Question

现在与link1和link2不同，我有两个分别具有不同损失函数的网络，并且我希望将这两个模型交替地放入一批中。

具体来说，如果有一个模型，A。我通过以下伪代码对其进行训练：

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

以上过程只能通过keras中的一行代码来实现：

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中实现此过程？

Answer 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)

更好的方法是将fit_generator与generator一起使用来填充X_train, Y_train。结果应该是

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))

如何在keras中交替拟合两个模型

1 个答案: