05_専門家の迅速な入門、MNISTデータセットのロード、データセットの分割と混同、クラスを定義する方法でモデルを構築、オプティマイザと損失関数の選択、トレーニングモデルとテストモデルの精度

https://tensorflow.google.cn/tutorials/quickstart/advanced
TensorFlowをプログラムにインポートします.

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

MNISTデータセットのロードと準備

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

# Add a channels dimension
x_train = x_train[..., tf.newaxis]
x_test = x_test[..., tf.newaxis]

tfを使用する.dataは、データセットをbatchに分割し、データセットを混同する.

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モデルのサブクラス化(model subclassing)APIを用いてtfを構築する.kerasモデル:

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()

トレーニング用にオプティマイザと損失関数を選択します.

loss_object = tf.keras.losses.SparseCategoricalCrossentropy()
optimizer = tf.keras.optimizers.Adam()

測定指標を選択してモデルの損失値(loss)と精度(accuracy)を測定した.これらの指標はepochに値を蓄積し,整理結果を印刷する.

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を使用する.GradientTapeは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)

テストモデル:

@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):
    #  epoch ， 
    train_loss.reset_states()
    train_accuracy.reset_states()
    test_loss.reset_states()
    test_accuracy.reset_states()

    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 = "Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}"
    print(template.format(
            epoch + 1,
            train_loss.result(),
            train_accuracy.result() * 100,
            test_loss.result(),
            test_accuracy.result() * 100))

出力結果:

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.
Epoch 1, Loss: 0.13633669912815094, Accuracy: 95.92000579833984, Test Loss: 0.054682306945323944, Test Accuracy: 98.19999694824219
Epoch 2, Loss: 0.041911669075489044, Accuracy: 98.70333099365234, Test Loss: 0.04665009677410126, Test Accuracy: 98.4000015258789
Epoch 3, Loss: 0.021748166531324387, Accuracy: 99.31666564941406, Test Loss: 0.05017175152897835, Test Accuracy: 98.36000061035156
Epoch 4, Loss: 0.01320651639252901, Accuracy: 99.55166625976562, Test Loss: 0.058168746531009674, Test Accuracy: 98.30999755859375
Epoch 5, Loss: 0.008145572617650032, Accuracy: 99.7316665649414, Test Loss: 0.06632857024669647, Test Accuracy: 98.30999755859375