Skip to content

Commit

Permalink
Merge pull request #521 from pyml-niigata:site_ja_r2_tutorials_quicks…
Browse files Browse the repository at this point in the history 
…tart

PiperOrigin-RevId: 247472085
  • Loading branch information
Copybara-Service committed May 9, 2019
2 parents fe50440 + a094a12 commit e300fcd
Show file tree
Hide file tree
Showing 2 changed files with 622 additions and 0 deletions.
387 changes: 387 additions & 0 deletions site/ja/r2/tutorials/quickstart/advanced.ipynb
View file
@@ -0,0 +1,387 @@
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "advanced.ipynb",
"version": "0.3.2",
"provenance": [],
"private_outputs": true,
"collapsed_sections": [],
"toc_visible": true
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "rX8mhOLljYeM"
},
"source": [
"##### Copyright 2019 The TensorFlow Authors.\n",
"\n",
"Licensed under the Apache License, Version 2.0 (the \"License\");"
]
},
{
"cell_type": "code",
"metadata": {
"cellView": "form",
"colab_type": "code",
"id": "BZSlp3DAjdYf",
"colab": {}
},
"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."
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "3wF5wszaj97Y"
},
"source": [
"# エキスパートのための TensorFlow 2.0 入門"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "DUNzJc4jTj6G"
},
"source": [
"<table class=\"tfo-notebook-buttons\" align=\"left\">\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://www.tensorflow.org/alpha/tutorials/quickstart/advanced\"><img src=\"https://www.tensorflow.org/images/tf_logo_32px.png\" />View on TensorFlow.org</a>\n",
" </td>\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/docs/blob/master/site/ja/r2/tutorials/quickstart/advanced.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
" </td>\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://github.com/tensorflow/docs/blob/master/site/ja/r2/tutorials/quickstart/advanced.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on GitHub</a>\n",
" </td>\n",
"</table>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "3iSSiYRWx0ba",
"colab_type": "text"
},
"source": [
"Note: これらのドキュメントは私たちTensorFlowコミュニティが翻訳したものです。コミュニティによる 翻訳は**ベストエフォート**であるため、この翻訳が正確であることや[英語の公式ドキュメント](https://www.tensorflow.org/?hl=en)の 最新の状態を反映したものであることを保証することはできません。 この翻訳の品質を向上させるためのご意見をお持ちの方は、GitHubリポジトリ[tensorflow/docs](https://github.com/tensorflow/docs)にプルリクエストをお送りください。 コミュニティによる翻訳やレビューに参加していただける方は、 [docs-ja@tensorflow.org メーリングリスト](https://groups.google.com/a/tensorflow.org/forum/#!forum/docs-ja)にご連絡ください。"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "hiH7AC-NTniF"
},
"source": [
"このファイルは[Google Colaboratory](https://colab.research.google.com/notebooks/welcome.ipynb) の notebook ファイルです。 Python プログラムはブラウザ上で直接実行されます。TensorFlowを学んだり使ったりするには最良の方法です。Google Colab のnotebookの実行方法は以下のとおりです。\n",
"\n",
"1. Pythonランタイムへの接続：メニューバーの右上で「接続」を選択します。\n",
"2. ノートブックのコードセルをすべて実行：「ランタイム」メニューから「すべてのセルを実行」を選択します。\n",
"\n",
"この他の例やガイドは[TensorFlow tutorials](https://www.tensorflow.org/alpha/tutorials/)を参照してください。\n",
"\n",
"はじめに、TensorFlowライブラリをプログラムにインポートします。"
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "0trJmd6DjqBZ",
"colab": {}
},
"source": [
"from __future__ import absolute_import, division, print_function, unicode_literals\n",
"\n",
"!pip install tensorflow-gpu==2.0.0-alpha0\n",
"import tensorflow as tf\n",
"\n",
"from tensorflow.keras.layers import Dense, Flatten, Conv2D\n",
"from tensorflow.keras import Model"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "7NAbSZiaoJ4z"
},
"source": [
"[MNIST データセット](http://yann.lecun.com/exdb/mnist/)をロードして準備します。"
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "JqFRS6K07jJs",
"colab": {}
},
"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\n",
