Python Keras，如何获得每一层的输出

您可以使用:model.layers[index].output轻松获取任何图层的输出

对于所有图层，请使用以下内容:

from keras import backend as K

inp = model.input                                           # input placeholder
outputs = [layer.output for layer in model.layers]          # all layer outputs
functors = [K.function([inp, K.learning_phase()], [out]) for out in outputs]    # evaluation functions

# Testing
test = np.random.random(input_shape)[np.newaxis,...]
layer_outs = [func([test, 1.]) for func in functors]
print layer_outs

注:要模拟辍学，使用learning_phase作为layer_outs中的1.，否则使用0.

Edit:(基于 comments )

K.function创建no/tensorflow张量函数，该函数稍后用于从给定输入的符号图中获取输出.

现在需要K.learning_phase()作为输入，因为许多Kera层(如Dropout/BatchNoralization)都依赖它在训练和测试期间改变行为.

因此，如果删除代码中的退出层，只需使用:

from keras import backend as K

inp = model.input                                           # input placeholder
outputs = [layer.output for layer in model.layers]          # all layer outputs
functors = [K.function([inp], [out]) for out in outputs]    # evaluation functions

# Testing
test = np.random.random(input_shape)[np.newaxis,...]
layer_outs = [func([test]) for func in functors]
print layer_outs

Edit 2: More optimized

I just realized that the previous answer is not that optimized as for each function evaluation the data will be transferred CPU->GPU memory and also the tensor calculations needs to be done for the lower layers over-n-over.

相反，这是一种更好的方法，因为您不需要多个函数，只需要一个函数就可以列出所有输出:

from keras import backend as K

inp = model.input                                           # input placeholder
outputs = [layer.output for layer in model.layers]          # all layer outputs
functor = K.function([inp, K.learning_phase()], outputs )   # evaluation function

# Testing
test = np.random.random(input_shape)[np.newaxis,...]
layer_outs = functor([test, 1.])
print layer_outs