{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "cellView": "form", "id": "BZSlp3DAjdYf" }, "outputs": [], "source": [ "# @title Licensed under the Apache License, Version 2.0 (the \"License\");\n", "# you may not use this file except in compliance with the License.\n", "# You may obtain a copy of the License at\n", "#\n", "# https://www.apache.org/licenses/LICENSE-2.0\n", "#\n", "# Unless required by applicable law or agreed to in writing, software\n", "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", "# See the License for the specific language governing permissions and\n", "# limitations under the License." ] }, { "cell_type": "markdown", "metadata": { "id": "3wF5wszaj97Y" }, "source": [ "# Number Classification with TensorFlow\n", "\n", "Copyright 2019 The TensorFlow Authors." ] }, { "cell_type": "markdown", "metadata": { "id": "DUNzJc4jTj6G" }, "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": "04QgGZc9bF5D" }, "source": [ "This short introduction uses [Keras](https://www.tensorflow.org/guide/keras/overview) to:\n", "\n", "1. Load a prebuilt dataset.\n", "1. Build a neural network machine learning model that classifies images.\n", "2. Train this neural network.\n", "3. Evaluate the accuracy of the model." ] }, { "cell_type": "markdown", "metadata": { "id": "hiH7AC-NTniF" }, "source": [ "This tutorial is a [Google Colaboratory](https://colab.research.google.com/notebooks/welcome.ipynb) notebook. Python programs are run directly in the browser—a great way to learn and use TensorFlow. To follow this tutorial, run the notebook in Google Colab by clicking the button at the top of this page.\n", "\n", "1. In Colab, connect to a Python runtime: At the top-right of the menu bar, select *CONNECT*.\n", "2. To run all the code in the notebook, select **Runtime** > **Run all**. To run the code cells one at a time, hover over each cell and select the **Run cell** icon." ] }, { "cell_type": "markdown", "metadata": { "id": "nnrWf3PCEzXL" }, "source": [ "## Set up TensorFlow\n", "\n", "Import TensorFlow into your program to get started:" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "id": "0trJmd6DjqBZ" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "TensorFlow version: 2.17.0\n" ] } ], "source": [ "import tensorflow as tf\n", "\n", "print(\"TensorFlow version:\", tf.__version__)" ] }, { "cell_type": "markdown", "metadata": { "id": "7NAbSZiaoJ4z" }, "source": [ "If you are following along in your own development environment, rather than [Colab](https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/quickstart/beginner.ipynb), see the [install guide](https://www.tensorflow.org/install) for setting up TensorFlow for development.\n", "\n", "Note: Make sure you have upgraded to the latest `pip` to install the TensorFlow 2 package if you are using your own development environment. See the [install guide](https://www.tensorflow.org/install) for details.\n", "\n", "## Load a dataset\n", "\n", "Load and prepare the MNIST dataset. The pixel values of the images range from 0 through 255. Scale these values to a range of 0 to 1 by dividing the values by `255.0`. This also converts the sample data from integers to floating-point numbers:" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "id": "7FP5258xjs-v" }, "outputs": [], "source": [ "mnist = tf.keras.datasets.mnist\n", "\n", "(x_train, y_train), (x_test, y_test) = mnist.load_data()\n", "x_train, x_test = x_train / 255.0, x_test / 255.0" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", "\n", "%matplotlib inline\n", "\n", "num_row = 2\n", "num_col = 5\n", "num = num_row * num_col\n", "images = x_train[:num]\n", "labels = y_train[:num]\n", "\n", "# plot images\n", "fig, axes = plt.subplots(num_row, num_col, figsize=(1.5 * num_col, 2 * num_row))\n", "for i in range(num):\n", " ax = axes[i // num_col, i % num_col]\n", " ax.imshow(images[i], cmap=\"gray\")\n", " ax.set_title(\"Label: {}\".format(labels[i]))\n", "plt.tight_layout()\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": { "id": "BPZ68wASog_I" }, "source": [ "## Build a machine learning model\n", "\n", "Build a `tf.keras.Sequential` model:" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "id": "h3IKyzTCDNGo" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/ariefrahmansyah/Library/Caches/pypoetry/virtualenvs/applied-python-training-MLD32oJZ-py3.12/lib/python3.12/site-packages/keras/src/layers/reshaping/flatten.py:37: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", " super().__init__(**kwargs)\n" ] } ], "source": [ "model = tf.keras.models.Sequential(\n", " [\n", " tf.keras.layers.Flatten(input_shape=(28, 28)),\n", " tf.keras.layers.Dense(128, activation=\"relu\"),\n", " tf.keras.layers.Dropout(0.2),\n", " tf.keras.layers.Dense(10),\n", " ]\n", ")" ] }, { "cell_type": "markdown", "metadata": { "id": "l2hiez2eIUz8" }, "source": [ "[`Sequential`](https://www.tensorflow.org/guide/keras/sequential_model) is useful for stacking layers where each layer has one input [tensor](https://www.tensorflow.org/guide/tensor) and one output tensor. Layers are functions with a known mathematical structure that can be reused and have trainable variables. Most TensorFlow models are composed of layers. This model uses the [`Flatten`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Flatten), [`Dense`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dense), and [`Dropout`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dropout) layers.\n", "\n", "For each example, the model returns a vector of [logits](https://developers.google.com/machine-learning/glossary#logits) or [log-odds](https://developers.google.com/machine-learning/glossary#log-odds) scores, one for each class." ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "id": "OeOrNdnkEEcR" }, "outputs": [ { "data": { "text/plain": [ "array([[-0.3805407 , 0.80421233, -0.31978986, -0.670506 , 0.06069487,\n", " -0.679445 , 0.40332592, 0.47335294, -0.30201632, 0.285113 ]],\n", " dtype=float32)" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predictions = model(x_train[:1]).numpy()\n", "predictions" ] }, { "cell_type": "markdown", "metadata": { "id": "tgjhDQGcIniO" }, "source": [ "The `tf.nn.softmax` function converts these logits to *probabilities* for each class: " ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "id": "zWSRnQ0WI5eq" }, "outputs": [ { "data": { "text/plain": [ "array([[0.06272263, 0.20509543, 0.06665121, 0.04693469, 0.09751029,\n", " 0.04651701, 0.13735777, 0.1473213 , 0.06784642, 0.12204331]],\n", " dtype=float32)" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tf.nn.softmax(predictions).numpy()" ] }, { "cell_type": "markdown", "metadata": { "id": "he5u_okAYS4a" }, "source": [ "Note: It is possible to bake the `tf.nn.softmax` function into the activation function for the last layer of the network. While this can make the model output more directly interpretable, this approach is discouraged as it's impossible to provide an exact and numerically stable loss calculation for all models when using a softmax output. " ] }, { "cell_type": "markdown", "metadata": { "id": "hQyugpgRIyrA" }, "source": [ "Define a loss function for training using `losses.SparseCategoricalCrossentropy`:" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "id": "RSkzdv8MD0tT" }, "outputs": [], "source": [ "loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)" ] }, { "cell_type": "markdown", "metadata": { "id": "SfR4MsSDU880" }, "source": [ "The loss function takes a vector of ground truth values and a vector of logits and returns a scalar loss for each example. This loss is equal to the negative log probability of the true class: The loss is zero if the model is sure of the correct class.