Keras，如何获取每一层的输出？-IT科技

摘要：问题描述：我用 CNN 训练了一个二元分类模型，这是我的代码model = Sequential() model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1], border_mode=...

问题描述：

我用 CNN 训练了一个二元分类模型，这是我的代码

model = Sequential()
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
                        border_mode='valid',
                        input_shape=input_shape))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
# (16, 16, 32)
model.add(Convolution2D(nb_filters*2, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters*2, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
# (8, 8, 64) = (2048)
model.add(Flatten())
model.add(Dense(1024))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(2))  # define a binary classification problem
model.add(Activation('softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer='adadelta',
              metrics=['accuracy'])
model.fit(x_train, y_train,
          batch_size=batch_size,
          nb_epoch=nb_epoch,
          verbose=1,
          validation_data=(x_test, y_test))

这里，我想要像 TensorFlow 一样获取每一层的输出，我该怎么做？

解决方案 1：

您可以使用以下方法轻松获取任意层的输出：model.layers[index].output

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如下1.方式layer_outs`0.`

编辑：（根据评论）

K.function创建 theano/tensorflow 张量函数，稍后用于根据输入从符号图中获取输出。

现在K.learning_phase()需要作为输入，因为许多 Keras 层（例如 Dropout/Batchnomalization）都依赖它在训练和测试期间改变行为。

因此，如果你在代码中删除 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：更加优化

我刚刚意识到前面的答案并没有那么优化，因为对于每次函数评估，数据都会被传输到 CPU->GPU 内存，而且还需要对较低层进行一遍又一遍的张量计算。

相反，这是一个更好的方法，因为您不需要多个函数，而只需要一个函数为您提供所有输出的列表：

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

解决方案 2：

来自https://keras.io/getting-started/faq/#how-can-i-obtain-the-output-of-an-intermediate-layer

一种简单的方法是创建一个新模型，它将输出您感兴趣的层：

from keras.models import Model

model = ...  # include here your original model

layer_name = 'my_layer'
intermediate_layer_model = Model(inputs=model.input,
                                 outputs=model.get_layer(layer_name).output)
intermediate_output = intermediate_layer_model.predict(data)

或者，你可以构建一个 Keras 函数，该函数将根据特定的输入返回特定层的输出，例如：

from keras import backend as K

# with a Sequential model
get_3rd_layer_output = K.function([model.layers[0].input],
                                  [model.layers[3].output])
layer_output = get_3rd_layer_output([x])[0]

解决方案 3：

根据此主题的所有好答案，我编写了一个库来获取每一层的输出。它抽象了所有复杂性，并设计得尽可能方便用户使用：

https://github.com/philipperemy/keract

它可以处理几乎所有的边缘情况。

希望有帮助！

解决方案 4：

以下对我来说看起来很简单：

model.layers[idx].output

上面是一个张量对象，因此您可以使用可应用于张量对象的操作来修改它。

例如，要获取形状model.layers[idx].output.get_shape()

idx是图层的索引，你可以从中找到它model.summary()

解决方案 5：

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

要打印单层的输出：

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)

要打印每一层的输出：

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)

解决方案 6：

以前的解决方案对我不起作用。我按如下所示处理了这个问题。

layer_outputs = []
for i in range(1, len(model.layers)):
    tmp_model = Model(model.layers[0].input, model.layers[i].output)
    tmp_output = tmp_model.predict(img)[0]
    layer_outputs.append(tmp_output)

解决方案 7：

我为自己编写了这个函数（在 Jupyter 中），灵感来自indraforyou的回答。它将自动绘制所有层输出。您的图像必须具有 (x, y, 1) 形状，其中 1 代表 1 个通道。您只需调用 plot_layer_outputs(...) 即可绘图。

%matplotlib inline
import matplotlib.pyplot as plt
from keras import backend as K

def get_layer_outputs():
    test_image = YOUR IMAGE GOES HERE!!!
    outputs    = [layer.output for layer in model.layers]          # all layer outputs
    comp_graph = [K.function([model.input]+ [K.learning_phase()], [output]) for output in outputs]  # evaluation functions

    # Testing
    layer_outputs_list = [op([test_image, 1.]) for op in comp_graph]
    layer_outputs = []

    for layer_output in layer_outputs_list:
        print(layer_output[0][0].shape, end='
-------------------
')
        layer_outputs.append(layer_output[0][0])

    return layer_outputs

def plot_layer_outputs(layer_number):    
    layer_outputs = get_layer_outputs()

    x_max = layer_outputs[layer_number].shape[0]
    y_max = layer_outputs[layer_number].shape[1]
    n     = layer_outputs[layer_number].shape[2]

