希望将此作为评论(但没有足够高的代表)添加到@indraforyou的回答中，以纠正@mathtick的评论中提到的问题。为了避免InvalidArgumentError: input_X:Y被提供和获取。异常，只需替换行输出=[层。模型中层的输出。输出= [layer.]模型中层的输出。层][1:]。

调整indraforyou的最小工作示例:

from keras import backend as K 
inp = model.input                                           # input placeholder
outputs = [layer.output for layer in model.layers][1:]        # all layer outputs except first (input) layer
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

附注:我尝试输出=[层。模型中层的输出。Layers[1:]]不起作用。

你可以通过使用:model.layers[index].output轻松获得任何层的输出

对于所有层使用这个:

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

注意:要模拟Dropout，请使用learning_phase作为1。在layer_outs中，否则使用0。

编辑:(根据评论)

K.function创建了ano/tensorflow张量函数，之后用于从给定输入的符号图中获得输出。

现在需要K.learning_phase()作为输入，因为许多Keras层(如Dropout/Batchnomalization)依赖它来改变训练和测试期间的行为。

所以如果你在你的代码中删除dropout层，你可以简单地使用:

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

编辑2:更优化

我刚刚意识到，前面的答案并没有优化，因为对于每个函数的计算，数据将被CPU->GPU内存传输，而且张量计算需要对较低的层进行n-over。

相反，这是一种更好的方式，因为你不需要多个函数，而是一个函数给你所有输出的列表:

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

这个答案基于:https://stackoverflow.com/a/59557567/2585501

打印单个图层的输出:

from tensorflow.keras import backend as K
layerIndex = 1
func = K.function([model.get_layer(index=0).input], model.get_layer(index=layerIndex).output)
layerOutput = func([input_data])  # input_data is a numpy array
print(layerOutput)

打印每一层的输出:

from tensorflow.keras import backend as K
for layerIndex, layer in enumerate(model.layers):
    func = K.function([model.get_layer(index=0).input], layer.output)
    layerOutput = func([input_data])  # input_data is a numpy array
    print(layerOutput)

来自:https://github.com/philipperemy/keras-visualize-activations/blob/master/read_activations.py

import keras.backend as K

def get_activations(model, model_inputs, print_shape_only=False, layer_name=None):
    print('----- activations -----')
    activations = []
    inp = model.input

    model_multi_inputs_cond = True
    if not isinstance(inp, list):
        # only one input! let's wrap it in a list.
        inp = [inp]
        model_multi_inputs_cond = False

    outputs = [layer.output for layer in model.layers if
               layer.name == layer_name or layer_name is None]  # all layer outputs

    funcs = [K.function(inp + [K.learning_phase()], [out]) for out in outputs]  # evaluation functions

    if model_multi_inputs_cond:
        list_inputs = []
        list_inputs.extend(model_inputs)
        list_inputs.append(0.)
    else:
        list_inputs = [model_inputs, 0.]

    # Learning phase. 0 = Test mode (no dropout or batch normalization)
    # layer_outputs = [func([model_inputs, 0.])[0] for func in funcs]
    layer_outputs = [func(list_inputs)[0] for func in funcs]
    for layer_activations in layer_outputs:
        activations.append(layer_activations)
        if print_shape_only:
            print(layer_activations.shape)
        else:
            print(layer_activations)
    return activations

通常，输出大小可以计算为

[(W−K + 2P / S] + 1

在哪里

W is the input volume - in your case you have not given us this
K is the Kernel size - in your case 2 == "filter" 
P is the padding - in your case 2
S is the stride - in your case 3

另一个更漂亮的说法是:

根据这个线程的所有好答案，我写了一个库来获取每一层的输出。它抽象了所有的复杂性，并被设计成尽可能友好的用户:

https://github.com/philipperemy/keract

它可以处理几乎所有的边界情况。

希望能有所帮助!