Keras,如何获得每一层的输出?

时间:2017-01-18 04:07:17

标签: python tensorflow deep-learning keras

我已经使用CNN训练了二进制分类模型,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一样得到每一层的输出,我该怎么做?

12 个答案:

答案 0 :(得分:118)

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:

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,请在learning_phase中使用1.作为layer_outs,否则请使用0.

修改(根据评论)

K.function创建theano / tensorflow张量函数,稍后用于从给定输入的符号图获得输出。

现在需要K.learning_phase()作为输入,因为Dropout / Batchnomalization等许多Keras层依赖于它来改变训练和测试时间的行为。

因此,如果您删除代码中的dropout图层,则只需使用:

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

编辑2:更优化

我刚刚意识到前面的答案不是针对每个功能评估进行优化的,数据将被转移CPU-> GPU内存以及需要对下层n-over进行张量计算。

相反,这是一个更好的方法,因为您不需要多个功能,但只有一个功能可以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

答案 1 :(得分:67)

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,输出您感兴趣的图层:

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,该函数将在给定某个输入的情况下返回某个图层的输出,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]

答案 2 :(得分:7)

我为自己写了这个函数(在Jupyter中),它的灵感来自于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。你只需要调用plot_layer_outputs(...)来绘图。

%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')

答案 3 :(得分:4)

以下对我来说很简单:

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来修改它。

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

idx是图层的索引,您可以从model.summary()

中找到它

答案 4 :(得分:3)

嗯,其他答案非常完整,但有一种非常基本的方式来“看”,而不是“获得”形状。

做一个model.summary()。它将打印所有图层及其输出形状。 “无”值表示可变尺寸,第一个尺寸为批量大小。

答案 5 :(得分:3)

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

答案 6 :(得分:1)

想将此添加为@indraforyou的答案作为注释(但没有足够高的声望),以更正@mathtick注释中提到的问题。为避免出现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

适应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

p.s。我尝试尝试诸如outputs = [layer.output for layer in model.layers[1:]]之类的尝试没有成功。

答案 7 :(得分:1)

基于该线程的所有良好答案,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,并被设计为尽可能易于使用:

https://github.com/philipperemy/keract

它处理几乎所有边缘情况

希望有帮助!

答案 8 :(得分:1)

如果您遇到以下情况之一:

  • 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:

  • outputs变量中为输入图层添加过滤器
  • functors循环中进行最小更改

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]

答案 9 :(得分:0)

假设您拥有:

1- Keras经过预训练的x

2-输入layer作为图像或一组图像。图像的分辨率应与输入层的尺寸兼容。例如,用于3通道(RGB)图像的 80 * 80 * 3

3-要激活的输出layer_names的名称。例如,“ flatten_2”层。这应该包含在model变量中,代表给定batch_size的图层名称。

4- get_activation是一个可选参数。

然后,您可以轻松地使用layer函数来激活给定输入x和预先训练的model的输出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

{{1}}

答案 10 :(得分:0)

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

要打印单层的输出,请执行以下操作:

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)

答案 11 :(得分:0)

以前的解决方案对我不起作用。我按如下所示处理了此问题。

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)