Z", "iopub.status.busy": "2020-09-23T00:11:56.331371Z", "iopub.status.idle": "2020-09-23T00:11:56.333821Z", "shell.execute_reply": "2020-09-23T00:11:56.333323Z" }, "id": "vasWnqRgy1H4" }, "outputs": [], "source": [ "#@title MIT License\n", "#\n", "# Copyright (c) 2017 François Chollet\n", "#\n", "# Permission is hereby granted, free of charge, to any person obtaining a\n", "# copy of this software and associated documentation files (the \"Software\"),\n", "# to deal in the Software without restriction, including without limitation\n", "# the rights to use, copy, modify, merge, publish, distribute, sublicense,\n", "# and/or sell copies of the Software, and to permit persons to whom the\n", "# Software is furnished to do so, subject to the following conditions:\n", "#\n", "# The above copyright notice and this permission notice shall be included in\n", "# all copies or substantial portions of the Software.\n", "#\n", "# THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\n", "# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\n", "# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL\n", "# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\n", "# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING\n", "# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER\n", "# DEALINGS IN THE SOFTWARE." ] }, { "cell_type": "markdown", "metadata": { "id": "YenH_9hJbFk1" }, "source": [ "# Clasificacion Basica: Predecir una imagen de moda" ] }, { "cell_type": "markdown", "metadata": { "id": "S5Uhzt6vVIB2" }, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " View on TensorFlow.org\n", " \n", " Run in Google Colab\n", " \n", " View source on GitHub\n", " \n", " Download notebook\n", "
" ] }, { "cell_type": "markdown", "metadata": { "id": "Uo47Ynr8gNAU" }, "source": [ "Note: Nuestra comunidad de Tensorflow ha traducido estos documentos. Como las traducciones de la comunidad\n", "son basados en el \"mejor esfuerzo\", no hay ninguna garantia que esta sea un reflejo preciso y actual \n", "de la [Documentacion Oficial en Ingles](https://www.tensorflow.org/?hl=en).\n", "Si tienen sugerencias sobre como mejorar esta traduccion, por favor envian un \"Pull request\"\n", "al siguiente repositorio [tensorflow/docs](https://github.com/tensorflow/docs).\n", "Para ofrecerse como voluntario o hacer revision de las traducciones de la Comunidad\n", "por favor contacten al siguiente grupo [docs@tensorflow.org list](https://groups.google.com/a/tensorflow.org/forum/#!forum/docs)." ] }, { "cell_type": "markdown", "metadata": { "id": "FbVhjPpzn6BM" }, "source": [ "Esta Guia entrena un modelo de red neuronal para clasificar imagenes de ropa como, tennis y camisetas. No hay problema sino entiende todos los detalles; es un repaso rapido de un programa completo de Tensorflow con los detalles explicados a medida que avanza.\n", "\n", "Esta Guia usa [tf.keras](https://www.tensorflow.org/guide/keras), un API de alto nivel para construir y entrenar modelos en Tensorflow." ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:11:56.338306Z", "iopub.status.busy": "2020-09-23T00:11:56.337617Z", "iopub.status.idle": "2020-09-23T00:12:03.150200Z", "shell.execute_reply": "2020-09-23T00:12:03.150753Z" }, "id": "dzLKpmZICaWN" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "2.3.0\n" ] } ], "source": [ "# TensorFlow y tf.keras\n", "import tensorflow as tf\n", "from tensorflow import keras\n", "\n", "# Librerias de ayuda\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "\n", "print(tf.__version__)" ] }, { "cell_type": "markdown", "metadata": { "id": "yR0EdgrLCaWR" }, "source": [ "## Importar el set de datos de moda de MNIST" ] }, { "cell_type": "markdown", "metadata": { "id": "DLdCchMdCaWQ" }, "source": [ "Esta guia usa el set de datos de [Fashion MNIST](https://github.com/zalandoresearch/fashion-mnist)\n", "que contiene mas de 70,000 imagenes en 10 categorias. Las imagenes muestran articulos individuales de ropa a una resolucion baja (28 por 28 pixeles) como se ve aca:\n", "\n", "\n", " \n", " \n", "
\n", " \"Fashion\n", "
\n", " Figure 1. Fashion-MNIST samples (by Zalando, MIT License).
 \n", "
\n", "\n", "Moda MNIST esta construida como un reemplazo para el set de datos clasico [MNIST](http://yann.lecun.com/exdb/mnist/) \n", "casi siempre utilizado como el \"Hola Mundo\" de programas de aprendizaje automatico (ML) para computo de vision. El set de datos de MNIST contiene imagenes de digitos escrito a mano (0, 1, 2, etc.) en un formato identico al de los articulos de ropa que va a utilizar aca.\n", "\n", "Esta guia utiliza Moda MNIST para variedad y por que es un poco mas retador que la regular MNIST. Ambos set de datos son relativamente pequenos y son usados para verificar que el algoritmo funciona como debe.\n", "\n", "Aca, 60,000 imagenes son usadas para entrenar la red neuronal y 10,000 imagenes son usadas para evaluar que tan exacto aprendia la red a clasificar imagenes. Pueden acceder al set de moda de MNIST directamente desde TensorFlow. Para importar y cargar el set de datos de MNIST directamente de TensorFlow:" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:03.156630Z", "iopub.status.busy": "2020-09-23T00:12:03.154908Z", "iopub.status.idle": "2020-09-23T00:12:04.600741Z", "shell.execute_reply": "2020-09-23T00:12:04.600139Z" }, "id": "7MqDQO0KCaWS" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz\n", "\r", " 8192/29515 [=======>......................] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "32768/29515 [=================================] - 0s 0us/step\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz\n", "\r", " 8192/26421880 [..............................] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 4202496/26421880 [===>..........................] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 8396800/26421880 [========>.....................] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "13443072/26421880 [==============>...............] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "16785408/26421880 [==================>...........] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "21520384/26421880 [=======================>......] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "25174016/26421880 [===========================>..] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "26427392/26421880 [==============================] - 1s 0us/step\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8192/5148 [===============================================] - 0s 0us/step\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 8192/4422102 [..............................] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "4423680/4422102 [==============================] - 0s 0us/step\n" ] } ], "source": [ "fashion_mnist = keras.datasets.fashion_mnist\n", "\n", "(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()" ] }, { "cell_type": "markdown", "metadata": { "id": "t9FDsUlxCaWW" }, "source": [ "[link text](https://)Al cargar el set de datos retorna cuatro arreglos en NumPy:\n", "\n", "* El arreglo `train_images` y `train_labels` son los arreglos que *training set*—el modelo de datos usa para aprender.\n", "* el modelo es probado contra los arreglos *test set*, el `test_images`, y `test_labels`.\n", "\n", "Las imagenes son 28x28 arreglos de NumPy, con valores de pixel que varian de 0 a 255. Los *labels* son un arreglo de integros, que van del 0 al 9. Estos corresponden a la *class* de ropa que la imagen representa.\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
LabelClass
0T-shirt/top
1Trouser
2Pullover
3Dress
4Coat
5Sandal
6Shirt
7Sneaker
8Bag
9Ankle boot
\n", "\n", "Cada imagen es mapeada a una unica etiqueta. Ya que los *Class names* no estan incluidoen el dataset, almacenelo aca para usarlos luego cuando se visualicen las imagenes:" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:04.605691Z", "iopub.status.busy": "2020-09-23T00:12:04.605005Z", "iopub.status.idle": "2020-09-23T00:12:04.607235Z", "shell.execute_reply": "2020-09-23T00:12:04.606589Z" }, "id": "IjnLH5S2CaWx" }, "outputs": [], "source": [ "class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',\n", " 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']" ] }, { "cell_type": "markdown", "metadata": { "id": "Brm0b_KACaWX" }, "source": [ "## Explore el set de datos\n", "\n", "Explore el formato de el set de datos antes de entrenar el modelo. Lo siguiente muestra que hay 60,000 imagenes en el set de entrenamiento, con cada imagen representada por pixeles de 28x28:" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:04.612889Z", "iopub.status.busy": "2020-09-23T00:12:04.612214Z", "iopub.status.idle": "2020-09-23T00:12:04.615425Z", "shell.execute_reply": "2020-09-23T00:12:04.615926Z" }, "id": "zW5k_xz1CaWX" }, "outputs": [ { "data": { "text/plain": [ "(60000, 28, 28)" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_images.shape" ] }, { "cell_type": "markdown", "metadata": { "id": "cIAcvQqMCaWf" }, "source": [ "Asimismo, hay 60,000 etiquetas en el set de entrenamiento:" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:04.619917Z", "iopub.status.busy": "2020-09-23T00:12:04.619263Z", "iopub.status.idle": "2020-09-23T00:12:04.622504Z", "shell.execute_reply": "2020-09-23T00:12:04.621929Z" }, "id": "TRFYHB2mCaWb" }, "outputs": [ { "data": { "text/plain": [ "60000" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(train_labels)" ] }, { "cell_type": "markdown", "metadata": { "id": "YSlYxFuRCaWk" }, "source": [ "Cada etiqueta es un integro entre 0 y 9:" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:04.626690Z", "iopub.status.busy": "2020-09-23T00:12:04.626075Z", "iopub.status.idle": "2020-09-23T00:12:04.629060Z", "shell.execute_reply": "2020-09-23T00:12:04.628553Z" }, "id": "XKnCTHz4CaWg" }, "outputs": [ { "data": { "text/plain": [ "array([9, 0, 0, ..., 3, 0, 5], dtype=uint8)" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_labels" ] }, { "cell_type": "markdown", "metadata": { "id": "TMPI88iZpO2T" }, "source": [ "Hay 10,000 imagenes en el set de pruebas. Otra vez, cada imagen es representada como pixeles de 28x28:" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:04.632971Z", "iopub.status.busy": "2020-09-23T00:12:04.632319Z", "iopub.status.idle": "2020-09-23T00:12:04.634737Z", "shell.execute_reply": "2020-09-23T00:12:04.635201Z" }, "id": "2KFnYlcwCaWl" }, "outputs": [ { "data": { "text/plain": [ "(10000, 28, 28)" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_images.shape" ] }, { "cell_type": "markdown", "metadata": { "id": "rd0A0Iu0CaWq" }, "source": [ "Y el set de pruebas contiene 10,000 etiquetas de imagen:" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:04.638892Z", "iopub.status.busy": "2020-09-23T00:12:04.638288Z", "iopub.status.idle": "2020-09-23T00:12:04.641162Z", "shell.execute_reply": "2020-09-23T00:12:04.640615Z" }, "id": "iJmPr5-ACaWn" }, "outputs": [ { "data": { "text/plain": [ "10000" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(test_labels)" ] }, { "cell_type": "markdown", "metadata": { "id": "ES6uQoLKCaWr" }, "source": [ "## Pre-procese el set de datos\n", "\n", "El set de datos debe ser pre-procesada antes de entrenar la red. Si usted inspecciona la primera imagen en el set de entrenamiento, va a encontrar que los valores de los pixeles estan entre 0 y 255:" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:04.662721Z", "iopub.status.busy": "2020-09-23T00:12:04.645719Z", "iopub.status.idle": "2020-09-23T00:12:04.845607Z", "shell.execute_reply": "2020-09-23T00:12:04.846037Z" }, "id": "m4VEw8Ud9Quh" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plt.figure()\n", "plt.imshow(train_images[0])\n", "plt.colorbar()\n", "plt.grid(False)\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": { "id": "Wz7l27Lz9S1P" }, "source": [ "Escale estos valores en un rango de 0 a 1 antes de alimentarlos al modelo de la red neuronal. Para hacero, divida los valores por 255. Es importante que el *training set* y el *testing set* se pre-procesen de la misma forma:" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:04.850245Z", "iopub.status.busy": "2020-09-23T00:12:04.849612Z", "iopub.status.idle": "2020-09-23T00:12:05.014795Z", "shell.execute_reply": "2020-09-23T00:12:05.015335Z" }, "id": "bW5WzIPlCaWv" }, "outputs": [], "source": [ "train_images = train_images / 255.0\n", "\n", "test_images = test_images / 255.0" ] }, { "cell_type": "markdown", "metadata": { "id": "Ee638AlnCaWz" }, "source": [ "Para verificar que el set de datos esta en el formato adecuado y que estan listos para construir y entrenar la red, vamos a desplegar las primeras 25 imagenes de el *training set* y despleguemos el nombre de cada clase debajo de cada imagen." ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:05.031312Z", "iopub.status.busy": "2020-09-23T00:12:05.030478Z", "iopub.status.idle": "2020-09-23T00:12:05.895379Z", "shell.execute_reply": "2020-09-23T00:12:05.895951Z" }, "id": "oZTImqg_CaW1" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.figure(figsize=(10,10))\n", "for i in range(25):\n", " plt.subplot(5,5,i+1)\n", " plt.xticks([])\n", " plt.yticks([])\n", " plt.grid(False)\n", " plt.imshow(train_images[i], cmap=plt.cm.binary)\n", " plt.xlabel(class_names[train_labels[i]])\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": { "id": "59veuiEZCaW4" }, "source": [ "## Construir el Modelo\n", "\n", "Construir la red neuronal requiere configurar las capas del modelo y luego compilar el modelo." ] }, { "cell_type": "markdown", "metadata": { "id": "Gxg1XGm0eOBy" }, "source": [ "### Configurar las Capas\n", "\n", "Los bloques de construccion basicos de una red neuronal son las *capas* o *layers*. Las capas extraen representaciones de el set de datos que se les alimentan. Con suerte, estas representaciones son considerables para el problema que estamos solucionando.