如何在keras中交替拟合两个模型答案

【问题标题】：How to fit two model alternately in keras如何在keras中交替拟合两个模型
【发布时间】：2019-10-20 01:21:55
【问题描述】：

与link1和link2不同，现在我有两个损失函数不同的网络，我想在一批中交替拟合这两个模型。

具体来说，如果有一个模型，A。我用下面的伪代码训练它：

model = some_value # initial
for e in 1:epoch
    for b in 1:batch
        model = train(A, model)

上面的程序在keras中只需要一行代码就可以实现：

model.fit(X_train, Y_train,
          batch_size=32, epoch=10)

现在，我有两个模型，A 和 B。我通过以下伪代码训练它们：

model_A = some_value # initial
model_B = some_value # initial
for e in 1:epoch
    for b in 1:batch
        model_A = train(A, model_B) # I using the model_B in the loss function of neural network model_A
        model_B = train(A, model_A) # I using the model_A in the loss function of neural network model_B

如何在keras中实现这个程序？

【问题讨论】：

标签： python-3.x keras neural-network

【解决方案1】：

batchlen = int(len(X_train)/batches)
for e in range(0,epochs):
    for b in range(0,batches):
        model_A.fit(
          X_train[b*batchlen:(b+1)*batchlen], 
          Y_train[b*batchlen:(b+1)*batchlen], 
          initial_epoch=e, 
          epochs=e+1)
        model_B.fit(X_train[b*batchlen:(b+1)*batchlen], Y_train[b*batchlen:(b+1)*batchlen], initial_epoch=e, epochs=e+1)

更好的方法是使用fit_generator 和generator 来提供X_train, Y_train。结果应该是这样的

for e in range(0,epochs):
    model_A.fit_generator(
      your_generator(X_train, Y_train), 
      initial_epoch=e, 
      epochs=e+1, 
      steps_per_epoch=len(X_train)/(batch_size))
    model_B.fit_generator(your_generator(X_train, Y_train), initial_epoch=e, epochs=e+1, steps_per_epoch=len(X_train)/(batch_size))

【讨论】：