一、使用内置的训练和评估
使用内置api(model.fit(), model.evaluate(), model.predict())
def buildInTrainAndEvaluate():
inputs = keras.Input(shape=(784,), name='digits')
x = layers.Dense(64, activation='relu', name='dense_1')(inputs)
x = layers.Dense(64, activation='relu', name='dense_2')(x)
outputs = layers.Dense(10, activation='softmax', name='predictions')(x)
# 构建模型
model = keras.Model(inputs=inputs, outputs=outputs)
# 加载数据
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
# 归一化
x_train = x_train.reshape(60000, 784).astype('float32') / 255
x_test = x_test.reshape(10000, 784).astype('float32') / 255
y_train = y_train.astype('float32')
y_test = y_test.astype('float32')
# 拆分数据和标签
x_val = x_train[-10000:]
y_val = y_train[-10000:]
x_train = x_train[:-10000]
y_train = y_train[:-10000]
# 编译模型， 设置训练参数（optimizer, loss, metrics）
model.compile(optimizer=keras.optimizers.RMSprop(), # Optimizer
# Loss function to minimize
loss=keras.losses.SparseCategoricalCrossentropy(),
# List of metrics to monitor
metrics=[keras.metrics.SparseCategoricalAccuracy()])
# 训练模型
print('# Fit model on training data')
history = model.fit(x_train, y_train,
batch_size=64,
epochs=3,
validation_data=(x_val, y_val))
print('\nhistory dict:', history.history)
# 评估模型
print('\n# Evaluate on test data')
results = model.evaluate(x_test, y_test, batch_size=128)
print('test loss, test acc:', results)
# 使用模型对新数据预测
print('\n# Generate predictions for 3 samples')
predictions = model.predict(x_test[:3])
print('predictions shape:', predictions.shape)