    L = []
    for i in range(n):
        L.append(np.zeros((x_max, y_max)))

    for i in range(n):
        for x in range(x_max):
            for y in range(y_max):
                L[i][x][y] = layer_outputs[layer_number][x][y][i]


    for img in L:
        plt.figure()
        plt.imshow(img, interpolation='nearest')

解决方案 8：

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

解决方案 9：

想将此作为评论添加到 @indraforyou 的答案中（但声誉不够高），以纠正 @mathtick 评论中提到的问题。要避免出现InvalidArgumentError: input_X:Y is both fed and fetched.异常，只需将该行替换outputs = [layer.output for layer in model.layers]为outputs = [layer.output for layer in model.layers][1:]，即

改编 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

附言：我尝试过诸如此类的事情，但outputs = [layer.output for layer in model.layers[1:]]没有成功。

解决方案 10：

假设您有：

1-Keras 预训练model。

2- 输入x图像或图像集。图像的分辨率应与输入层的尺寸兼容。例如，3 通道 (RGB) 图像的分辨率为80803 。

3- 获取激活的输出的名称layer。例如，“flatten_2”层。这应该包含在layer_names变量中，表示给定层的名称model。

4-batch_size是一个可选参数。

然后您可以轻松使用函数来获取给定输入和预先训练的get_activation输出的激活：layer`x`model

import six
import numpy as np
import keras.backend as k
from numpy import float32
def get_activations(x, model, layer, batch_size=128):
"""
Return the output of the specified layer for input `x`. `layer` is specified by layer index (between 0 and
`nb_layers - 1`) or by name. The number of layers can be determined by counting the results returned by
calling `layer_names`.
:param x: Input for computing the activations.
:type x: `np.ndarray`. Example: x.shape = (80, 80, 3)
:param model: pre-trained Keras model. Including weights.
:type model: keras.engine.sequential.Sequential. Example: model.input_shape = (None, 80, 80, 3)
:param layer: Layer for computing the activations
:type layer: `int` or `str`. Example: layer = 'flatten_2'
:param batch_size: Size of batches.
:type batch_size: `int`
:return: The output of `layer`, where the first dimension is the batch size corresponding to `x`.
:rtype: `np.ndarray`. Example: activations.shape = (1, 2000)
"""

    layer_names = [layer.name for layer in model.layers]
    if isinstance(layer, six.string_types):
        if layer not in layer_names:
            raise ValueError('Layer name %s is not part of the graph.' % layer)
        layer_name = layer
    elif isinstance(layer, int):
        if layer < 0 or layer >= len(layer_names):
            raise ValueError('Layer index %d is outside of range (0 to %d included).'
                             % (layer, len(layer_names) - 1))
        layer_name = layer_names[layer]
    else:
        raise TypeError('Layer must be of type `str` or `int`.')

    layer_output = model.get_layer(layer_name).output
    layer_input = model.input
    output_func = k.function([layer_input], [layer_output])

    # Apply preprocessing
    if x.shape == k.int_shape(model.input)[1:]:
        x_preproc = np.expand_dims(x, 0)
    else:
        x_preproc = x
    assert len(x_preproc.shape) == 4

    # Determine shape of expected output and prepare array
    output_shape = output_func([x_preproc[0][None, ...]])[0].shape
    activations = np.zeros((x_preproc.shape[0],) + output_shape[1:], dtype=float32)

    # Get activations with batching
    for batch_index in range(int(np.ceil(x_preproc.shape[0] / float(batch_size)))):
        begin, end = batch_index * batch_size, min((batch_index + 1) * batch_size, x_preproc.shape[0])
        activations[begin:end] = output_func([x_preproc[begin:end]])[0]

    return activations

解决方案 11：

如果您有以下情况之一：

错误：InvalidArgumentError: input_X:Y is both fed and fetched
多个输入的情况

您需要做以下更改：

outputs为变量中的输入层添加过滤器
functors循环中的细微变化

最小示例：

from keras.engine.input_layer import InputLayer
inp = model.input
outputs = [layer.output for layer in model.layers if not isinstance(layer, InputLayer)]
functors = [K.function(inp + [K.learning_phase()], [x]) for x in outputs]
layer_outputs = [fun([x1, x2, xn, 1]) for fun in functors]

解决方案 12：

一般来说，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

另一个更漂亮的表述：

美化后的等式