05_专家的快速入门、加载MNIST数据集、数据集切分和混淆、定义类的方式构建模型、选择优化器和损失函数、训练模型和测试模型准确率

https://tensorflow.google.cn/tutorials/quickstart/advanced

导入TensorFlow到你的程序中：

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

加载和准备MNIST数据集

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]

使用 tf.data 来将数据集切分为 batch 以及混淆数据集：

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)

使用 Keras 模型子类化（model subclassing） API构建tf.keras模型：

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()

为训练选择优化器与损失函数：

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

选择衡量指标来度量模型的损失值（loss）和准确率（accuracy）。这些指标在epoch上累积值，然后打印出整理结果。

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')

使用tf.GradientTape来训练模型：

@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)

测试模型：

@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):
    # 在下一个epoch开始是，重置评估指标
    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))

输出结果：

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