我试图删除最后一层,以便我可以使用转移学习。
vgg16_model = keras.applications.vgg16.VGG16()
model = Sequential()
for layer in vgg16_model.layers:
model.add(layer)
model.layers.pop()
# Freeze the layers
for layer in model.layers:
layer.trainable = False
# Add 'softmax' instead of earlier 'prediction' layer.
model.add(Dense(2, activation='softmax'))
# Check the summary, and yes new layer has been added.
model.summary()
但我得到的输出并不是我的预期。它仍然显示最后一层vgg16模型。
这是输出
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
**THE HIDDEN LAYERS**
_________________________________________________________________
fc1 (Dense) (None, 4096) 102764544
_________________________________________________________________
fc2 (Dense) (None, 4096) 16781312
_________________________________________________________________
predictions (Dense) (None, 1000) 4097000
_________________________________________________________________
dense_10 (Dense) (None, 2) 2002
=================================================================
Total params: 138,359,546
Trainable params: 2,002
Non-trainable params: 138,357,544
注意 - 在输出中我没有显示整个模型,只显示了前几层和最后一层。
我应该如何删除最后一层做转移学习?
P.S硬版本= 2.2.4
首先,不要将最后一层添加到模型中。这样你甚至不需要pop
vgg16_model = keras.applications.vgg16.VGG16()
model = Sequential()
for layer in vgg16_model.layers[:-1]: # this is where I changed your code
model.add(layer)
# Freeze the layers
for layer in model.layers:
layer.trainable = False
# Add 'softmax' instead of earlier 'prediction' layer.
model.add(Dense(2, activation='softmax'))
作为markuscosinus答案的替代方案,您可以在预测图层之前获取输出并将其传递给您自己的预测图层。你可以这样做:
for layer in vgg16_model.layers:
layer.trainable = False
last_layer = vgg16_model.get_layer('fc2').output
out = Flatten()(last_layer)
out = Dense(128, activation='relu', name='fc3')(out)
out = Dropout(0.5)(out)
out = Dense(n_classes, activation='softmax', name='prediction')(out)
vgg16_custom_model = Model(input=vgg16_model.input, output=out)
我建议你在softmax之前添加一个Flatten和另一个Dense图层,因为最后一个“fc2”有4096个节点,很难将它改为2。
当然,在预测之前退出会给你更好的结果。