\n", "\n", "La mayoria de aprendizaje profundo consiste de unir capas sencillas. \n", "La mayoria de las capas como `tf.keras.layers.Dense`, tienen parametros que son aprendidos durante el entrenamiento." ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:05.902968Z", "iopub.status.busy": "2020-09-23T00:12:05.900405Z", "iopub.status.idle": "2020-09-23T00:12:07.650519Z", "shell.execute_reply": "2020-09-23T00:12:07.650995Z" }, "id": "9ODch-OFCaW4" }, "outputs": [], "source": [ "model = keras.Sequential([\n", " keras.layers.Flatten(input_shape=(28, 28)),\n", " keras.layers.Dense(128, activation='relu'),\n", " keras.layers.Dense(10, activation='softmax')\n", "])" ] }, { "cell_type": "markdown", "metadata": { "id": "gut8A_7rCaW6" }, "source": [ "La primera capa de esta red, `tf.keras.layers.Flatten`, \n", "transforma el formato de las imagenes de un arreglo bi-dimensional (de 28 por 28 pixeles) a un arreglo uni dimensional (de 28*28 pixeles = 784 pixeles). Observe esta capa como una capa no apilada de filas de pixeles en la misma imagen y alineandolo. Esta capa no tiene parametros que aprender; solo reformatea el set de datos.\n", "\n", "Despues de que los pixeles estan \"aplanados\", la secuencia consiste de dos capas`tf.keras.layers.Dense`. Estas estan densamente conectadas, o completamente conectadas. La primera capa `Dense` tiene 128 nodos (o neuronas). La segunda (y ultima) capa es una capa de 10 nodos *softmax* que devuelve un arreglo de 10 probabilidades que suman a 1. Cada nodo contiene una calificacion que indica la probabilidad que la actual imagen pertenece a una de las 10 clases.\n", "\n", "### Compile el modelo\n", "\n", "Antes de que el modelo este listo para entrenar , se necesitan algunas configuraciones mas. Estas son agregadas durante el paso de compilacion del modelo:\n", "\n", "* *Loss function* —Esto mide que tan exacto es el modelo durante el entrenamiento. Quiere minimizar esta funcion para dirigir el modelo en la direccion adecuada.\n", "* *Optimizer* — Esto es como el modelo se actualiza basado en el set de datos que ve y la funcion de perdida.\n", "* *Metrics* — Se usan para monitorear los pasos de entrenamiento y de pruebas.\n", "El siguiente ejemplo usa *accuracy* (exactitud) , la fraccion de la imagenes que son correctamente clasificadas." ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:07.663857Z", "iopub.status.busy": "2020-09-23T00:12:07.663044Z", "iopub.status.idle": "2020-09-23T00:12:07.670764Z", "shell.execute_reply": "2020-09-23T00:12:07.670104Z" }, "id": "Lhan11blCaW7" }, "outputs": [], "source": [ "model.compile(optimizer='adam',\n", " loss='sparse_categorical_crossentropy',\n", " metrics=['accuracy'])" ] }, { "cell_type": "markdown", "metadata": { "id": "qKF6uW-BCaW-" }, "source": [ "## Entrenar el Modelo\n", "\n", "Entrenar el modelo de red neuronal requiere de los siguientes pasos:\n", "\n", "1. Entregue los datos de entrenamiento al modelo. En este ejemplo , el set de datos de entrenamiento estan en los arreglos `train_images` y `train_labels`.\n", "2. el modelo aprende a asociar imagenes y etiquetas.\n", "3. Usted le pregunta al modelo que haga predicciones sobre un set de datos que se encuentran en el ejemplo,incluido en el arreglo `test_images`. Verifique que las predicciones sean iguales a las etiquetas de el arreglo`test_labels`.\n", "\n", "Para comenzar a entrenar, llame el metodo `model.fit`, es llamado asi por que *fit* (ajusta) el modelo a el set de datos de entrenamiento:" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:07.675211Z", "iopub.status.busy": "2020-09-23T00:12:07.674345Z", "iopub.status.idle": "2020-09-23T00:12:36.454526Z", "shell.execute_reply": "2020-09-23T00:12:36.453882Z" }, "id": "xvwvpA64CaW_" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/1875 [..............................] - ETA: 0s - loss: 2.4750 - accuracy: 0.1250" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 35/1875 [..............................] - ETA: 2s - loss: 1.3644 - accuracy: 0.5732" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 70/1875 [>.............................] - ETA: 2s - loss: 1.0950 - accuracy: 0.6371" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 104/1875 [>.............................] - ETA: 2s - loss: 0.9755 - accuracy: 0.6689" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 138/1875 [=>............................] - ETA: 2s - loss: 0.9059 - accuracy: 0.6904" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 172/1875 [=>............................] - ETA: 2s - loss: 0.8516 - accuracy: 0.7057" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 207/1875 [==>...........................] - ETA: 2s - loss: 0.8094 - accuracy: 0.7216" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 241/1875 [==>...........................] - ETA: 2s - loss: 0.7767 - accuracy: 0.7329" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 275/1875 [===>..........................] - ETA: 2s - loss: 0.7476 - accuracy: 0.7427" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 310/1875 [===>..........................] - ETA: 2s - loss: 0.7216 - accuracy: 0.7521" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 344/1875 [====>.........................] - ETA: 2s - loss: 0.7050 - accuracy: 0.7563" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 378/1875 [=====>........................] - ETA: 2s - loss: 0.6920 - accuracy: 0.7602" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 412/1875 [=====>........................] - ETA: 2s - loss: 0.6852 - accuracy: 0.7636" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 446/1875 [======>.......................] - ETA: 2s - loss: 0.6774 - accuracy: 0.7665" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 480/1875 [======>.......................] - ETA: 2s - loss: 0.6630 - accuracy: 0.7714" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 514/1875 [=======>......................] - ETA: 2s - loss: 0.6523 - accuracy: 0.7747" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 548/1875 [=======>......................] - ETA: 1s - loss: 0.6429 - 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\b\b\r", " 583/1875 [========>.....................] - ETA: 1s - loss: 0.6336 - accuracy: 0.7815" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 618/1875 [========>.....................] - ETA: 1s - loss: 0.6267 - accuracy: 0.7833" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 652/1875 [=========>....................] - ETA: 1s - loss: 0.6201 - accuracy: 0.7857" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 687/1875 [=========>....................] - ETA: 1s - loss: 0.6131 - accuracy: 0.7870" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 722/1875 [==========>...................] - ETA: 1s - loss: 0.6064 - 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\b\b\r", " 756/1875 [===========>..................] - ETA: 1s - loss: 0.6013 - 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\b\b\r", " 791/1875 [===========>..................] - ETA: 1s - loss: 0.5944 - accuracy: 0.7927" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 826/1875 [============>.................] - ETA: 1s - loss: 0.5886 - 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\b\b\r", " 860/1875 [============>.................] - ETA: 1s - loss: 0.5855 - accuracy: 0.7957" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 894/1875 [=============>................] - ETA: 1s - loss: 0.5809 - 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\b\b\r", " 928/1875 [=============>................] - ETA: 1s - loss: 0.5759 - 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\b\b\r", " 962/1875 [==============>...............] - ETA: 1s - loss: 0.5716 - 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\b\b\r", " 996/1875 [==============>...............] - ETA: 1s - loss: 0.5686 - 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\b\b\r", "1031/1875 [===============>..............] - ETA: 1s - loss: 0.5642 - accuracy: 0.8034" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1066/1875 [================>.............] - ETA: 1s - loss: 0.5608 - accuracy: 0.8044" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1100/1875 [================>.............] - ETA: 1s - loss: 0.5564 - 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\b\b\r", "1134/1875 [=================>............] - ETA: 1s - loss: 0.5527 - accuracy: 0.8077" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1168/1875 [=================>............] - ETA: 1s - loss: 0.5507 - 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\b\b\r", "1202/1875 [==================>...........] - ETA: 0s - loss: 0.5479 - accuracy: 0.8091" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1236/1875 [==================>...........] - ETA: 0s - loss: 0.5449 - accuracy: 0.8099" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1271/1875 [===================>..........] - ETA: 0s - loss: 0.5418 - 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\b\b\r", "1306/1875 [===================>..........] - ETA: 0s - loss: 0.5398 - accuracy: 0.8117" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1341/1875 [====================>.........] - ETA: 0s - loss: 0.5377 - accuracy: 0.8126" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1375/1875 [=====================>........] - ETA: 0s - loss: 0.5345 - accuracy: 0.8133" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1409/1875 [=====================>........] - ETA: 0s - loss: 0.5313 - 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\b\b\r", "1443/1875 [======================>.......] - ETA: 0s - loss: 0.5289 - accuracy: 0.8152" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1477/1875 [======================>.......] - ETA: 0s - loss: 0.5257 - accuracy: 0.8162" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1511/1875 [=======================>......] - ETA: 0s - loss: 0.5240 - accuracy: 0.8169" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1546/1875 [=======================>......] - ETA: 0s - loss: 0.5218 - accuracy: 0.8175" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1580/1875 [========================>.....] - ETA: 0s - loss: 0.5189 - accuracy: 0.8184" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1614/1875 [========================>.....] - ETA: 0s - loss: 0.5158 - accuracy: 0.8192" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1649/1875 [=========================>....] - ETA: 0s - loss: 0.5122 - accuracy: 0.8204" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1683/1875 [=========================>....] - ETA: 0s - loss: 0.5100 - accuracy: 0.8210" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1717/1875 [==========================>...] - ETA: 0s - loss: 0.5088 - accuracy: 0.8211" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1752/1875 [===========================>..] - ETA: 0s - loss: 0.5067 - accuracy: 0.8221" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1785/1875 [===========================>..] - ETA: 0s - loss: 0.5049 - accuracy: 0.8228" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1820/1875 [============================>.] - ETA: 0s - loss: 0.5036 - accuracy: 0.8233" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1853/1875 [============================>.] - ETA: 0s - loss: 0.5012 - accuracy: 0.8238" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1875/1875 [==============================] - 3s 1ms/step - loss: 0.5003 - accuracy: 0.8241\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 2/10\n", "\r", " 1/1875 [..............................] - ETA: 0s - loss: 0.3235 - 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", " 33/1875 [..............................] - ETA: 2s - loss: 0.3450 - accuracy: 0.8816" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 66/1875 [>.............................] - ETA: 2s - loss: 0.3862 - accuracy: 0.8617" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 100/1875 [>.............................] - ETA: 2s - loss: 0.4087 - accuracy: 0.8594" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 134/1875 [=>............................] - ETA: 2s - loss: 0.4085 - accuracy: 0.8601" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 168/1875 [=>............................] - ETA: 2s - loss: 0.4066 - accuracy: 0.8609" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 202/1875 [==>...........................] - ETA: 2s - loss: 0.3978 - accuracy: 0.8632" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 235/1875 [==>...........................] - ETA: 2s - loss: 0.3924 - accuracy: 0.8636" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 270/1875 [===>..........................] - ETA: 2s - loss: 0.3928 - accuracy: 0.8625" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 305/1875 [===>..........................] - ETA: 2s - loss: 0.3941 - accuracy: 0.8618" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 340/1875 [====>.........................] - ETA: 2s - loss: 0.3969 - accuracy: 0.8591" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 374/1875 [====>.........................] - ETA: 2s - loss: 