Keras，如何获得每一层的输出？

Question

我已经用 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))

在这里，我想像 TensorFlow 一样获取每一层的输出，我该怎么做？

Answer 1

您可以使用以下命令轻松获取任何层的输出：model.layers[index].output

所有层都使用这个：

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，在 layer_outs 中使用 learning_phase 作为 1.，否则使用 0.

编辑：（基于 cmets）

K.function 创建 theano/tensorflow 张量函数，稍后用于在给定输入的情况下从符号图中获取输出。

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

因此，如果您删除代码中的 dropout 层，您可以简单地使用：

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，之前的答案并没有优化，因为对于每个函数评估，数据将被传输到 CPU->GPU 内存，并且还需要对较低层进行张量计算。

相反，这是一种更好的方法，因为您不需要多个函数，而是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

Answer 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，该模型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，您可以构建一个 Keras 函数，该函数将在给定特定输入的情况下返回特定层的输出，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]

Answer 3

基于这个线程的所有好的答案，我编写了一个库来获取每一层的输出。它抽象了所有的复杂性，并被设计为尽可能用户友好：

https://github.com/philipperemy/keract

它处理几乎所有的边缘情况。

希望对你有帮助！

Answer 4

对我来说，以下看起来很简单：

model.layers[idx].output

上面是张量对象，因此您可以使用可应用于张量对象的操作对其进行修改。

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

idx是层的索引，你可以从model.summary()找到它

Answer 5

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

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)

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)

Answer 6

我为自己（在 Jupyter 中）编写了这个函数，它的灵感来自 indraforyou 的回答。它将自动绘制所有图层输出。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(...) 即可进行绘图。

%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='\n-------------------\n')
        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')

Answer 7

发件人：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

Answer 8

想将此作为评论（但没有足够高的代表）添加到@indraforyou 的答案中，以纠正@mathtick 评论中提到的问题。为避免InvalidArgumentError: input_X:Y is both fed and fetched. 异常，只需将outputs = [layer.output for layer in model.layers] 行替换为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

附言我尝试尝试诸如outputs = [layer.output for layer in model.layers[1:]] 之类的东西没有奏效。

Answer 9

以前的解决方案对我不起作用。我处理了这个问题，如下所示。

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)

Answer 10

假设你有：

1- Keras 预训练 model。

2- 输入x 作为图像或图像集。图像的分辨率应与输入层的尺寸兼容。例如 80*80*3 用于 3 通道 (RGB) 图像。

3- 输出名称layer 以获得激活。例如，“flatten_2”图层。这应该包含在layer_names 变量中，表示给定model 的图层名称。

4- batch_size 是一个可选参数。

然后你可以很容易地使用get_activation 函数来激活输出layer 对于给定的输入x 和预训练的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

Answer 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

您需要进行以下更改：

• 为outputs变量中的输入层添加过滤器
• functors 循环的微小变化

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]

Answer 12

嗯，其他答案都非常完整，但是有一个非常基本的方法来“看到”，而不是“得到”形状。

只需做一个model.summary()。它将打印所有图层及其输出形状。 “无”值表示可变维度，第一个维度将是批量大小。