\n", "\n", "This untrained model gives probabilities close to random (1/10 for each class), so the initial loss should be close to `-tf.math.log(1/10) ~= 2.3`." ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "id": "NJWqEVrrJ7ZB" }, "outputs": [ { "data": { "text/plain": [ "3.0679374" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "loss_fn(y_train[:1], predictions).numpy()" ] }, { "cell_type": "markdown", "metadata": { "id": "ada44eb947d4" }, "source": [ "Before you start training, configure and compile the model using Keras `Model.compile`. Set the [`optimizer`](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers) class to `adam`, set the `loss` to the `loss_fn` function you defined earlier, and specify a metric to be evaluated for the model by setting the `metrics` parameter to `accuracy`." ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "id": "9foNKHzTD2Vo" }, "outputs": [], "source": [ "model.compile(optimizer=\"adam\", loss=loss_fn, metrics=[\"accuracy\"])" ] }, { "cell_type": "markdown", "metadata": { "id": "ix4mEL65on-w" }, "source": [ "## Train and evaluate your model\n", "\n", "Use the `Model.fit` method to adjust your model parameters and minimize the loss: " ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "id": "y7suUbJXVLqP" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/5\n", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 995us/step - accuracy: 0.8607 - loss: 0.4769\n", "Epoch 2/5\n", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9549 - loss: 0.1528\n", "Epoch 3/5\n", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 991us/step - accuracy: 0.9666 - loss: 0.1097\n", "Epoch 4/5\n", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 985us/step - accuracy: 0.9727 - loss: 0.0898\n", "Epoch 5/5\n", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9771 - loss: 0.0764\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 314/1875\u001b[0m \u001b[32m━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.7341 - loss: 0.9244" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 356/1875\u001b[0m \u001b[32m━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.7463 - loss: 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\r", "\u001b[1m 398/1875\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.7564 - loss: 0.8490" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 438/1875\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.7648 - loss: 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\r", "\u001b[1m 480/1875\u001b[0m \u001b[32m━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.7727 - loss: 0.7937" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 523/1875\u001b[0m \u001b[32m━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.7797 - loss: 0.7697" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 564/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.7857 - loss: 0.7490" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 604/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.7911 - loss: 0.7305" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 646/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.7962 - loss: 0.7128" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 689/1875\u001b[0m \u001b[32m━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.8009 - loss: 0.6964" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 730/1875\u001b[0m \u001b[32m━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.8050 - loss: 0.6820" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 772/1875\u001b[0m \u001b[32m━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.8089 - loss: 0.6682" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 813/1875\u001b[0m \u001b[32m━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.8125 - loss: 0.6557" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 855/1875\u001b[0m \u001b[32m━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.8159 - loss: 0.6437" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 897/1875\u001b[0m \u001b[32m━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.8191 - loss: 0.6325" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 938/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.8221 - loss: 0.6222" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 978/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.8248 - loss: 0.6127" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1019/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.8274 - loss: 0.6035" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1059/1875\u001b[0m \u001b[32m━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.8298 - loss: 0.5950" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1100/1875\u001b[0m \u001b[32m━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8321 - loss: 0.5868" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1141/1875\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8344 - loss: 0.5789" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1181/1875\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8364 - loss: 0.5716" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1221/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8384 - loss: 0.5647" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1259/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8402 - loss: 0.5583" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1298/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8420 - loss: 0.5521" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1336/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8437 - loss: 0.5462" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1375/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8453 - loss: 0.5404" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1414/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8469 - loss: 0.5348" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1453/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8484 - loss: 0.5294" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1491/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8499 - loss: 0.5243" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1532/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8514 - loss: 0.5190" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1573/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8528 - loss: 0.5139" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1615/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8543 - loss: 0.5089" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1655/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8556 - loss: 0.5042" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1695/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8569 - loss: 0.4997" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1736/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8581 - loss: 0.4953" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1777/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8594 - loss: 0.4910" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1816/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8605 - loss: 0.4870" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1857/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.8616 - loss: 0.4829" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 1ms/step - accuracy: 0.8622 - loss: 0.4811\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 2/5\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "\u001b[1m 1/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1:30\u001b[0m 48ms/step - accuracy: 0.9375 - loss: 0.3879" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 42/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9523 - loss: 0.1747 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 82/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9543 - loss: 0.1602" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 122/1875\u001b[0m \u001b[32m━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9551 - loss: 0.1561" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 165/1875\u001b[0m \u001b[32m━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9552 - loss: 0.1541" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 207/1875\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9549 - loss: 0.1536" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 249/1875\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9544 - loss: 0.1538" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 292/1875\u001b[0m \u001b[32m━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9539 - loss: 0.1547" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 334/1875\u001b[0m \u001b[32m━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9536 - loss: 0.1552" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 376/1875\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9534 - loss: 0.1557" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 417/1875\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9532 - loss: 0.1562" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 458/1875\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9531 - loss: 0.1567" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 500/1875\u001b[0m \u001b[32m━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9530 - loss: 0.1570" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 542/1875\u001b[0m \u001b[32m━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9530 - loss: 0.1572" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 584/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9530 - loss: 0.1573" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 627/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9531 - loss: 0.1573" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 669/1875\u001b[0m \u001b[32m━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9531 - loss: 0.1573" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 711/1875\u001b[0m \u001b[32m━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9531 - loss: 0.1575" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 753/1875\u001b[0m \u001b[32m━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9531 - loss: 0.1576" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 796/1875\u001b[0m \u001b[32m━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9531 - loss: 0.1576" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 838/1875\u001b[0m \u001b[32m━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9532 - loss: 0.1576" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 881/1875\u001b[0m \u001b[32m━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9532 - loss: 0.1576" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 924/1875\u001b[0m \u001b[32m━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9533 - loss: 0.1576" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 967/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9534 - loss: 0.1576" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1010/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9534 - loss: 0.1575" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1052/1875\u001b[0m \u001b[32m━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9535 - loss: 0.1574" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1095/1875\u001b[0m \u001b[32m━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9535 - loss: 0.1573" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1137/1875\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9536 - loss: 0.1572" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1178/1875\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9537 - loss: 0.1570" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1220/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9537 - loss: 0.1568" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1261/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9538 - loss: 0.1566" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1304/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9539 - loss: 0.1564" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1347/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9540 - loss: 0.1562" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1389/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9540 - loss: 0.1561" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1431/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9541 - loss: 0.1559" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1473/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9542 - loss: 0.1557" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1514/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9542 - loss: 0.1555" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1556/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9543 - loss: 0.1553" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1597/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9544 - loss: 0.1551" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1638/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9544 - loss: 0.1550" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1680/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9545 - loss: 0.1548" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1723/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9545 - loss: 0.1546" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1764/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9546 - loss: 0.1544" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1806/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9546 - loss: 0.1542" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1847/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9547 - loss: 0.1541" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9547 - loss: 0.1539\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 3/5\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "\u001b[1m 1/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1:26\u001b[0m 46ms/step - accuracy: 0.9688 - loss: 0.2087" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 41/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9718 - loss: 0.1163 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 80/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9684 - loss: 0.1186" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 122/1875\u001b[0m \u001b[32m━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9669 - loss: 0.1197" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 166/1875\u001b[0m \u001b[32m━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9667 - loss: 0.1187" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 210/1875\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9669 - loss: 0.1177" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 254/1875\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9671 - loss: 0.1166" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 299/1875\u001b[0m \u001b[32m━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9674 - loss: 0.1157" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 344/1875\u001b[0m \u001b[32m━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9675 - loss: 0.1152" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 388/1875\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1145" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 431/1875\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1141" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 471/1875\u001b[0m \u001b[32m━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1138" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 514/1875\u001b[0m \u001b[32m━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9678 - loss: 0.1135" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 558/1875\u001b[0m \u001b[32m━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9678 - loss: 0.1131" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 601/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9678 - loss: 0.1129" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 644/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9678 - loss: 0.1127" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 686/1875\u001b[0m \u001b[32m━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9678 - loss: 0.1126" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 727/1875\u001b[0m \u001b[32m━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1125" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 768/1875\u001b[0m \u001b[32m━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1125" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 811/1875\u001b[0m \u001b[32m━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1125" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 853/1875\u001b[0m \u001b[32m━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1124" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 896/1875\u001b[0m \u001b[32m━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1122" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 938/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1121" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 980/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1120" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1023/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1119" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1066/1875\u001b[0m \u001b[32m━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1117" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1110/1875\u001b[0m \u001b[32m━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1116" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1154/1875\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1115" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1198/1875\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1115" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1241/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1114" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1285/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1113" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1327/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1112" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1370/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1112" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1414/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9677 - loss: 0.1111" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1458/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1111" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1501/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1110" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1543/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1110" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1585/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1109" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1628/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1109" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1670/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1109" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1713/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1108" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1756/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1108" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1799/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1107" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1843/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1107" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9676 - loss: 0.1107\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 4/5\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "\u001b[1m 1/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1:26\u001b[0m 46ms/step - accuracy: 0.9375 - loss: 0.1125" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 42/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9758 - loss: 0.0701 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 85/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9752 - loss: 0.0739" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 128/1875\u001b[0m \u001b[32m━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9754 - loss: 0.0742" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 173/1875\u001b[0m \u001b[32m━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9758 - loss: 0.0745" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 217/1875\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9758 - loss: 0.0755" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 261/1875\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9756 - loss: 0.0766" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 305/1875\u001b[0m \u001b[32m━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9755 - loss: 0.0774" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 349/1875\u001b[0m \u001b[32m━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9753 - loss: 0.0781" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 393/1875\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9751 - loss: 0.0789" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 438/1875\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9749 - loss: 0.0794" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 483/1875\u001b[0m \u001b[32m━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9749 - loss: 0.0798" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 528/1875\u001b[0m \u001b[32m━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9748 - loss: 0.0802" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 572/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9747 - loss: 0.0806" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 616/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9746 - loss: 0.0810" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 660/1875\u001b[0m \u001b[32m━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9746 - loss: 0.0813" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 705/1875\u001b[0m \u001b[32m━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9745 - loss: 0.0815" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 749/1875\u001b[0m \u001b[32m━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9745 - loss: 0.0816" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 792/1875\u001b[0m \u001b[32m━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9745 - loss: 0.0818" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 836/1875\u001b[0m \u001b[32m━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9744 - loss: 0.0820" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 880/1875\u001b[0m \u001b[32m━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9744 - loss: 0.0821" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 924/1875\u001b[0m \u001b[32m━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9744 - loss: 0.0822" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 967/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9744 - loss: 0.0823" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1011/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9743 - loss: 0.0824" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1055/1875\u001b[0m \u001b[32m━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9743 - loss: 0.0826" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1097/1875\u001b[0m \u001b[32m━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9742 - loss: 0.0827" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1140/1875\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9742 - loss: 0.0828" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1184/1875\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9742 - loss: 0.0830" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1228/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9741 - loss: 0.0831" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1272/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9741 - loss: 0.0832" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1316/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9741 - loss: 0.0832" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1360/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9741 - loss: 0.0833" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1403/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9740 - loss: 0.0834" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1447/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9740 - loss: 0.0835" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1491/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9740 - loss: 0.0836" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1535/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9739 - loss: 0.0837" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1578/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9739 - loss: 0.0838" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1621/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9739 - loss: 0.0839" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1664/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9739 - loss: 0.0840" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1708/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9739 - loss: 0.0840" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1752/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9738 - loss: 0.0841" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1796/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9738 - loss: 0.0842" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1839/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9738 - loss: 0.0843" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9738 - loss: 0.0843\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 5/5\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "\u001b[1m 1/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1:25\u001b[0m 46ms/step - accuracy: 1.0000 - loss: 0.0105" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 42/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9725 - loss: 0.0800 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 84/1875\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9727 - loss: 0.0810" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 