0.3965 - accuracy: 0.8598" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 409/1875 [=====>........................] - ETA: 2s - loss: 0.3945 - accuracy: 0.8602" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 444/1875 [======>.......................] - ETA: 2s - loss: 0.3913 - accuracy: 0.8610" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 479/1875 [======>.......................] - ETA: 2s - loss: 0.3892 - accuracy: 0.8620" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 514/1875 [=======>......................] - ETA: 2s - loss: 0.3870 - accuracy: 0.8622" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 548/1875 [=======>......................] - ETA: 1s - loss: 0.3855 - accuracy: 0.8628" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 582/1875 [========>.....................] - ETA: 1s - loss: 0.3849 - accuracy: 0.8628" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 616/1875 [========>.....................] - ETA: 1s - loss: 0.3850 - accuracy: 0.8622" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 650/1875 [=========>....................] - ETA: 1s - loss: 0.3852 - accuracy: 0.8615" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 685/1875 [=========>....................] - ETA: 1s - loss: 0.3841 - accuracy: 0.8619" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 719/1875 [==========>...................] - ETA: 1s - loss: 0.3867 - accuracy: 0.8614" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 754/1875 [===========>..................] - ETA: 1s - loss: 0.3852 - accuracy: 0.8617" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 789/1875 [===========>..................] - ETA: 1s - loss: 0.3840 - accuracy: 0.8622" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 823/1875 [============>.................] - ETA: 1s - loss: 0.3850 - accuracy: 0.8620" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 857/1875 [============>.................] - ETA: 1s - loss: 0.3856 - accuracy: 0.8621" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 891/1875 [=============>................] - ETA: 1s - loss: 0.3856 - accuracy: 0.8620" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 925/1875 [=============>................] - ETA: 1s - loss: 0.3861 - accuracy: 0.8617" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 959/1875 [==============>...............] - ETA: 1s - loss: 0.3858 - accuracy: 0.8617" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 993/1875 [==============>...............] - ETA: 1s - loss: 0.3842 - accuracy: 0.8625" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1027/1875 [===============>..............] - ETA: 1s - loss: 0.3830 - accuracy: 0.8629" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1062/1875 [===============>..............] - ETA: 1s - loss: 0.3829 - accuracy: 0.8628" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1096/1875 [================>.............] - ETA: 1s - loss: 0.3816 - accuracy: 0.8632" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1130/1875 [=================>............] - ETA: 1s - loss: 0.3816 - accuracy: 0.8632" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1164/1875 [=================>............] - ETA: 1s - loss: 0.3817 - accuracy: 0.8630" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1198/1875 [==================>...........] - ETA: 1s - loss: 0.3817 - accuracy: 0.8630" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1232/1875 [==================>...........] - ETA: 0s - loss: 0.3810 - accuracy: 0.8628" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1266/1875 [===================>..........] - ETA: 0s - loss: 0.3808 - accuracy: 0.8631" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1300/1875 [===================>..........] - ETA: 0s - loss: 0.3811 - accuracy: 0.8633" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1335/1875 [====================>.........] - ETA: 0s - loss: 0.3804 - accuracy: 0.8636" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1368/1875 [====================>.........] - ETA: 0s - loss: 0.3795 - accuracy: 0.8638" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1402/1875 [=====================>........] - ETA: 0s - loss: 0.3786 - accuracy: 0.8642" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1437/1875 [=====================>........] - ETA: 0s - loss: 0.3783 - accuracy: 0.8644" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1472/1875 [======================>.......] - ETA: 0s - loss: 0.3776 - accuracy: 0.8648" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1505/1875 [=======================>......] - ETA: 0s - loss: 0.3772 - accuracy: 0.8648" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1539/1875 [=======================>......] - ETA: 0s - loss: 0.3759 - accuracy: 0.8653" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1574/1875 [========================>.....] - ETA: 0s - loss: 0.3756 - accuracy: 0.8654" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1608/1875 [========================>.....] - ETA: 0s - loss: 0.3751 - accuracy: 0.8656" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1642/1875 [=========================>....] - ETA: 0s - loss: 0.3753 - accuracy: 0.8658" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1676/1875 [=========================>....] - ETA: 0s - loss: 0.3748 - accuracy: 0.8658" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1710/1875 [==========================>...] - ETA: 0s - loss: 0.3747 - accuracy: 0.8657" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1744/1875 [==========================>...] - ETA: 0s - loss: 0.3752 - accuracy: 0.8657" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1778/1875 [===========================>..] - ETA: 0s - loss: 0.3745 - accuracy: 0.8658" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1813/1875 [============================>.] - ETA: 0s - loss: 0.3745 - accuracy: 0.8661" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1848/1875 [============================>.] - ETA: 0s - loss: 0.3746 - accuracy: 0.8662" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1875/1875 [==============================] - 3s 1ms/step - loss: 0.3747 - accuracy: 0.8661\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 3/10\n", "\r", " 1/1875 [..............................] - ETA: 0s - loss: 0.1675 - 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", " 36/1875 [..............................] - ETA: 2s - loss: 0.3319 - accuracy: 0.8741" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 70/1875 [>.............................] - ETA: 2s - loss: 0.3328 - accuracy: 0.8781" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 104/1875 [>.............................] - ETA: 2s - loss: 0.3235 - accuracy: 0.8834" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 139/1875 [=>............................] - ETA: 2s - loss: 0.3237 - accuracy: 0.8833" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 173/1875 [=>............................] - ETA: 2s - loss: 0.3257 - accuracy: 0.8801" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 208/1875 [==>...........................] - ETA: 2s - loss: 0.3338 - accuracy: 0.8777" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 243/1875 [==>...........................] - ETA: 2s - loss: 0.3362 - accuracy: 0.8760" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 278/1875 [===>..........................] - ETA: 2s - loss: 0.3381 - 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", " 312/1875 [===>..........................] - ETA: 2s - loss: 0.3375 - accuracy: 0.8766" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 346/1875 [====>.........................] - ETA: 2s - loss: 0.3380 - accuracy: 0.8764" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 381/1875 [=====>........................] - ETA: 2s - loss: 0.3371 - accuracy: 0.8763" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 415/1875 [=====>........................] - ETA: 2s - loss: 0.3381 - accuracy: 0.8761" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 449/1875 [======>.......................] - ETA: 2s - loss: 0.3359 - accuracy: 0.8762" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 483/1875 [======>.......................] - ETA: 2s - loss: 0.3373 - accuracy: 0.8763" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 517/1875 [=======>......................] - ETA: 1s - loss: 0.3386 - accuracy: 0.8761" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 552/1875 [=======>......................] - ETA: 1s - loss: 0.3394 - accuracy: 0.8760" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 587/1875 [========>.....................] - ETA: 1s - loss: 0.3375 - accuracy: 0.8771" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 622/1875 [========>.....................] - ETA: 1s - loss: 0.3364 - accuracy: 0.8774" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 656/1875 [=========>....................] - ETA: 1s - loss: 0.3367 - accuracy: 0.8772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 690/1875 [==========>...................] - ETA: 1s - loss: 0.3359 - accuracy: 0.8774" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 724/1875 [==========>...................] - ETA: 1s - loss: 0.3351 - accuracy: 0.8775" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 757/1875 [===========>..................] - ETA: 1s - loss: 0.3334 - accuracy: 0.8783" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 791/1875 [===========>..................] - ETA: 1s - loss: 0.3340 - accuracy: 0.8781" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 826/1875 [============>.................] - ETA: 1s - loss: 0.3344 - accuracy: 0.8776" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 860/1875 [============>.................] - ETA: 1s - loss: 0.3350 - accuracy: 0.8775" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 894/1875 [=============>................] - ETA: 1s - loss: 0.3352 - accuracy: 0.8775" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 928/1875 [=============>................] - ETA: 1s - loss: 0.3362 - accuracy: 0.8770" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 962/1875 [==============>...............] - ETA: 1s - loss: 0.3371 - accuracy: 0.8770" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 997/1875 [==============>...............] - ETA: 1s - loss: 0.3377 - accuracy: 0.8770" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1031/1875 [===============>..............] - ETA: 1s - loss: 0.3368 - accuracy: 0.8771" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1065/1875 [================>.............] - ETA: 1s - loss: 0.3370 - accuracy: 0.8768" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1099/1875 [================>.............] - ETA: 1s - loss: 0.3381 - accuracy: 0.8765" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1134/1875 [=================>............] - ETA: 1s - loss: 0.3367 - accuracy: 0.8771" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1169/1875 [=================>............] - ETA: 1s - loss: 0.3372 - accuracy: 0.8770" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1204/1875 [==================>...........] - ETA: 0s - loss: 0.3373 - accuracy: 0.8772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1239/1875 [==================>...........] - ETA: 0s - loss: 0.3380 - accuracy: 0.8769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1274/1875 [===================>..........] - ETA: 0s - loss: 0.3364 - accuracy: 0.8776" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1308/1875 [===================>..........] - ETA: 0s - loss: 0.3357 - accuracy: 0.8779" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1342/1875 [====================>.........] - ETA: 0s - loss: 0.3366 - accuracy: 0.8775" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1376/1875 [=====================>........] - ETA: 0s - loss: 0.3359 - accuracy: 0.8779" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1410/1875 [=====================>........] - ETA: 0s - loss: 0.3350 - accuracy: 0.8780" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1445/1875 [======================>.......] - ETA: 0s - loss: 0.3349 - accuracy: 0.8778" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1479/1875 [======================>.......] - ETA: 0s - loss: 0.3336 - accuracy: 0.8780" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1513/1875 [=======================>......] - ETA: 0s - loss: 0.3335 - accuracy: 0.8781" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1547/1875 [=======================>......] - ETA: 0s - loss: 0.3335 - accuracy: 0.8783" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1581/1875 [========================>.....] - ETA: 0s - loss: 0.3332 - accuracy: 0.8784" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1616/1875 [========================>.....] - ETA: 0s - loss: 0.3334 - accuracy: 0.8784" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1650/1875 [=========================>....] - ETA: 0s - loss: 0.3340 - accuracy: 0.8784" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1684/1875 [=========================>....] - ETA: 0s - loss: 0.3350 - accuracy: 0.8779" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1718/1875 [==========================>...] - ETA: 0s - loss: 0.3343 - accuracy: 0.8783" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1752/1875 [===========================>..] - ETA: 0s - loss: 0.3346 - accuracy: 0.8784" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1787/1875 [===========================>..] - ETA: 0s - loss: 0.3347 - accuracy: 0.8784" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1821/1875 [============================>.] - ETA: 0s - loss: 0.3349 - accuracy: 0.8782" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1855/1875 [============================>.] - ETA: 0s - loss: 0.3355 - accuracy: 0.8778" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1875/1875 [==============================] - 3s 1ms/step - loss: 0.3359 - accuracy: 0.8776\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 4/10\n", "\r", " 1/1875 [..............................] - ETA: 0s - loss: 0.3793 - 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", " 35/1875 [..............................] - ETA: 2s - loss: 0.3246 - accuracy: 0.8768" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 68/1875 [>.............................] - ETA: 2s - loss: 0.3076 - accuracy: 0.8842" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 100/1875 [>.............................] - ETA: 2s - loss: 0.3153 - accuracy: 0.8831" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 133/1875 [=>............................] - ETA: 2s - loss: 0.3115 - accuracy: 0.8863" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 166/1875 [=>............................] - ETA: 2s - loss: 0.3206 - accuracy: 0.8829" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 199/1875 [==>...........................] - ETA: 2s - loss: 0.3201 - accuracy: 0.8822" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 233/1875 [==>...........................] - ETA: 2s - loss: 0.3188 - accuracy: 0.8830" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 267/1875 [===>..........................] - ETA: 2s - loss: 0.3207 - accuracy: 0.8819" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 300/1875 [===>..........................] - ETA: 2s - loss: 0.3224 - accuracy: 0.8818" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 334/1875 [====>.........................] - ETA: 2s - loss: 0.3229 - accuracy: 0.8813" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 368/1875 [====>.........................] - ETA: 2s - loss: 0.3240 - accuracy: 0.8808" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 401/1875 [=====>........................] - ETA: 2s - loss: 0.3217 - accuracy: 0.8825" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 434/1875 [=====>........................] - ETA: 2s - loss: 0.3213 - accuracy: 0.8821" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 468/1875 [======>.......................] - ETA: 2s - loss: 0.3211 - accuracy: 0.8827" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 502/1875 [=======>......................] - ETA: 2s - loss: 0.3221 - accuracy: 0.8821" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 536/1875 [=======>......................] - ETA: 2s - loss: 0.3224 - accuracy: 0.8824" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 570/1875 [========>.....................] - ETA: 1s - loss: 0.3205 - accuracy: 0.8825" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 604/1875 [========>.....................] - ETA: 1s - loss: 0.3188 - accuracy: 0.8832" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 638/1875 [=========>....................] - ETA: 1s - loss: 0.3203 - accuracy: 0.8825" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 672/1875 [=========>....................] - ETA: 1s - loss: 0.3194 - accuracy: 0.8824" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 707/1875 [==========>...................] - ETA: 1s - loss: 0.3193 - accuracy: 0.8826" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 740/1875 [==========>...................] - ETA: 1s - loss: 0.3210 - accuracy: 0.8822" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 774/1875 [===========>..................] - ETA: 1s - loss: 0.3201 - accuracy: 0.8823" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 807/1875 [===========>..................] - ETA: 1s - loss: 0.3199 - accuracy: 0.8825" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 841/1875 [============>.................] - ETA: 1s - loss: 0.3206 - accuracy: 0.8820" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 874/1875 [============>.................] - ETA: 1s - loss: 0.3223 - accuracy: 0.8818" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 908/1875 [=============>................] - ETA: 1s - loss: 0.3212 - accuracy: 0.8822" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 942/1875 [==============>...............] - ETA: 1s - loss: 0.3219 - accuracy: 0.8817" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 976/1875 [==============>...............] - ETA: 1s - loss: 0.3207 - accuracy: 0.8819" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1010/1875 [===============>..............] - ETA: 1s - loss: 0.3192 - accuracy: 0.8822" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1044/1875 [===============>..............] - ETA: 1s - loss: 0.3181 - accuracy: 0.8825" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1078/1875 [================>.............] - ETA: 1s - loss: 0.3182 - accuracy: 0.8827" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1112/1875 [================>.............] - ETA: 1s - loss: 0.3178 - accuracy: 0.8828" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1146/1875 [=================>............] - ETA: 1s - loss: 0.3179 - accuracy: 0.8829" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1180/1875 [=================>............] - ETA: 1s - loss: 0.3175 - accuracy: 0.8832" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1214/1875 [==================>...........] - ETA: 0s - loss: 0.3175 - accuracy: 0.8832" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1249/1875 [==================>...........] - ETA: 0s - loss: 0.3171 - accuracy: 0.8834" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1283/1875 [===================>..........] - ETA: 0s - loss: 0.3163 - accuracy: 0.8835" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1317/1875 [====================>.........] - ETA: 0s - loss: 0.3169 - accuracy: 0.8834" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1351/1875 [====================>.........] - ETA: 0s - loss: 0.3165 - accuracy: 0.8836" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1385/1875 [=====================>........] - ETA: 0s - loss: 0.3157 - accuracy: 0.8837" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1418/1875 [=====================>........] - ETA: 0s - loss: 0.3159 - accuracy: 0.8835" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1453/1875 [======================>.......] - ETA: 0s - loss: 0.3149 - accuracy: 0.8838" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1485/1875 [======================>.......] - ETA: 0s - loss: 0.3141 - accuracy: 0.8841" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1519/1875 [=======================>......] - ETA: 0s - loss: 0.3134 - accuracy: 0.8845" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1553/1875 [=======================>......] - ETA: 0s - loss: 0.3130 - accuracy: 0.8849" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1586/1875 [========================>.....] - ETA: 0s - loss: 0.3126 - accuracy: 0.8851" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1620/1875 [========================>.....] - ETA: 0s - loss: 0.3122 - accuracy: 0.8852" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1654/1875 [=========================>....] - ETA: 0s - loss: 0.3121 - accuracy: 0.8855" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1687/1875 [=========================>....] - ETA: 0s - loss: 0.3121 - accuracy: 0.8855" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1721/1875 [==========================>...] - ETA: 0s - loss: 0.3121 - accuracy: 0.8855" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1754/1875 [===========================>..] - ETA: 0s - loss: 0.3116 - accuracy: 0.8855" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1788/1875 [===========================>..] - ETA: 0s - loss: 0.3111 - accuracy: 0.8858" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1822/1875 [============================>.] - ETA: 0s - loss: 0.3112 - accuracy: 0.8857" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1855/1875 [============================>.] - ETA: 0s - loss: 0.3110 - accuracy: 0.8858" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1875/1875 [==============================] - 3s 2ms/step - loss: 0.3106 - accuracy: 0.8859\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 5/10\n", "\r", " 1/1875 [..............................] - ETA: 0s - loss: 0.3088 - 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", " 34/1875 [..............................] - ETA: 2s - loss: 0.2928 - accuracy: 0.8989" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 68/1875 [>.............................] - ETA: 2s - loss: 0.2999 - accuracy: 0.8929" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 102/1875 [>.............................] - ETA: 2s - loss: 0.3018 - accuracy: 0.8888" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 136/1875 [=>............................] - ETA: 2s - loss: 0.3012 - accuracy: 0.8890" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 170/1875 [=>............................] - ETA: 2s - loss: 0.2936 - accuracy: 0.8908" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 204/1875 [==>...........................] - ETA: 2s - loss: 0.2933 - accuracy: 0.8900" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 238/1875 [==>...........................] - ETA: 2s - loss: 0.2884 - accuracy: 0.8914" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 272/1875 [===>..........................] - ETA: 2s - loss: 0.2928 - accuracy: 0.8917" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 306/1875 [===>..........................] - ETA: 2s - loss: 0.2886 - accuracy: 0.8935" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 340/1875 [====>.........................] - ETA: 2s - loss: 0.2846 - accuracy: 0.8943" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 375/1875 [=====>........................] - ETA: 2s - loss: 0.2826 - accuracy: 0.8951" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 410/1875 [=====>........................] - ETA: 2s - loss: 0.2856 - accuracy: 0.8950" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 444/1875 [======>.......................] - ETA: 2s - loss: 0.2863 - accuracy: 0.8941" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 479/1875 [======>.......................] - ETA: 2s - loss: 0.2875 - accuracy: 0.8937" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 513/1875 [=======>......................] - ETA: 2s - loss: 0.2906 - accuracy: 0.8923" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 547/1875 [=======>......................] - ETA: 1s - loss: 0.2917 - accuracy: 0.8914" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 582/1875 [========>.....................] - ETA: 1s - loss: 0.2905 - accuracy: 0.8919" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 616/1875 [========>.....................] - ETA: 1s - loss: 0.2937 - accuracy: 0.8907" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 651/1875 [=========>....................] - ETA: 1s - loss: 0.2948 - accuracy: 0.8907" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 685/1875 [=========>....................] - ETA: 1s - loss: 0.2965 - accuracy: 0.8896" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 719/1875 [==========>...................] - ETA: 1s - loss: 0.2952 - accuracy: 0.8895" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 754/1875 [===========>..................] - ETA: 1s - loss: 0.2949 - accuracy: 0.8896" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 789/1875 [===========>..................] - ETA: 1s - loss: 0.2950 - accuracy: 0.8898" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 824/1875 [============>.................] - ETA: 1s - loss: 0.2941 - accuracy: 0.8904" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 858/1875 [============>.................] - ETA: 1s - loss: 0.2939 - accuracy: 0.8903" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 894/1875 [=============>................] - ETA: 1s - loss: 0.2930 - accuracy: 0.8908" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 928/1875 [=============>................] - ETA: 1s - loss: 0.2935 - accuracy: 0.8909" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 962/1875 [==============>...............] - ETA: 1s - loss: 0.2928 - accuracy: 0.8913" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 996/1875 [==============>...............] - ETA: 1s - loss: 0.2909 - accuracy: 0.8920" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1030/1875 [===============>..............] - ETA: 1s - loss: 0.2912 - accuracy: 0.8917" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1064/1875 [================>.............] - ETA: 1s - loss: 0.2922 - accuracy: 0.8911" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1098/1875 [================>.............] - ETA: 1s - loss: 0.2926 - accuracy: 0.8909" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1132/1875 [=================>............] - ETA: 1s - loss: 0.2921 - accuracy: 0.8911" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1165/1875 [=================>............] - ETA: 1s - loss: 0.2926 - accuracy: 0.8909" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1199/1875 [==================>...........] - ETA: 1s - loss: 0.2926 - accuracy: 