是否可以在激活功能之前获取VGG19的conv4_1层的激活前输出？
Keras Applications的VGG19网络具有以下层：
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
_________________________________________________________________
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv4 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
_________________________________________________________________
block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
_________________________________________________________________
block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_conv4 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
_________________________________________________________________
block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv4 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
_________________________________________________________________
flatten (Flatten) (None, 25088) 0
_________________________________________________________________
fc1 (Dense) (None, 4096) 102764544
_________________________________________________________________
fc2 (Dense) (None, 4096) 16781312
_________________________________________________________________
predictions (Dense) (None, 1000) 4097000
=================================================================
Total params: 143,667,240
Trainable params: 143,667,240
Non-trainable params: 0
我假设这些输出是激活后（relu）。
答案 0 :(得分：1)
是的，是的，激活功能内置于此处的层中，因此除非您愿意做一些工作，否则您不能在激活之前访问输出：
首先，精确复制要观察其输出的图层，只需省略激活功能即可。如果我对您的理解正确，那么您需要block4_conv1，它的索引为12。检查它的配置是这样的：
>>> vgg.layers[12].name
'block4_conv1'
>>> vgg.layers[12].filters
512
>>> vgg.layers[12].kernel_size
(3, 3)
>>> vgg.layers[12].padding
'same'
创建此层的副本而不激活：
block4_conv1_copy = Conv2D(filters=512, kernel_size=(3, 3), padding='same')
现在，创建一个包含所有vgg层0-11以及第12层副本的新模型：
injection_model = Sequential(vgg.layers[:12] + [block4_conv1_copy])
injection_model.summary()
这应该产生
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv4 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 28, 28, 512) 1180160
=================================================================
Total params: 3,505,728
Trainable params: 3,505,728
Non-trainable params: 0
_________________________________________________________________
现在block4_conv1_copy知道其输入形状，这是设置权重所必需的：
block4_conv1_copy.set_weights(vgg.layers[12].get_weights())
应该的！只需调用injection_model.predict(some_input)，您就可以在激活之前观察第12层的输出。