TensorFlow2.0入门到进阶2.16 —— 手动实现超参数搜索

1、理论原理

超参数搜索：
https://blog.csdn.net/caoyuan666/article/details/105933836

2、代码

这里手动实现网格搜索，其实就是提前设立几个参数，通过for函数来实现。

#learning_rate[1e-4,3e-4,1e-3,3e-3,1e-2,3e-2]
#w = w + grad * learning_rate

histories=[]
learning_rate=[1e-4,3e-4,1e-3,3e-3,1e-2,3e-2]
for lr in learning_rate:
    model=keras.models.Sequential([
        keras.layers.Dense(30,activation='relu',
                          input_shape=x_train.shape[1:]),
        keras.layers.Dense(1),
    ])
    optimizer = keras.optimizers.SGD(lr)

    model.summary()
    model.compile(loss='mean_squared_error',
                  optimizer=optimizer,)
    callbacks=[keras.callbacks.EarlyStopping(patience=5,min_delta=1e-2)]
    history=model.fit(x_train_scaled,y_train,
             epochs=100,
             validation_data=(x_valid_scaled,y_valid),
             callbacks = callbacks )
    histories.append(history)