0.8909" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1233/1875 [==================>...........] - ETA: 0s - loss: 0.2927 - accuracy: 0.8908" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1267/1875 [===================>..........] - ETA: 0s - loss: 0.2933 - accuracy: 0.8907" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1302/1875 [===================>..........] - ETA: 0s - loss: 0.2948 - accuracy: 0.8902" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1336/1875 [====================>.........] - ETA: 0s - loss: 0.2945 - accuracy: 0.8904" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1370/1875 [====================>.........] - ETA: 0s - loss: 0.2935 - accuracy: 0.8910" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1404/1875 [=====================>........] - ETA: 0s - loss: 0.2928 - accuracy: 0.8913" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1439/1875 [======================>.......] - ETA: 0s - loss: 0.2928 - accuracy: 0.8913" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1473/1875 [======================>.......] - ETA: 0s - loss: 0.2937 - accuracy: 0.8910" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1507/1875 [=======================>......] - ETA: 0s - loss: 0.2937 - accuracy: 0.8908" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1541/1875 [=======================>......] - ETA: 0s - loss: 0.2939 - accuracy: 0.8905" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1575/1875 [========================>.....] - ETA: 0s - loss: 0.2939 - accuracy: 0.8907" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1609/1875 [========================>.....] - ETA: 0s - loss: 0.2945 - accuracy: 0.8906" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1643/1875 [=========================>....] - ETA: 0s - loss: 0.2943 - accuracy: 0.8908" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1677/1875 [=========================>....] - ETA: 0s - loss: 0.2943 - accuracy: 0.8907" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1711/1875 [==========================>...] - ETA: 0s - loss: 0.2938 - accuracy: 0.8911" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1745/1875 [==========================>...] - ETA: 0s - loss: 0.2941 - accuracy: 0.8912" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1779/1875 [===========================>..] - ETA: 0s - loss: 0.2941 - accuracy: 0.8911" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1812/1875 [===========================>..] - ETA: 0s - loss: 0.2937 - accuracy: 0.8912" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1846/1875 [============================>.] - ETA: 0s - loss: 0.2942 - accuracy: 0.8911" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1875/1875 [==============================] - 3s 1ms/step - loss: 0.2940 - accuracy: 0.8912\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 6/10\n", "\r", " 1/1875 [..............................] - ETA: 0s - loss: 0.3256 - 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", " 36/1875 [..............................] - ETA: 2s - loss: 0.2717 - accuracy: 0.9123" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 69/1875 [>.............................] - ETA: 2s - loss: 0.2880 - accuracy: 0.8995" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 102/1875 [>.............................] - ETA: 2s - loss: 0.2856 - accuracy: 0.8968" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 136/1875 [=>............................] - ETA: 2s - loss: 0.2884 - accuracy: 0.8989" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 169/1875 [=>............................] - ETA: 2s - loss: 0.2848 - accuracy: 0.8987" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 203/1875 [==>...........................] - ETA: 2s - loss: 0.2863 - accuracy: 0.8987" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 237/1875 [==>...........................] - ETA: 2s - loss: 0.2858 - accuracy: 0.8981" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 271/1875 [===>..........................] - ETA: 2s - loss: 0.2864 - accuracy: 0.8979" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 305/1875 [===>..........................] - ETA: 2s - loss: 0.2854 - accuracy: 0.8986" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 339/1875 [====>.........................] - ETA: 2s - loss: 0.2857 - accuracy: 0.8986" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 373/1875 [====>.........................] - ETA: 2s - loss: 0.2861 - accuracy: 0.8983" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 407/1875 [=====>........................] - ETA: 2s - loss: 0.2873 - accuracy: 0.8970" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 441/1875 [======>.......................] - ETA: 2s - loss: 0.2856 - accuracy: 0.8971" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 475/1875 [======>.......................] - ETA: 2s - loss: 0.2851 - accuracy: 0.8963" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 509/1875 [=======>......................] - ETA: 2s - loss: 0.2849 - accuracy: 0.8969" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 543/1875 [=======>......................] - ETA: 1s - loss: 0.2863 - accuracy: 0.8959" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 577/1875 [========>.....................] - ETA: 1s - loss: 0.2858 - accuracy: 0.8959" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 610/1875 [========>.....................] - ETA: 1s - loss: 0.2865 - accuracy: 0.8950" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 644/1875 [=========>....................] - ETA: 1s - loss: 0.2850 - accuracy: 0.8952" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 678/1875 [=========>....................] - ETA: 1s - loss: 0.2836 - accuracy: 0.8958" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 712/1875 [==========>...................] - ETA: 1s - loss: 0.2833 - accuracy: 0.8955" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 746/1875 [==========>...................] - ETA: 1s - loss: 0.2837 - accuracy: 0.8952" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 780/1875 [===========>..................] - ETA: 1s - loss: 0.2839 - accuracy: 0.8954" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 814/1875 [============>.................] - ETA: 1s - loss: 0.2846 - accuracy: 0.8953" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 848/1875 [============>.................] - ETA: 1s - loss: 0.2843 - accuracy: 0.8952" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 882/1875 [=============>................] - ETA: 1s - loss: 0.2832 - accuracy: 0.8955" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 916/1875 [=============>................] - ETA: 1s - loss: 0.2825 - accuracy: 0.8958" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 950/1875 [==============>...............] - ETA: 1s - loss: 0.2826 - accuracy: 0.8958" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 984/1875 [==============>...............] - ETA: 1s - loss: 0.2820 - accuracy: 0.8960" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1018/1875 [===============>..............] - ETA: 1s - loss: 0.2812 - accuracy: 0.8962" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1052/1875 [===============>..............] - ETA: 1s - loss: 0.2814 - accuracy: 0.8956" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1085/1875 [================>.............] - ETA: 1s - loss: 0.2809 - accuracy: 0.8960" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1118/1875 [================>.............] - ETA: 1s - loss: 0.2811 - accuracy: 0.8960" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1152/1875 [=================>............] - ETA: 1s - loss: 0.2812 - accuracy: 0.8960" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1186/1875 [=================>............] - ETA: 1s - loss: 0.2811 - accuracy: 0.8958" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1220/1875 [==================>...........] - ETA: 0s - loss: 0.2802 - accuracy: 0.8962" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1254/1875 [===================>..........] - ETA: 0s - loss: 0.2802 - accuracy: 0.8962" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1288/1875 [===================>..........] - ETA: 0s - loss: 0.2811 - accuracy: 0.8961" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1322/1875 [====================>.........] - ETA: 0s - loss: 0.2810 - accuracy: 0.8961" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1356/1875 [====================>.........] - ETA: 0s - loss: 0.2807 - accuracy: 0.8964" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1391/1875 [=====================>........] - ETA: 0s - loss: 0.2803 - accuracy: 0.8963" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1425/1875 [=====================>........] - ETA: 0s - loss: 0.2798 - accuracy: 0.8963" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1459/1875 [======================>.......] - ETA: 0s - loss: 0.2806 - accuracy: 0.8962" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1494/1875 [======================>.......] - ETA: 0s - loss: 0.2806 - accuracy: 0.8963" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1528/1875 [=======================>......] - ETA: 0s - loss: 0.2801 - accuracy: 0.8965" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1562/1875 [=======================>......] - ETA: 0s - loss: 0.2799 - accuracy: 0.8966" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1596/1875 [========================>.....] - ETA: 0s - loss: 0.2794 - accuracy: 0.8969" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1631/1875 [=========================>....] - ETA: 0s - loss: 0.2796 - accuracy: 0.8967" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1665/1875 [=========================>....] - ETA: 0s - loss: 0.2794 - accuracy: 0.8967" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1699/1875 [==========================>...] - ETA: 0s - loss: 0.2791 - accuracy: 0.8969" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1733/1875 [==========================>...] - ETA: 0s - loss: 0.2800 - accuracy: 0.8964" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1766/1875 [===========================>..] - ETA: 0s - loss: 0.2789 - accuracy: 0.8968" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1798/1875 [===========================>..] - ETA: 0s - loss: 0.2793 - accuracy: 0.8967" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1830/1875 [============================>.] - ETA: 0s - loss: 0.2796 - accuracy: 0.8966" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1861/1875 [============================>.] - ETA: 0s - loss: 0.2800 - accuracy: 0.8965" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1875/1875 [==============================] - 3s 2ms/step - loss: 0.2797 - accuracy: 0.8967\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 7/10\n", "\r", " 1/1875 [..............................] - ETA: 0s - loss: 0.2288 - 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", " 34/1875 [..............................] - ETA: 2s - loss: 0.2903 - accuracy: 0.8934" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 67/1875 [>.............................] - ETA: 2s - loss: 0.2679 - accuracy: 0.9021" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 99/1875 [>.............................] - ETA: 2s - loss: 0.2719 - accuracy: 0.9028" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 131/1875 [=>............................] - ETA: 2s - loss: 0.2639 - accuracy: 0.9043" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 164/1875 [=>............................] - ETA: 2s - loss: 0.2693 - accuracy: 0.9028" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 197/1875 [==>...........................] - ETA: 2s - loss: 0.2694 - accuracy: 0.9024" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 230/1875 [==>...........................] - ETA: 2s - loss: 0.2687 - accuracy: 0.9030" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 264/1875 [===>..........................] - ETA: 2s - loss: 0.2654 - accuracy: 0.9045" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 297/1875 [===>..........................] - ETA: 2s - loss: 0.2657 - accuracy: 0.9028" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 331/1875 [====>.........................] - ETA: 2s - loss: 0.2668 - accuracy: 0.9023" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 364/1875 [====>.........................] - ETA: 2s - loss: 0.2654 - accuracy: 0.9027" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 398/1875 [=====>........................] - ETA: 2s - loss: 0.2688 - accuracy: 0.9009" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 432/1875 [=====>........................] - ETA: 2s - loss: 0.2675 - accuracy: 0.9013" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 466/1875 [======>.......................] - ETA: 2s - loss: 0.2668 - accuracy: 0.9012" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 500/1875 [=======>......................] - ETA: 2s - loss: 0.2668 - accuracy: 0.9006" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 534/1875 [=======>......................] - ETA: 2s - loss: 0.2649 - accuracy: 0.9012" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 568/1875 [========>.....................] - ETA: 1s - loss: 0.2653 - accuracy: 0.9011" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 602/1875 [========>.....................] - ETA: 1s - loss: 0.2667 - accuracy: 0.9011" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 635/1875 [=========>....................] - ETA: 1s - loss: 0.2654 - accuracy: 0.9013" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 668/1875 [=========>....................] - ETA: 1s - loss: 0.2659 - accuracy: 0.9014" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 701/1875 [==========>...................] - ETA: 1s - loss: 0.2645 - accuracy: 0.9024" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 734/1875 [==========>...................] - ETA: 1s - loss: 0.2649 - accuracy: 0.9021" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 768/1875 [===========>..................] - ETA: 1s - loss: 0.2655 - accuracy: 0.9023" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 801/1875 [===========>..................] - ETA: 1s - loss: 0.2656 - accuracy: 0.9022" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 835/1875 [============>.................] - ETA: 1s - loss: 0.2644 - accuracy: 0.9023" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 869/1875 [============>.................] - ETA: 1s - loss: 0.2631 - accuracy: 0.9028" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 903/1875 [=============>................] - ETA: 1s - loss: 0.2635 - accuracy: 0.9025" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 937/1875 [=============>................] - ETA: 1s - loss: 0.2637 - accuracy: 0.9021" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 971/1875 [==============>...............] - ETA: 1s - loss: 0.2634 - accuracy: 0.9024" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1006/1875 [===============>..............] - ETA: 1s - loss: 0.2628 - accuracy: 0.9025" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1040/1875 [===============>..............] - ETA: 1s - loss: 0.2620 - accuracy: 0.9030" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1074/1875 [================>.............] - ETA: 1s - loss: 0.2615 - accuracy: 0.9031" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1108/1875 [================>.............] - ETA: 1s - loss: 0.2621 - accuracy: 0.9031" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1142/1875 [=================>............] - ETA: 1s - loss: 0.2629 - accuracy: 0.9027" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1176/1875 [=================>............] - ETA: 1s - loss: 0.2629 - accuracy: 0.9029" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1210/1875 [==================>...........] - ETA: 1s - loss: 0.2643 - accuracy: 0.9023" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1244/1875 [==================>...........] - ETA: 0s - loss: 0.2645 - accuracy: 0.9023" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1278/1875 [===================>..........] - ETA: 0s - loss: 0.2646 - accuracy: 0.9021" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1311/1875 [===================>..........] - ETA: 0s - loss: 0.2650 - accuracy: 0.9021" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1345/1875 [====================>.........] - ETA: 0s - loss: 0.2657 - accuracy: 0.9019" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1378/1875 [=====================>........] - ETA: 0s - loss: 0.2664 - accuracy: 0.9018" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1412/1875 [=====================>........] - ETA: 0s - loss: 0.2664 - accuracy: 0.9017" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1446/1875 [======================>.......] - ETA: 0s - loss: 0.2665 - accuracy: 0.9014" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1480/1875 [======================>.......] - ETA: 0s - loss: 0.2658 - accuracy: 0.9016" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1513/1875 [=======================>......] - ETA: 0s - loss: 0.2661 - accuracy: 0.9017" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1546/1875 [=======================>......] - ETA: 0s - loss: 0.2668 - accuracy: 0.9013" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1580/1875 [========================>.....] - ETA: 0s - loss: 0.2666 - accuracy: 0.9015" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1614/1875 [========================>.....] - ETA: 0s - loss: 0.2668 - accuracy: 0.9015" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1648/1875 [=========================>....] - ETA: 0s - loss: 0.2667 - accuracy: 0.9015" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1682/1875 [=========================>....] - ETA: 0s - loss: 0.2668 - accuracy: 0.9015" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1716/1875 [==========================>...] - ETA: 0s - loss: 0.2671 - accuracy: 0.9013" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1751/1875 [===========================>..] - ETA: 0s - loss: 0.2683 - accuracy: 0.9010" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1786/1875 [===========================>..] - ETA: 0s - loss: 0.2690 - accuracy: 0.9009" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1819/1875 [============================>.] - ETA: 0s - loss: 0.2694 - accuracy: 0.9007" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1853/1875 [============================>.] - ETA: 0s - loss: 0.2689 - accuracy: 0.9009" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1875/1875 [==============================] - 3s 2ms/step - loss: 0.2685 - accuracy: 0.9010\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 8/10\n", "\r", " 1/1875 [..............................] - ETA: 0s - loss: 0.2126 - 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", " 34/1875 [..............................] - ETA: 2s - loss: 0.2296 - accuracy: 0.9182" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 68/1875 [>.............................] - ETA: 2s - loss: 0.2486 - accuracy: 0.9099" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 102/1875 [>.............................] - ETA: 2s - loss: 0.2420 - accuracy: 0.9081" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 136/1875 [=>............................] - ETA: 2s - loss: 0.2409 - accuracy: 0.9072" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 170/1875 [=>............................] - ETA: 2s - loss: 0.2419 - accuracy: 0.9064" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 203/1875 [==>...........................] - ETA: 2s - loss: 0.2445 - accuracy: 0.9047" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 237/1875 [==>...........................] - ETA: 2s - loss: 0.2433 - accuracy: 0.9057" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 270/1875 [===>..........................] - ETA: 2s - loss: 0.2429 - accuracy: 0.9065" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 304/1875 [===>..........................] - ETA: 2s - loss: 0.2438 - accuracy: 0.9066" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 338/1875 [====>.........................] - ETA: 2s - loss: 0.2419 - accuracy: 0.9075" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 371/1875 [====>.........................] - ETA: 2s - loss: 0.2427 - accuracy: 0.9071" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 404/1875 [=====>........................] - ETA: 2s - loss: 0.2433 - accuracy: 0.9066" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 438/1875 [======>.......................] - ETA: 2s - loss: 0.2453 - accuracy: 0.9063" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 472/1875 [======>.......................] - ETA: 2s - loss: 0.2435 - accuracy: 0.9068" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 505/1875 [=======>......................] - ETA: 2s - loss: 0.2465 - accuracy: 0.9059" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 538/1875 [=======>......................] - ETA: 2s - loss: 0.2467 - accuracy: 0.9059" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 572/1875 [========>.....................] - ETA: 1s - loss: 0.2478 - accuracy: 0.9057" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 606/1875 [========>.....................] - ETA: 1s - loss: 0.2486 - accuracy: 0.9058" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 640/1875 [=========>....................] - ETA: 1s - loss: 0.2489 - accuracy: 0.9056" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 674/1875 [=========>....................] - ETA: 1s - loss: 0.2480 - accuracy: 0.9057" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 709/1875 [==========>...................] - ETA: 1s - loss: 0.2488 - accuracy: 0.9051" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 744/1875 [==========>...................] - ETA: 1s - loss: 0.2504 - accuracy: 0.9047" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 778/1875 [===========>..................] - ETA: 1s - loss: 0.2517 - accuracy: 0.9038" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 811/1875 [===========>..................] - ETA: 1s - loss: 0.2529 - accuracy: 0.9035" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 845/1875 [============>.................] - ETA: 1s - loss: 0.2548 - accuracy: 0.9025" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 878/1875 [=============>................] - ETA: 1s - loss: 0.2564 - accuracy: 0.9021" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 913/1875 [=============>................] - ETA: 1s - loss: 0.2570 - accuracy: 0.9019" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 946/1875 [==============>...............] - ETA: 1s - loss: 0.2562 - accuracy: 0.9020" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 980/1875 [==============>...............] - ETA: 1s - loss: 0.2557 - accuracy: 0.9020" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1013/1875 [===============>..............] - ETA: 1s - loss: 0.2559 - accuracy: 0.9020" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1047/1875 [===============>..............] - ETA: 1s - loss: 0.2558 - accuracy: 0.9023" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1081/1875 [================>.............] - ETA: 1s - loss: 0.2556 - accuracy: 0.9024" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1115/1875 [================>.............] - ETA: 1s - loss: 0.2553 - accuracy: 0.9025" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1150/1875 [=================>............] - ETA: 1s - loss: 0.2555 - accuracy: 0.9027" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1184/1875 [=================>............] - ETA: 1s - loss: 0.2553 - accuracy: 0.9028" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1218/1875 [==================>...........] - ETA: 0s - loss: 0.2563 - accuracy: 0.9027" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1252/1875 [===================>..........] - ETA: 0s - loss: 0.2568 - accuracy: 0.9024" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1286/1875 [===================>..........] - ETA: 0s - loss: 0.2568 - accuracy: 0.9025" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1320/1875 [====================>.........] - ETA: 0s - loss: 0.2574 - accuracy: 0.9022" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1354/1875 [====================>.........] - ETA: 0s - loss: 0.2582 - accuracy: 0.9020" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1388/1875 [=====================>........] - ETA: 0s - loss: 0.2585 - accuracy: 0.9019" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1422/1875 [=====================>........] - ETA: 0s - loss: 0.2583 - accuracy: 0.9020" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1456/1875 [======================>.......] - ETA: 0s - loss: 0.2586 - accuracy: 0.9021" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1490/1875 [======================>.......] - ETA: 0s - loss: 0.2591 - accuracy: 0.9020" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1524/1875 [=======================>......] - ETA: 0s - loss: 0.2594 - accuracy: 0.9020" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1559/1875 [=======================>......] - ETA: 0s - loss: 0.2587 - accuracy: 0.9023" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1593/1875 [========================>.....] - ETA: 0s - loss: 0.2589 - accuracy: 0.9024" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1627/1875 [=========================>....] - ETA: 0s - loss: 0.2584 - accuracy: 0.9025" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1660/1875 [=========================>....] - ETA: 0s - loss: 0.2592 - accuracy: 0.9024" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1694/1875 [==========================>...] - ETA: 0s - loss: 0.2589 - accuracy: 0.9024" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1728/1875 [==========================>...] - ETA: 0s - loss: 0.2590 - accuracy: 0.9026" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1762/1875 [===========================>..] - ETA: 0s - loss: 0.2584 - accuracy: 0.9028" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1796/1875 [===========================>..] - ETA: 0s - loss: 0.2584 - accuracy: 0.9029" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1830/1875 [============================>.] - ETA: 0s - loss: 0.2584 - accuracy: 0.9029" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1864/1875 [============================>.] - ETA: 0s - loss: 0.2583 - accuracy: 0.9030" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1875/1875 [==============================] - 3s 1ms/step - loss: 0.2586 - accuracy: 0.9030\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 9/10\n", "\r", " 1/1875 [..............................] - ETA: 0s - loss: 0.3450 - 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", " 34/1875 [..............................] - ETA: 2s - loss: 0.2340 - accuracy: 