ValueError: You are trying to load a weight file containing 14 layers into a model with 3 layers

Question

（我找不到以前提出的问题的解决方案。）我使用 VGG16 来测试我的数据。我的 class 数字是 2，我使用 this page 冻结转换层并训练顶层。这是代码：

from keras.applications import VGG16
model = VGG16(include_top=False,classes=2,input_shape(224,224,3),weights='imagenet')

然后我创建了 top_model，它将成为我的 Vgg16 的顶级模型：

top_model=Sequential()
top_model.add(Flatten(input_shape=model.output_shape[1:]))
top_model.add(Dense(4096,activation='relu'))
top_model.add(Dense(4096,activation='relu'))
top_model.add(Dense(2,activation='softmax'))
model= Model(inputs=model.input, output=top_model(model.output))

然后我冻结了一些图层并编译了模型：

for layer in model.layers[:19]:
 layer.trainable=False

model.compile(loss='binary_crossentropy',optimizer=optimizers.SGD(lr=1e-4, momentum=0.9),
           metrics=['accuracy'])

经过一些数据增强过程后，我训练了模型并像这样保存了权重：

model.fit_generator(trainGenerator,samples_per_epoch=numTraining//batchSize,
                  epochs=numEpoch,
                  validation_data=valGenerator,
                  validation_steps=numValid//batchSize)

model.save_weights('top3_weights.h5')

之后，我的权重被保存，我更改了代码的第二部分以便能够用我的数据测试整个模型：

model = VGG16(include_top=False,classes=2,input_shape=(224,224,3),weights='imagenet')

top_model=Sequential()
top_model.add(Flatten(input_shape=model.output_shape[1:]))
top_model.add(Dense(4096,activation='relu'))
top_model.add(Dense(4096,activation='relu'))
top_model.add(Dense(2,activation='softmax'))
top_model.load_weights(r'C:\Users\Umit Kilic\Komodomyfiles\umit\top3_weights.h5') #(this line is added)
model= Model(inputs=model.input, output=top_model(model.output))

最后，当我尝试用代码总结模型时：

print(model.summary())

我收到错误和输出：

Using TensorFlow backend.
Traceback (most recent call last):
  File "C:\Users\Umit Kilic\Komodomyfiles\umit\test_vgg16.py", line 38, in <module>
    top_model.load_weights(r'C:\Users\Umit Kilic\Komodomyfiles\umit\top3_weights.h5')
  File "C:\Users\Umit Kilic\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\network.py", line 1166, in load_weights
f, self.layers, reshape=reshape)
  File "C:\Users\Umit Kilic\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\saving.py", line 1030, in load_weights_from_hdf5_group
str(len(filtered_layers)) + ' layers.')
ValueError: You are trying to load a weight file containing 14 layers into a model with 3 layers.

有什么帮助吗？

Answer 1

model包含完整模型，即VGG的堆叠模型加上top_model。当你保存它的重量时，它有 14 层。您不能在 top_model 中加载它，因为 VGG 权重也在其中，但您可以在新的 model.

中加载它

model = VGG16(include_top=False,classes=2,input_shape=(224,224,3),weights='imagenet')
top_model=Sequential()
top_model.add(Flatten(input_shape=model.output_shape[1:])) 
top_model.add(Dense(4096,activation='relu'))
top_model.add(Dense(4096,activation='relu'))
top_model.add(Dense(2,activation='softmax'))
model= Model(inputs=model.input, output=top_model(model.output))

model.load_weights(r'C:\Users\Umit Kilic\Komodomyfiles\umit\top3_weights.h5') #(this line is added)

ValueError: You are trying to load a weight file containing 14 layers into a model with 3 layers

ValueError: You are trying to load a weight file containing 14 layers into a model with 3 layers

python

keras

tensorflow

pre-trained-model

valueerror