{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "name": "keras-tf-sample.ipynb", "version": "0.3.2", "provenance": [], "include_colab_link": true }, "kernelspec": { "name": "python3", "display_name": "Python 3" } }, "cells": [ { "cell_type": "markdown", "metadata": { "id": "view-in-github", "colab_type": "text" }, "source": [ "\"Open" ] }, { "cell_type": "markdown", "metadata": { "id": "zy5ichg1VA97", "colab_type": "text" }, "source": [ "以下のサイトを参考にしました。\n", "- 「Keras / Tensorflowで始めるディープラーニング入門」 https://qiita.com/yampy/items/706d44417c433e68db0d" ] }, { "cell_type": "code", "metadata": { "id": "7jRl9looUSZ9", "colab_type": "code", "colab": { "base_uri": "https://localhost:8080/", "height": 34 }, "outputId": "b0c3cd80-32ac-413d-d585-b103ddadcda7" }, "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" ], "execution_count": 1, "outputs": [ { "output_type": "stream", "text": [ "Using TensorFlow backend.\n" ], "name": "stderr" } ] }, { "cell_type": "code", "metadata": { "id": "7tTXTQn0UyGi", "colab_type": "code", "colab": {} }, "source": [ "batch_size = 128\n", "num_classes = 10\n", "epochs = 3\n", "\n" ], "execution_count": 0, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "trCXc0XGU1xt", "colab_type": "code", "colab": {} }, "source": [ "img_rows, img_cols = 28, 28\n", "\n", "(x_train, y_train), (x_test, y_test) = mnist.load_data()" ], "execution_count": 0, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "9z32qSQqU9Px", "colab_type": "code", "colab": {} }, "source": [ "#Kerasのバックエンドで動くTensorFlowとTheanoでは入力チャンネルの順番が違うので場合分けして書いています\n", "if K.image_data_format() == 'channels_first':\n", " x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)\n", " x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)\n", " input_shape = (1, img_rows, img_cols)\n", "else:\n", " 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" ], "execution_count": 0, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "du1XCGbBVECT", "colab_type": "code", "colab": { "base_uri": "https://localhost:8080/", "height": 68 }, "outputId": "aadeacb2-91e6-4e05-d707-b9ece60eaef0" }, "source": [ "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')" ], "execution_count": 5, "outputs": [ { "output_type": "stream", "text": [ "x_train shape: (60000, 28, 28, 1)\n", "60000 train samples\n", "10000 test samples\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "AqnRhJyoVrjO", "colab_type": "code", "colab": {} }, "source": [ "y_train = y_train.astype('int32')\n", "y_test = y_test.astype('int32')\n", "y_train = keras.utils.np_utils.to_categorical(y_train, num_classes)\n", "y_test = keras.utils.np_utils.to_categorical(y_test, num_classes)\n" ], "execution_count": 0, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "CSklWGNjVvOR", "colab_type": "code", "colab": { "base_uri": "https://localhost:8080/", "height": 315 }, "outputId": "ce8a8390-6d52-4e43-b0aa-6ab33ce0470c" }, "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'))" ], "execution_count": 7, "outputs": [ { "output_type": "stream", "text": [ "WARNING: Logging before flag parsing goes to stderr.\n", "W0815 22:39:48.780859 139626640222080 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:74: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n", "\n", "W0815 22:39:48.803259 139626640222080 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n", "\n", "W0815 22:39:48.809604 139626640222080 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n", "\n", "W0815 22:39:48.843924 139626640222080 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3976: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.\n", "\n", "W0815 22:39:48.847448 139626640222080 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:133: The name tf.placeholder_with_default is deprecated. Please use tf.compat.v1.placeholder_with_default instead.\n", "\n", "W0815 22:39:48.860003 139626640222080 deprecation.py:506] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3445: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.\n", "Instructions for updating:\n", "Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.\n" ], "name": "stderr" } ] }, { "cell_type": "code", "metadata": { "id": "j_d10YewWISw", "colab_type": "code", "colab": { "base_uri": "https://localhost:8080/", "height": 105 }, "outputId": "a3d42703-5820-47ca-e5c1-737362237107" }, "source": [ "model.compile(loss=keras.losses.categorical_crossentropy,\n", " optimizer=keras.optimizers.Adadelta(),\n", " metrics=['accuracy'])" ], "execution_count": 8, "outputs": [ { "output_type": "stream", "text": [ "W0815 22:39:48.964365 139626640222080 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/optimizers.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n", "\n", "W0815 22:39:48.975083 139626640222080 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3295: The name tf.log is deprecated. Please use tf.math.log instead.\n", "\n" ], "name": "stderr" } ] }, { "cell_type": "code", "metadata": { "id": "D_Yuht6EWMpx", "colab_type": "code", "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "outputId": "b422c382-6e64-4e24-d720-5528a99dd734" }, "source": [ "model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs,\n", " verbose=1, validation_data=(x_test, y_test))" ], "execution_count": 9, "outputs": [ { "output_type": "stream", "text": [ "W0815 22:39:49.110717 139626640222080 deprecation.py:323] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_grad.py:1250: add_dispatch_support..wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n", "Instructions for updating:\n", "Use tf.where in 2.0, which has the same broadcast rule as np.where\n" ], "name": "stderr" }, { "output_type": "stream", "text": [ "Train on 60000 samples, validate on 10000 samples\n", "Epoch 1/3\n", "60000/60000 [==============================] - 158s 3ms/step - loss: 0.2604 - acc: 0.9192 - val_loss: 0.0632 - val_acc: 0.9808\n", "Epoch 2/3\n", "60000/60000 [==============================] - 157s 3ms/step - loss: 0.0910 - acc: 0.9732 - val_loss: 0.0436 - val_acc: 0.9855\n", "Epoch 3/3\n", "60000/60000 [==============================] - 157s 3ms/step - loss: 0.0650 - acc: 0.9805 - val_loss: 0.0370 - val_acc: 0.9870\n" ], "name": "stdout" }, { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": { "tags": [] }, "execution_count": 9 } ] } ] }