使用tensorflow对mnist进行分类

import tensorflow as tf

mnist = tf.keras.datasets.mnist



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

model = tf.keras.models.Sequential(
    [
        tf.keras.layers.Flatten(input_shape=(28, 28)),
        tf.keras.layers.Dense(128, activation='relu'),
        tf.keras.layers.Dense(10, activation='softmax')
    ]
)

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

model.fit(x_train, y_train, epochs=5)

model.evaluate(x_test, y_test)

结果如下：
…
…
56960/60000 [=>…] - ETA: 0s - loss: 0.0438 - acc: 0.9862
57408/60000 [=>…] - ETA: 0s - loss: 0.0439 - acc: 0.9861
57696/60000 [=>…] - ETA: 0s - loss: 0.0438 - acc: 0.9861
57984/60000 [=>…] - ETA: 0s - loss: 0.0439 - acc: 0.9861
58336/60000 [>.] - ETA: 0s - loss: 0.0440 - acc: 0.9860
58688/60000 [>.] - ETA: 0s - loss: 0.0440 - acc: 0.9861
58880/60000 [>.] - ETA: 0s - loss: 0.0439 - acc: 0.9861
59072/60000 [>.] - ETA: 0s - loss: 0.0439 - acc: 0.9861
59392/60000 [>.] - ETA: 0s - loss: 0.0439 - acc: 0.9861
59680/60000 [>.] - ETA: 0s - loss: 0.0441 - acc: 0.9860
59968/60000 [>.] - ETA: 0s - loss: 0.0440 - acc: 0.9861
60000/60000 [==] - 11s 176us/step - loss: 0.0439 - acc: 0.9861