128/1875\u001b[0m \u001b[32m━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9725 - loss: 0.0817" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 172/1875\u001b[0m \u001b[32m━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9731 - loss: 0.0814" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 216/1875\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9738 - loss: 0.0805" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 260/1875\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9745 - loss: 0.0792" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 304/1875\u001b[0m \u001b[32m━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9749 - loss: 0.0784" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 349/1875\u001b[0m \u001b[32m━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9751 - loss: 0.0778" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 392/1875\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9754 - loss: 0.0775" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 435/1875\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9755 - loss: 0.0773" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 479/1875\u001b[0m \u001b[32m━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9756 - loss: 0.0773" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 522/1875\u001b[0m \u001b[32m━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9758 - loss: 0.0772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 565/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9759 - loss: 0.0772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 609/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9760 - loss: 0.0772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 651/1875\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9760 - loss: 0.0772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 693/1875\u001b[0m \u001b[32m━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9761 - loss: 0.0772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 736/1875\u001b[0m \u001b[32m━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9762 - loss: 0.0772" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 778/1875\u001b[0m \u001b[32m━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9762 - loss: 0.0771" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 821/1875\u001b[0m \u001b[32m━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9762 - loss: 0.0771" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 864/1875\u001b[0m \u001b[32m━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9763 - loss: 0.0771" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 906/1875\u001b[0m \u001b[32m━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9763 - loss: 0.0771" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 950/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9763 - loss: 0.0771" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m 994/1875\u001b[0m \u001b[32m━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0770" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1037/1875\u001b[0m \u001b[32m━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0770" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1081/1875\u001b[0m \u001b[32m━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1125/1875\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1169/1875\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1214/1875\u001b[0m \u001b[32m━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1258/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1302/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1346/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1389/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1432/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1476/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1518/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1558/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1600/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1642/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1684/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1727/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1770/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1814/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1859/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9764 - loss: 0.0769\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model.fit(x_train, y_train, epochs=5)" ] }, { "cell_type": "markdown", "metadata": { "id": "4mDAAPFqVVgn" }, "source": [ "The `Model.evaluate` method checks the model's performance, usually on a [validation set](https://developers.google.com/machine-learning/glossary#validation-set) or [test set](https://developers.google.com/machine-learning/glossary#test-set)." ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "id": "F7dTAzgHDUh7" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "313/313 - 0s - 468us/step - accuracy: 0.9753 - loss: 0.0798\n" ] }, { "data": { "text/plain": [ "[0.07982742041349411, 0.9753000140190125]" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model.evaluate(x_test, y_test, verbose=2)" ] }, { "cell_type": "markdown", "metadata": { "id": "T4JfEh7kvx6m" }, "source": [ "The image classifier is now trained to ~98% accuracy on this dataset. To learn more, read the [TensorFlow tutorials](https://www.tensorflow.org/tutorials/)." ] }, { "cell_type": "markdown", "metadata": { "id": "Aj8NrlzlJqDG" }, "source": [ "If you want your model to return a probability, you can wrap the trained model, and attach the softmax to it:" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "id": "rYb6DrEH0GMv" }, "outputs": [], "source": [ "probability_model = tf.keras.Sequential([model, tf.keras.layers.Softmax()])" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "id": "cnqOZtUp1YR_" }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "probability_model(x_test[:5])" ] }, { "cell_type": "markdown", "metadata": { "id": "-47O6_GLdRuT" }, "source": [ "## Conclusion\n", "\n", "Congratulations! You have trained a machine learning model using a prebuilt dataset using the [Keras](https://www.tensorflow.org/guide/keras/overview) API.\n", "\n", "For more examples of using Keras, check out the [tutorials](https://www.tensorflow.org/tutorials/keras/). To learn more about building models with Keras, read the [guides](https://www.tensorflow.org/guide/keras). If you want learn more about loading and preparing data, see the tutorials on [image data loading](https://www.tensorflow.org/tutorials/load_data/images) or [CSV data loading](https://www.tensorflow.org/tutorials/load_data/csv).\n" ] } ], "metadata": { "colab": { "name": "beginner.ipynb", "toc_visible": true }, "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.4" } }, "nbformat": 4, "nbformat_minor": 4 }