"\n",
"# Add a channels dimension\n",
"x_train = x_train[..., tf.newaxis]\n",
"x_test = x_test[..., tf.newaxis]"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "k1Evqx0S22r_"
},
"source": [
"データセットをシャッフルし、バッチ化するために tf.data を使います。"
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "8Iu_quO024c2",
"colab": {}
},
"source": [
"train_ds = tf.data.Dataset.from_tensor_slices(\n",
" (x_train, y_train)).shuffle(10000).batch(32)\n",
"test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "BPZ68wASog_I"
},
"source": [
"Kerasの[model subclassing API](https://www.tensorflow.org/guide/keras#model_subclassing)を使って`tf.keras`モデルを作ります。"
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "h3IKyzTCDNGo",
"colab": {}
},
"source": [
"class MyModel(Model):\n",
" def __init__(self):\n",
" super(MyModel, self).__init__()\n",
" self.conv1 = Conv2D(32, 3, activation='relu')\n",
" self.flatten = Flatten()\n",
" self.d1 = Dense(128, activation='relu')\n",
" self.d2 = Dense(10, activation='softmax')\n",
"\n",
" def call(self, x):\n",
" x = self.conv1(x)\n",
" x = self.flatten(x)\n",
" x = self.d1(x)\n",
" return self.d2(x)\n",
"\n",
"model = MyModel()"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "uGih-c2LgbJu"
},
"source": [
"訓練のためにオプティマイザと損失関数を選びます。"
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "u48C9WQ774n4",
"colab": {}
},
"source": [
"loss_object = tf.keras.losses.SparseCategoricalCrossentropy()\n",
"\n",
"optimizer = tf.keras.optimizers.Adam()"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "JB6A1vcigsIe"
},
"source": [
"モデルの損失と正解率を計測するためのメトリクスを選択します。これらのメトリクスはエポックごとに値を集計し、最終結果を出力します。"
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "N0MqHFb4F_qn",
"colab": {}
},
"source": [
"train_loss = tf.keras.metrics.Mean(name='train_loss')\n",
"train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')\n",
"\n",
"test_loss = tf.keras.metrics.Mean(name='test_loss')\n",
"test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "ix4mEL65on-w"
},
"source": [
"`tf.GradientTape`を使ってモデルを訓練します。"
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "OZACiVqA8KQV",
"colab": {}
},
"source": [
"@tf.function\n",
"def train_step(image, label):\n",
" with tf.GradientTape() as tape:\n",
" predictions = model(image)\n",
" loss = loss_object(label, predictions)\n",
" gradients = tape.gradient(loss, model.trainable_variables)\n",
" optimizer.apply_gradients(zip(gradients, model.trainable_variables))\n",
"\n",
" train_loss(loss)\n",
" train_accuracy(label, predictions)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "Z8YT7UmFgpjV"
},
"source": [
"次にモデルをテストします。"
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "xIKdEzHAJGt7",
"colab": {}
},
"source": [
"@tf.function\n",
"def test_step(image, label):\n",
" predictions = model(image)\n",
" t_loss = loss_object(label, predictions)\n",
"\n",
" test_loss(t_loss)\n",
" test_accuracy(label, predictions)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "i-2pkctU_Ci7",
"colab": {}
},
"source": [
"EPOCHS = 5\n",
"\n",
"for epoch in range(EPOCHS):\n",
" for image, label in train_ds:\n",
" train_step(image, label)\n",
"\n",
" for test_image, test_label in test_ds:\n",
" test_step(test_image, test_label)\n",
"\n",
" template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'\n",
" print (template.format(epoch+1,\n",
" train_loss.result(),\n",
" train_accuracy.result()*100,\n",
" test_loss.result(),\n",
" test_accuracy.result()*100))"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "T4JfEh7kvx6m"
},
"source": [
"この画像分類器は、今回のデータセットで訓練した場合、最大98%程度の正解率となります。更に学ぶには[TensorFlow tutorials](https://www.tensorflow.org/alpha/tutorials/)を読んでください。"
]
}
]
}

0 comments on commit e300fcd

Please sign in to comment.