0.9044" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 68/1875 [>.............................] - ETA: 2s - loss: 0.2444 - accuracy: 0.9026" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 102/1875 [>.............................] - ETA: 2s - loss: 0.2403 - accuracy: 0.9035" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 135/1875 [=>............................] - ETA: 2s - loss: 0.2471 - accuracy: 0.9028" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 169/1875 [=>............................] - ETA: 2s - loss: 0.2429 - accuracy: 0.9050" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 202/1875 [==>...........................] - ETA: 2s - loss: 0.2443 - accuracy: 0.9050" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 236/1875 [==>...........................] - ETA: 2s - loss: 0.2478 - accuracy: 0.9032" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 270/1875 [===>..........................] - ETA: 2s - loss: 0.2488 - accuracy: 0.9016" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 304/1875 [===>..........................] - ETA: 2s - loss: 0.2432 - accuracy: 0.9052" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 339/1875 [====>.........................] - ETA: 2s - loss: 0.2378 - accuracy: 0.9074" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 374/1875 [====>.........................] - ETA: 2s - loss: 0.2377 - accuracy: 0.9080" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 408/1875 [=====>........................] - ETA: 2s - loss: 0.2398 - accuracy: 0.9076" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 442/1875 [======>.......................] - ETA: 2s - loss: 0.2391 - accuracy: 0.9085" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 476/1875 [======>.......................] - ETA: 2s - loss: 0.2388 - accuracy: 0.9092" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 511/1875 [=======>......................] - ETA: 2s - loss: 0.2392 - accuracy: 0.9100" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 546/1875 [=======>......................] - ETA: 1s - loss: 0.2396 - accuracy: 0.9089" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 580/1875 [========>.....................] - ETA: 1s - loss: 0.2389 - accuracy: 0.9095" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 615/1875 [========>.....................] - ETA: 1s - loss: 0.2385 - accuracy: 0.9095" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 649/1875 [=========>....................] - ETA: 1s - loss: 0.2407 - accuracy: 0.9092" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 684/1875 [=========>....................] - ETA: 1s - loss: 0.2412 - accuracy: 0.9091" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 719/1875 [==========>...................] - ETA: 1s - loss: 0.2398 - accuracy: 0.9092" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 753/1875 [===========>..................] - ETA: 1s - loss: 0.2406 - accuracy: 0.9092" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 787/1875 [===========>..................] - ETA: 1s - loss: 0.2404 - accuracy: 0.9095" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 821/1875 [============>.................] - ETA: 1s - loss: 0.2406 - accuracy: 0.9090" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 856/1875 [============>.................] - ETA: 1s - loss: 0.2412 - accuracy: 0.9087" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 890/1875 [=============>................] - ETA: 1s - loss: 0.2419 - accuracy: 0.9086" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 925/1875 [=============>................] - ETA: 1s - loss: 0.2424 - accuracy: 0.9085" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 959/1875 [==============>...............] - ETA: 1s - loss: 0.2431 - accuracy: 0.9083" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 993/1875 [==============>...............] - ETA: 1s - loss: 0.2424 - accuracy: 0.9087" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1028/1875 [===============>..............] - ETA: 1s - loss: 0.2422 - accuracy: 0.9086" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1063/1875 [================>.............] - ETA: 1s - loss: 0.2424 - accuracy: 0.9088" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1098/1875 [================>.............] - ETA: 1s - loss: 0.2438 - accuracy: 0.9080" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1132/1875 [=================>............] - ETA: 1s - loss: 0.2443 - accuracy: 0.9079" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1166/1875 [=================>............] - ETA: 1s - loss: 0.2443 - accuracy: 0.9083" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1200/1875 [==================>...........] - ETA: 0s - loss: 0.2446 - accuracy: 0.9081" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1235/1875 [==================>...........] - ETA: 0s - loss: 0.2456 - accuracy: 0.9079" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1269/1875 [===================>..........] - ETA: 0s - loss: 0.2450 - accuracy: 0.9081" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1303/1875 [===================>..........] - ETA: 0s - loss: 0.2450 - accuracy: 0.9078" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1338/1875 [====================>.........] - ETA: 0s - loss: 0.2449 - accuracy: 0.9075" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1373/1875 [====================>.........] - ETA: 0s - loss: 0.2453 - accuracy: 0.9075" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1408/1875 [=====================>........] - ETA: 0s - loss: 0.2454 - accuracy: 0.9075" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1442/1875 [======================>.......] - ETA: 0s - loss: 0.2448 - accuracy: 0.9078" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1477/1875 [======================>.......] - ETA: 0s - loss: 0.2450 - accuracy: 0.9079" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1511/1875 [=======================>......] - ETA: 0s - loss: 0.2450 - accuracy: 0.9079" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1545/1875 [=======================>......] - ETA: 0s - loss: 0.2454 - accuracy: 0.9075" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1579/1875 [========================>.....] - ETA: 0s - loss: 0.2455 - accuracy: 0.9076" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1614/1875 [========================>.....] - ETA: 0s - loss: 0.2455 - accuracy: 0.9076" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1649/1875 [=========================>....] - ETA: 0s - loss: 0.2450 - accuracy: 0.9079" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1684/1875 [=========================>....] - ETA: 0s - loss: 0.2451 - accuracy: 0.9080" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1718/1875 [==========================>...] - ETA: 0s - loss: 0.2451 - accuracy: 0.9080" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1753/1875 [===========================>..] - ETA: 0s - loss: 0.2453 - accuracy: 0.9079" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1788/1875 [===========================>..] - ETA: 0s - loss: 0.2454 - accuracy: 0.9080" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1823/1875 [============================>.] - ETA: 0s - loss: 0.2464 - accuracy: 0.9077" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1858/1875 [============================>.] - ETA: 0s - loss: 0.2464 - accuracy: 0.9076" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1875/1875 [==============================] - 3s 1ms/step - loss: 0.2468 - accuracy: 0.9074\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 10/10\n", "\r", " 1/1875 [..............................] - ETA: 0s - loss: 0.2577 - 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", " 35/1875 [..............................] - ETA: 2s - loss: 0.2145 - accuracy: 0.9268" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 69/1875 [>.............................] - ETA: 2s - loss: 0.2391 - accuracy: 0.9126" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 103/1875 [>.............................] - ETA: 2s - loss: 0.2388 - accuracy: 0.9135" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 138/1875 [=>............................] - ETA: 2s - loss: 0.2377 - accuracy: 0.9139" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 172/1875 [=>............................] - ETA: 2s - loss: 0.2393 - accuracy: 0.9126" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 207/1875 [==>...........................] - ETA: 2s - loss: 0.2326 - accuracy: 0.9147" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 241/1875 [==>...........................] - ETA: 2s - loss: 0.2307 - accuracy: 0.9151" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 275/1875 [===>..........................] - ETA: 2s - loss: 0.2325 - accuracy: 0.9134" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 309/1875 [===>..........................] - ETA: 2s - loss: 0.2330 - accuracy: 0.9130" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 344/1875 [====>.........................] - ETA: 2s - loss: 0.2347 - accuracy: 0.9120" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 378/1875 [=====>........................] - ETA: 2s - loss: 0.2356 - accuracy: 0.9118" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 412/1875 [=====>........................] - ETA: 2s - loss: 0.2334 - accuracy: 0.9129" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 446/1875 [======>.......................] - ETA: 2s - loss: 0.2336 - accuracy: 0.9135" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 481/1875 [======>.......................] - ETA: 2s - loss: 0.2333 - accuracy: 0.9133" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 516/1875 [=======>......................] - ETA: 2s - loss: 0.2338 - accuracy: 0.9132" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 551/1875 [=======>......................] - ETA: 1s - loss: 0.2334 - accuracy: 0.9134" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 585/1875 [========>.....................] - ETA: 1s - loss: 0.2324 - accuracy: 0.9138" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 619/1875 [========>.....................] - ETA: 1s - loss: 0.2341 - accuracy: 0.9132" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 654/1875 [=========>....................] - ETA: 1s - loss: 0.2344 - accuracy: 0.9129" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 689/1875 [==========>...................] - ETA: 1s - loss: 0.2331 - accuracy: 0.9132" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 724/1875 [==========>...................] - ETA: 1s - loss: 0.2324 - accuracy: 0.9133" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 758/1875 [===========>..................] - ETA: 1s - loss: 0.2322 - accuracy: 0.9133" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 793/1875 [===========>..................] - ETA: 1s - loss: 0.2324 - accuracy: 0.9131" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 828/1875 [============>.................] - ETA: 1s - loss: 0.2341 - accuracy: 0.9122" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 862/1875 [============>.................] - ETA: 1s - loss: 0.2332 - accuracy: 0.9125" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 896/1875 [=============>................] - ETA: 1s - loss: 0.2343 - accuracy: 0.9119" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 929/1875 [=============>................] - ETA: 1s - loss: 0.2356 - accuracy: 0.9116" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 964/1875 [==============>...............] - ETA: 1s - loss: 0.2367 - accuracy: 0.9110" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", " 999/1875 [==============>...............] - ETA: 1s - loss: 0.2369 - accuracy: 0.9110" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1033/1875 [===============>..............] - ETA: 1s - loss: 0.2358 - accuracy: 0.9112" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1067/1875 [================>.............] - ETA: 1s - loss: 0.2374 - accuracy: 0.9108" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1102/1875 [================>.............] - ETA: 1s - loss: 0.2363 - accuracy: 0.9113" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1137/1875 [=================>............] - ETA: 1s - loss: 0.2363 - accuracy: 0.9111" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1171/1875 [=================>............] - ETA: 1s - loss: 0.2377 - accuracy: 0.9107" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1205/1875 [==================>...........] - ETA: 0s - loss: 0.2373 - accuracy: 0.9107" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1239/1875 [==================>...........] - ETA: 0s - loss: 0.2385 - accuracy: 0.9103" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1273/1875 [===================>..........] - ETA: 0s - loss: 0.2386 - accuracy: 0.9101" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1308/1875 [===================>..........] - ETA: 0s - loss: 0.2377 - accuracy: 0.9105" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1343/1875 [====================>.........] - ETA: 0s - loss: 0.2367 - accuracy: 0.9110" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1378/1875 [=====================>........] - ETA: 0s - loss: 0.2366 - accuracy: 0.9111" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1413/1875 [=====================>........] - ETA: 0s - loss: 0.2369 - accuracy: 0.9110" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1447/1875 [======================>.......] - ETA: 0s - loss: 0.2368 - accuracy: 0.9110" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1482/1875 [======================>.......] - ETA: 0s - loss: 0.2373 - accuracy: 0.9109" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1517/1875 [=======================>......] - ETA: 0s - loss: 0.2374 - accuracy: 0.9109" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1552/1875 [=======================>......] - ETA: 0s - loss: 0.2375 - accuracy: 0.9107" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1586/1875 [========================>.....] - ETA: 0s - loss: 0.2378 - accuracy: 0.9107" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1620/1875 [========================>.....] - ETA: 0s - loss: 0.2379 - accuracy: 0.9106" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1655/1875 [=========================>....] - ETA: 0s - loss: 0.2375 - accuracy: 0.9107" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1690/1875 [==========================>...] - ETA: 0s - loss: 0.2380 - accuracy: 0.9104" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1724/1875 [==========================>...] - ETA: 0s - loss: 0.2383 - accuracy: 0.9104" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1759/1875 [===========================>..] - ETA: 0s - loss: 0.2380 - accuracy: 0.9107" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1794/1875 [===========================>..] - ETA: 0s - loss: 0.2381 - accuracy: 0.9108" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1828/1875 [============================>.] - ETA: 0s - loss: 0.2388 - accuracy: 0.9106" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1863/1875 [============================>.] - ETA: 0s - loss: 0.2386 - accuracy: 0.9106" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1875/1875 [==============================] - 3s 1ms/step - loss: 0.2386 - accuracy: 0.9106\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model.fit(train_images, train_labels, epochs=10)" ] }, { "cell_type": "markdown", "metadata": { "id": "W3ZVOhugCaXA" }, "source": [ "A medida que el modelo entrena, la perdida y la exactitud son desplegadas. Este modelo alcanza una exactitud de 0.88 (o 88%) sobre el set de datos de entrenamiento." ] }, { "cell_type": "markdown", "metadata": { "id": "oEw4bZgGCaXB" }, "source": [ "## Evaluar Exactitud\n", "\n", "Siguente, compare como el rendimiento del modelo sobre el set de datos:" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:36.459549Z", "iopub.status.busy": "2020-09-23T00:12:36.458790Z", "iopub.status.idle": "2020-09-23T00:12:37.082116Z", "shell.execute_reply": "2020-09-23T00:12:37.082547Z" }, "id": "VflXLEeECaXC" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "313/313 - 0s - loss: 0.3350 - accuracy: 0.8840\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "Test accuracy: 0.8840000033378601\n" ] } ], "source": [ "test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)\n", "\n", "print('\\nTest accuracy:', test_acc)" ] }, { "cell_type": "markdown", "metadata": { "id": "yWfgsmVXCaXG" }, "source": [ "Resulta que la exactitud sobre el set de datos es un poco menor que la exactitud sobre el set de entrenamiento. Esta diferencia entre el entrenamiento y el test se debe a *overfitting* (sobre ajuste). Sobre ajuste sucede cuando un modelo de aprendizaje de maquina (ML) tiene un rendimiento peor sobre un set de datos nuevo, que nunca antes ha visto comparado con el de entrenamiento." ] }, { "cell_type": "markdown", "metadata": { "id": "xsoS7CPDCaXH" }, "source": [ "## Hacer predicciones\n", "\n", "Con el modelo entrenado usted puede usarlo para hacer predicciones sobre imagenes." ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:37.087029Z", "iopub.status.busy": "2020-09-23T00:12:37.086398Z", "iopub.status.idle": "2020-09-23T00:12:37.407345Z", "shell.execute_reply": "2020-09-23T00:12:37.406539Z" }, "id": "Gl91RPhdCaXI" }, "outputs": [], "source": [ "predictions = model.predict(test_images)" ] }, { "cell_type": "markdown", "metadata": { "id": "x9Kk1voUCaXJ" }, "source": [ "Aca, el modelo ha predecido la etiqueta para cada imagen en el set de datos de *test* (prueba). Miremos la primera prediccion:" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:37.412550Z", "iopub.status.busy": "2020-09-23T00:12:37.411807Z", "iopub.status.idle": "2020-09-23T00:12:37.414437Z", "shell.execute_reply": "2020-09-23T00:12:37.414875Z" }, "id": "3DmJEUinCaXK" }, "outputs": [ { "data": { "text/plain": [ "array([8.98017061e-06, 1.05824974e-07, 1.47653412e-09, 6.39178294e-11,\n", " 6.63487398e-08, 1.56312122e-03, 3.97483973e-07, 6.77545443e-02,\n", " 8.32966691e-08, 9.30672705e-01], dtype=float32)" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predictions[0]" ] }, { "cell_type": "markdown", "metadata": { "id": "-hw1hgeSCaXN" }, "source": [ "*una* prediccion es un arreglo de 10 numeros. Estos representan el nivel de \"confianza\" del modelo sobre las imagenes de cada uno de los 10 articulos de moda/ropa. Ustedes pueden revisar cual tiene el nivel mas alto de confianza:" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:37.419598Z", "iopub.status.busy": "2020-09-23T00:12:37.418897Z", "iopub.status.idle": "2020-09-23T00:12:37.421942Z", "shell.execute_reply": "2020-09-23T00:12:37.421420Z" }, "id": "qsqenuPnCaXO" }, "outputs": [ { "data": { "text/plain": [ "9" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.argmax(predictions[0])" ] }, { "cell_type": "markdown", "metadata": { "id": "E51yS7iCCaXO" }, "source": [ "Entonces,el modelo tiene mayor confianza que esta imagen es un bota de tobillo \"ankle boot\" o `class_names[9]`. Examinando las etiquetas de *test* o de pruebas muestra que esta clasificaion es correcta:" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:37.426275Z", "iopub.status.busy": "2020-09-23T00:12:37.425639Z", "iopub.status.idle": "2020-09-23T00:12:37.428526Z", "shell.execute_reply": "2020-09-23T00:12:37.428018Z" }, "id": "Sd7Pgsu6CaXP" }, "outputs": [ { "data": { "text/plain": [ "9" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_labels[0]" ] }, { "cell_type": "markdown", "metadata": { "id": "ygh2yYC972ne" }, "source": [ "**Grafique** esto para poder ver todo el set de la prediccion de las 10 clases." ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:37.436576Z", "iopub.status.busy": "2020-09-23T00:12:37.435927Z", "iopub.status.idle": "2020-09-23T00:12:37.437739Z", "shell.execute_reply": "2020-09-23T00:12:37.438165Z" }, "id": "DvYmmrpIy6Y1" }, "outputs": [], "source": [ "def plot_image(i, predictions_array, true_label, img):\n", " predictions_array, true_label, img = predictions_array, true_label[i], img[i]\n", " plt.grid(False)\n", " plt.xticks([])\n", " plt.yticks([])\n", "\n", " plt.imshow(img, cmap=plt.cm.binary)\n", "\n", " predicted_label = np.argmax(predictions_array)\n", " if predicted_label == true_label:\n", " color = 'blue'\n", " else:\n", " color = 'red'\n", "\n", " plt.xlabel(\"{} {:2.0f}% ({})\".format(class_names[predicted_label],\n", " 100*np.max(predictions_array),\n", " class_names[true_label]),\n", " color=color)\n", "\n", "def plot_value_array(i, predictions_array, true_label):\n", " predictions_array, true_label = predictions_array, true_label[i]\n", " plt.grid(False)\n", " plt.xticks(range(10))\n", " plt.yticks([])\n", " thisplot = plt.bar(range(10), predictions_array, color=\"#777777\")\n", " plt.ylim([0, 1])\n", " predicted_label = np.argmax(predictions_array)\n", "\n", " thisplot[predicted_label].set_color('red')\n", " thisplot[true_label].set_color('blue')" ] }, { "cell_type": "markdown", "metadata": { "id": "d4Ov9OFDMmOD" }, "source": [ "Miremos la imagen [0], sus predicciones y el arreglo de predicciones. Las etiquetas de prediccion correctas estan en azul y las incorrectas estan en rojo. El numero entrega el porcentaje (sobre 100) para la etiqueta predecida." ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:37.447943Z", "iopub.status.busy": "2020-09-23T00:12:37.443377Z", "iopub.status.idle": "2020-09-23T00:12:37.559790Z", "shell.execute_reply": "2020-09-23T00:12:37.560326Z" }, "id": "HV5jw-5HwSmO" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "i = 0\n", "plt.figure(figsize=(6,3))\n", "plt.subplot(1,2,1)\n", "plot_image(i, predictions[i], test_labels, test_images)\n", "plt.subplot(1,2,2)\n", "plot_value_array(i, predictions[i], test_labels)\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:37.574455Z", "iopub.status.busy": "2020-09-23T00:12:37.572922Z", "iopub.status.idle": "2020-09-23T00:12:37.679858Z", "shell.execute_reply": "2020-09-23T00:12:37.679297Z" }, "id": "Ko-uzOufSCSe" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "i = 12\n", "plt.figure(figsize=(6,3))\n", "plt.subplot(1,2,1)\n", "plot_image(i, predictions[i], test_labels, test_images)\n", "plt.subplot(1,2,2)\n", "plot_value_array(i, predictions[i], test_labels)\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": { "id": "kgdvGD52CaXR" }, "source": [ "Vamos a graficar multiples imagenes con sus predicciones. Notese que el modelo puede estar equivocado aun cuando tiene mucha confianza." ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:37.704262Z", "iopub.status.busy": "2020-09-23T00:12:37.703472Z", "iopub.status.idle": "2020-09-23T00:12:39.542467Z", "shell.execute_reply": "2020-09-23T00:12:39.543014Z" }, "id": "hQlnbqaw2Qu_" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Plot the first X test images, their predicted labels, and the true labels.\n", "# Color correct predictions in blue and incorrect predictions in red.\n", "num_rows = 5\n", "num_cols = 3\n", "num_images = num_rows*num_cols\n", "plt.figure(figsize=(2*2*num_cols, 2*num_rows))\n", "for i in range(num_images):\n", " plt.subplot(num_rows, 2*num_cols, 2*i+1)\n", " plot_image(i, predictions[i], test_labels, test_images)\n", " plt.subplot(num_rows, 2*num_cols, 2*i+2)\n", " plot_value_array(i, predictions[i], test_labels)\n", "plt.tight_layout()\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": { "id": "R32zteKHCaXT" }, "source": [ "Finalmente, usamos el modelo entrenado para hacer una prediccion sobre una unica imagen." ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:39.547795Z", "iopub.status.busy": "2020-09-23T00:12:39.547091Z", "iopub.status.idle": "2020-09-23T00:12:39.549226Z", "shell.execute_reply": "2020-09-23T00:12:39.549730Z" }, "id": "yRJ7JU7JCaXT" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(28, 28)\n" ] } ], "source": [ "# Grab an image from the test dataset.\n", "img = test_images[1]\n", "\n", "print(img.shape)" ] }, { "cell_type": "markdown", "metadata": { "id": "vz3bVp21CaXV" }, "source": [ "Los modelos de `tf.keras` son optimizados sobre *batch* o bloques, \n", "o coleciones de ejemplos por vez.\n", "De acuerdo a esto, aunque use una unica imagen toca agregarla a una lista:" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:39.554000Z", "iopub.status.busy": "2020-09-23T00:12:39.553363Z", "iopub.status.idle": "2020-09-23T00:12:39.556184Z", "shell.execute_reply": "2020-09-23T00:12:39.555583Z" }, "id": "lDFh5yF_CaXW" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(1, 28, 28)\n" ] } ], "source": [ "# Add the image to a batch where it's the only member.\n", "img = (np.expand_dims(img,0))\n", "\n", "print(img.shape)" ] }, { "cell_type": "markdown", "metadata": { "id": "EQ5wLTkcCaXY" }, "source": [ "Ahora prediga la etiqueta correcta para esta imagen:" ] }, { "cell_type": "code", "execution_count": 28, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:39.560100Z", "iopub.status.busy": "2020-09-23T00:12:39.559462Z", "iopub.status.idle": "2020-09-23T00:12:39.595462Z", "shell.execute_reply": "2020-09-23T00:12:39.595894Z" }, "id": "o_rzNSdrCaXY" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[2.7196244e-05 2.3026301e-14 9.9943405e-01 3.2361061e-10 3.3726924e-04\n", " 6.5815242e-11 2.0145018e-04 1.0427863e-13 4.7570725e-10 5.1079822e-15]]\n" ] } ], "source": [ "predictions_single = model.predict(img)\n", "\n", "print(predictions_single)" ] }, { "cell_type": "code", "execution_count": 29, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:39.613213Z", "iopub.status.busy": "2020-09-23T00:12:39.607790Z", "iopub.status.idle": "2020-09-23T00:12:39.693950Z", "shell.execute_reply": "2020-09-23T00:12:39.693294Z" }, "id": "6Ai-cpLjO-3A" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plot_value_array(1, predictions_single[0], test_labels)\n", "_ = plt.xticks(range(10), class_names, rotation=45)" ] }, { "cell_type": "markdown", "metadata": { "id": "cU1Y2OAMCaXb" }, "source": [ "`model.predict` retorna una lista de listas para cada imagen dentro del *batch* o bloque de datos. Tome la prediccion para nuestra unica imagen dentro del *batch* o bloque:" ] }, { "cell_type": "code", "execution_count": 30, "metadata": { "execution": { "iopub.execute_input": "2020-09-23T00:12:39.698805Z", "iopub.status.busy": "2020-09-23T00:12:39.698163Z", "iopub.status.idle": "2020-09-23T00:12:39.701361Z", "shell.execute_reply": "2020-09-23T00:12:39.700720Z" }, "id": "2tRmdq_8CaXb" }, "outputs": [ { "data": { "text/plain": [ "2" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.argmax(predictions_single[0])" ] }, { "cell_type": "markdown", "metadata": { "id": "YFc2HbEVCaXd" }, "source": [ "Y el modelo predice una etiqueta de 2." ] } ], "metadata": { "colab": { "collapsed_sections": [], "name": "classification.ipynb", "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": "3.6.9" } }, "nbformat": 4, "nbformat_minor": 0 }