Keras,如何获得每一层的输出？

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一样获得每一层的输出,我该怎么做？

1> indraforyou..：

---

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

对于所有图层使用此:

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:为了模拟差使用learning_phase如1.在layer_outs以其它方式使用0.

编辑:(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K.learning_phase()需要作为输入,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而优化的,数据将被转移到CPU-> GPU内存,并且还需要对下层n-over进行张量计算.

相反,这是一个更好的方法,因为您不需要多个函数,但只有一个函数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

---

先生，您的回答很好，您的代码中的`K.function（[inp] + [K.learning_phase（）]，[out]）`是什么意思？

---

@StavBodik模型使用`K.function` [此处]（https://github.com/keras-team/keras/blob/master/keras/engine/training.py#L1007-L1011）构建预测函数，并进行预测在[此处]（https://github.com/keras-team/keras/blob/master/keras/engine/training.py#L1800-L1803）的预测循环中使用它。Predict遍历批处理大小（如果未设置，则默认为32），但这可以减轻对GPU内存的限制。所以我不确定为什么您观察`model.predict`会更快。

2> blue-sky..：

---

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,该函数将在给定特定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]

3> Philippe Rem..：

---

基于此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

希望能帮助到你！

4> Miladiouss..：

---

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')

5> 小智..：

---

以下对我来说看起来很简单：

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，获得形状 model.layers[idx].output.get_shape()

idx 是图层的索引，您可以从中找到它 model.summary()