{ "cells": [ { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "import keras\n", "from keras.datasets import mnist\n", "from keras.models import Sequential\n", "from keras.layers import Dense, Dropout, Flatten\n", "from keras.layers import Conv2D, MaxPooling2D\n", "from keras import backend as K\n", "\n", "%matplotlib inline\n", "\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "batch_size = 128\n", "num_classes = 10\n", "epochs = 12\n", "\n", "# input image dimensions\n", "img_rows, img_cols = 28, 28\n", "\n", "# the data, split between train and test sets\n", "(x_train, y_train), (x_test, y_test) = mnist.load_data()" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Ground truth digit: 5\n" ] }, { "data": { "text/plain": [ " " ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ " " ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "print(\"Ground truth digit: \" + str(y_train[0]))\n", "plt.imshow(x_train[0,:,:])" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "x_train shape: (60000, 28, 28, 1)\n", "60000 train samples\n", "10000 test samples\n" ] } ], "source": [ "x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)\n", "x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)\n", "input_shape = (img_rows, img_cols, 1)\n", "\n", "x_train = x_train.astype('float32')\n", "x_test = x_test.astype('float32')\n", "x_train /= 255\n", "x_test /= 255\n", "print('x_train shape:', x_train.shape)\n", "print(x_train.shape[0], 'train samples')\n", "print(x_test.shape[0], 'test samples')\n", "\n", "# convert class vectors to binary class matrices\n", "y_train = keras.utils.to_categorical(y_train, num_classes)\n", "y_test = keras.utils.to_categorical(y_test, num_classes)" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [], "source": [ "model = Sequential()\n", "model.add(Conv2D(32, kernel_size=(3, 3),\n", " activation='relu',\n", " input_shape=input_shape))\n", "model.add(Conv2D(64, (3, 3), activation='relu'))\n", "model.add(MaxPooling2D(pool_size=(2, 2)))\n", "model.add(Dropout(0.25))\n", "model.add(Flatten())\n", "model.add(Dense(128, activation='relu'))\n", "model.add(Dropout(0.5))\n", "model.add(Dense(num_classes, activation='softmax'))\n", "\n", "model.compile(loss=keras.losses.categorical_crossentropy,\n", " optimizer=keras.optimizers.Adadelta(),\n", " metrics=['accuracy'])" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Train on 60000 samples, validate on 10000 samples\n", "Epoch 1/12\n", "60000/60000 [==============================] - 83s 1ms/step - loss: 0.2700 - acc: 0.9181 - val_loss: 0.0589 - val_acc: 0.9813\n", "Epoch 2/12\n", "60000/60000 [==============================] - 86s 1ms/step - loss: 0.0924 - acc: 0.9731 - val_loss: 0.0440 - val_acc: 0.9857\n", "Epoch 3/12\n", "60000/60000 [==============================] - 88s 1ms/step - loss: 0.0698 - acc: 0.9802 - val_loss: 0.0336 - val_acc: 0.9888\n", "Epoch 4/12\n", "60000/60000 [==============================] - 87s 1ms/step - loss: 0.0548 - acc: 0.9834 - val_loss: 0.0335 - val_acc: 0.9891\n", "Epoch 5/12\n", "60000/60000 [==============================] - 95s 2ms/step - loss: 0.0468 - acc: 0.9865 - val_loss: 0.0287 - val_acc: 0.9901\n", "Epoch 6/12\n", "60000/60000 [==============================] - 85s 1ms/step - loss: 0.0429 - acc: 0.9871 - val_loss: 0.0305 - val_acc: 0.9899\n", "Epoch 7/12\n", "60000/60000 [==============================] - 88s 1ms/step - loss: 0.0385 - acc: 0.9882 - val_loss: 0.0282 - val_acc: 0.9914\n", "Epoch 8/12\n", "60000/60000 [==============================] - 89s 1ms/step - loss: 0.0346 - acc: 0.9889 - val_loss: 0.0327 - val_acc: 0.9893\n", "Epoch 9/12\n", "60000/60000 [==============================] - 90s 2ms/step - loss: 0.0319 - acc: 0.9902 - val_loss: 0.0291 - val_acc: 0.9916\n", "Epoch 10/12\n", "60000/60000 [==============================] - 89s 1ms/step - loss: 0.0303 - acc: 0.9904 - val_loss: 0.0274 - val_acc: 0.9915\n", "Epoch 11/12\n", "60000/60000 [==============================] - 88s 1ms/step - loss: 0.0290 - acc: 0.9907 - val_loss: 0.0239 - val_acc: 0.9920\n", "Epoch 12/12\n", "60000/60000 [==============================] - 2345s 39ms/step - loss: 0.0268 - acc: 0.9915 - val_loss: 0.0292 - val_acc: 0.9911\n", "Test loss: 0.029208712538642795\n", "Test accuracy: 0.9911\n" ] } ], "source": [ "model.fit(x_train, y_train,\n", " batch_size=batch_size,\n", " epochs=epochs,\n", " verbose=1,\n", " validation_data=(x_test, y_test))\n", "score = model.evaluate(x_test, y_test, verbose=0)\n", "print('Test loss:', score[0])\n", "print('Test accuracy:', score[1])" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Ground truth digit: [0. 0. 0. 0. 0. 0. 0. 1. 0. 0.]\n", "Predicted digit: [[8.6205862e-11 6.5843611e-09 1.3023222e-07 6.5092524e-07 1.1015908e-11\n", " 9.6391515e-13 1.3074086e-14 9.9999917e-01 2.8599112e-10 1.6961188e-07]]\n", "Digit image:\n", "(28, 28, 1)\n" ] }, { "data": { "text/plain": [ " " ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ " " ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "ypred = model.predict(x_test[0,:,:].reshape(1, 28, 28, 1))\n", "\n", "print(\"Ground truth digit: \" + str(y_test[0]))\n", "print(\"Predicted digit: \" + str(ypred))\n", "print(\"Digit image:\")\n", "\n", "plt.imshow(x_test[0].reshape(28,28))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.3" } }, "nbformat": 4, "nbformat_minor": 2 }

map