每个时期后如何在训练过程中打印重量和偏向

Question

How to print the weights and bias in a neural network after each epoch during training

I have tried the following code:

print_weights = LambdaCallback(on_epoch_end=lambda epoch, logs: print(merged.layers[1].get_weights()[0][0:5], merged.layers[2].get_weights()[0][0:5]))


merged.compile(optimizer='adam',loss=[loss1, loss2],loss_weights=[alpham, 1 - alpham], metrics=['accuracy'],callbacks = [print_weights])  

But I am getting the following error:

ValueError: ('Some keys in session_kwargs are not supported at this time: %s', dict_keys(['callbacks']))

Answer 1

model.compile不接受提供给model.fit的回调。