Tensorflow for advanced

Classic/VPC環境で利用できます。

さらに多くの例や詳しい案内は、TensorFlowチュートリアルをご参照ください。

始めに、プログラムにTensorFlowライブラリをインポートします。

import tensorflow as tf

from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras import Model

MNISTデータセットをロードして準備します。

mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

# チャネル次元を追加します。
x_train = x_train[..., tf.newaxis]
x_test = x_test[..., tf.newaxis]

f.dataを使用してデータセットを混ぜ、バッチを作成します。

train_ds = tf.data.Dataset.from_tensor_slices(
    (x_train, y_train)).shuffle(10000).batch(32)
test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)

Kerasのモデルサブクラス化(subclassing) APIを使用してtf.kerasモデルを作成します。

class MyModel(Model):
  def __init__(self):
    super(MyModel, self).__init__()
    self.conv1 = Conv2D(32, 3, activation='relu')
    self.flatten = Flatten()
    self.d1 = Dense(128, activation='relu')
    self.d2 = Dense(10, activation='softmax')

  def call(self, x):
    x = self.conv1(x)
    x = self.flatten(x)
    x = self.d1(x)
    return self.d2(x)

model = MyModel()

訓練に必要なオプティマイザー(optimizer)と損失関数を選択します。

loss_object = tf.keras.losses.SparseCategoricalCrossentropy()

optimizer = tf.keras.optimizers.Adam()

モデルの損失と性能を測定する指標を選択します。エポックが行われる間、収集された測定指標に基づいて最終結果を出力します。

train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')

test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')

tf.GradientTapeを使用してモデルを訓練します。

@tf.function
def train_step(images, labels):
  with tf.GradientTape() as tape:
    predictions = model(images)
    loss = loss_object(labels, predictions)
  gradients = tape.gradient(loss, model.trainable_variables)
  optimizer.apply_gradients(zip(gradients, model.trainable_variables))

  train_loss(loss)
  train_accuracy(labels, predictions)

ではモデルをテストします。

@tf.function
def test_step(images, labels):
  predictions = model(images)
  t_loss = loss_object(labels, predictions)

  test_loss(t_loss)
  test_accuracy(labels, predictions)

EPOCHS = 5

for epoch in range(EPOCHS):
  for images, labels in train_ds:
    train_step(images, labels)

  for test_images, test_labels in test_ds:
    test_step(test_images, test_labels)

  template = 「エポック：{}、損失：{}、精度：{}、テスト損失：{}、テスト精度{}」
  print (template.format(epoch+1,
                         train_loss.result(),
                         train_accuracy.result()*100,
                         test_loss.result(),
                         test_accuracy.result()*100))
                         
'''
WARNING:tensorflow:Entity <function train_step at 0x7f24a41c2b70> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Str'
WARNING: Entity <function train_step at 0x7f24a41c2b70> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Str'
WARNING:tensorflow:Layer my_model is casting an input tensor from dtype float64 to the layer's dtype of float32, which is new behavior in TensorFlow 2.  The layer has dtype float32 because it's dtype defaults to floatx.

If you intended to run this layer in float32, you can safely ignore this warning. If in doubt, this warning is likely only an issue if you are porting a TensorFlow 1.X model to TensorFlow 2.

To change all layers to have dtype float64 by default, call `tf.keras.backend.set_floatx('float64')`. To change just this layer, pass dtype='float64' to the layer constructor. If you are the author of this layer, you can disable autocasting by passing autocast=False to the base Layer constructor.

WARNING:tensorflow:Entity <bound method MyModel.call of <__main__.MyModel object at 0x7f24a14b7908>> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: Bad argument number for Name: 3, expecting 4
WARNING: Entity <bound method MyModel.call of <__main__.MyModel object at 0x7f24a14b7908>> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: Bad argument number for Name: 3, expecting 4
WARNING:tensorflow:Entity <function Function._initialize_uninitialized_variables.<locals>.initialize_variables at 0x7f24a13f4840> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Num'
WARNING: Entity <function Function._initialize_uninitialized_variables.<locals>.initialize_variables at 0x7f24a13f4840> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Num'
WARNING:tensorflow:Entity <bound method MyModel.call of <__main__.MyModel object at 0x7f24a14b7908>> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: Bad argument number for Name: 3, expecting 4
WARNING: Entity <bound method MyModel.call of <__main__.MyModel object at 0x7f24a14b7908>> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: Bad argument number for Name: 3, expecting 4
WARNING:tensorflow:Entity <function test_step at 0x7f24a41c2bf8> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Str'
WARNING: Entity <function test_step at 0x7f24a41c2bf8> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Str'
WARNING:tensorflow:Entity <bound method MyModel.call of <__main__.MyModel object at 0x7f24a14b7908>> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: Bad argument number for Name: 3, expecting 4
WARNING: Entity <bound method MyModel.call of <__main__.MyModel object at 0x7f24a14b7908>> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: Bad argument number for Name: 3, expecting 4
WARNING:tensorflow:Entity <bound method MyModel.call of <__main__.MyModel object at 0x7f24a14b7908>> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: Bad argument number for Name: 3, expecting 4
WARNING: Entity <bound method MyModel.call of <__main__.MyModel object at 0x7f24a14b7908>> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: Bad argument number for Name: 3, expecting 4
エポック：1、損失：0.1347680389881134、精度：95.9366683959961、テスト損失：0.05350242182612419、テスト精度：98.12999725341797
エポック：2、損失：0.0896165519952774、精度：97.27583312988281、テスト損失：0.054728906601667404、テスト精度：98.13500213623047
エポック：3、損失：0.06729747354984283、精度：97.9477767944336、テスト損失：0.05539105087518692、テスト精度：98.16667175292969
エポック：4、損失：0.05394642427563667、精度：98.34916687011719、テスト損失：0.055290184915065765、テスト精度：98.23750305175781
エポック：5、損失：0.04513656720519066、精度：98.60933685302734、テスト損失：0.05616115406155586、テスト精度：98.27400207519531
'''

訓練された画像分類器は、このデータセットで約98%の精度を達成します。詳細内容は、TensorFlowチュートリアルをご参照ください。