无法加载微调权重Keras与ResNet50

Question

我第一次使用冻结在我的数据集ResNet50层训练有素以下：

model_r50 = ResNet50(weights='imagenet', include_top=False) 
model_r50.summary() 

input_layer = Input(shape=(img_width,img_height,3),name = 'image_input') 

output_r50 = model_r50(input_layer) 

fl = Flatten(name='flatten')(output_r50) 
dense = Dense(1024, activation='relu', name='fc1')(fl) 
drop = Dropout(0.5, name='drop')(dense) 
pred = Dense(nb_classes, activation='softmax', name='predictions')(drop) 
fine_model = Model(outputs=pred,inputs=input_layer) 
for layer in model_r50.layers: 
    layer.trainable = False 
    print layer 

fine_model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy']) 
fine_model.summary() 

然后我尝试微调其与层使用解冻如下：

model_r50 = ResNet50(weights='imagenet', include_top=False) 
model_r50.summary() 

input_layer = Input(shape=(img_width,img_height,3),name = 'image_input') 

output_r50 = model_r50(input_layer) 

fl = Flatten(name='flatten')(output_r50) 
dense = Dense(1024, activation='relu', name='fc1')(fl) 
drop = Dropout(0.5, name='drop')(dense) 
pred = Dense(nb_classes, activation='softmax', name='predictions')(drop) 
fine_model = Model(outputs=pred,inputs=input_layer) 
weights = 'val54_r50.01-0.86.hdf5' 
fine_model.load_weights('models/'+weights) 
fine_model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy']) 
fine_model.summary() 

但我从这个地方得到这个错误。我只是解冻网络，并没有改变任何东西！

load_weights_from_hdf5_group(f, self.layers) 
    File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 3008, in load_weights_from_hdf5_group 
    K.batch_set_value(weight_value_tuples) 
    File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 2189, in batch_set_value 
    get_session().run(assign_ops, feed_dict=feed_dict) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 778, in run 
    run_metadata_ptr) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 961, in _run 
    % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape()))) 
ValueError: Cannot feed value of shape (128,) for Tensor u'Placeholder_140:0', which has shape '(512,)' 

而且不一致。大部分时间我都会有不同的形状。这是为什么发生？如果我只是将ResNet更改为VGG19，则不会发生这种情况。 Keras中的ResNet有问题吗？

Answer 1

你的fine_model是Model与其中的另一个Model（即ResNet50）。看来问题是save_weight()和load_weight()无法正确处理这种类型的嵌套Model。

也许你可以尝试以不会导致“嵌套Model”的方式构建模型。例如，

input_layer = Input(shape=(img_width, img_height, 3), name='image_input') 
model_r50 = ResNet50(weights='imagenet', include_top=False, input_tensor=input_layer) 
output_r50 = model_r50.output 
fl = Flatten(name='flatten')(output_r50) 
...