Keras轉移學習與Resnet50失敗，異常

Question

我正在使用Resnet50做轉移學習。後端是張量流。 我試圖在RESNET疊放三個層，但失敗，以下錯誤：

Exception: The shape of the input to "Flatten" is not fully defined (got (None, None, 2048). 
Make sure to pass a complete "input_shape" or "batch_input_shape" argument to the first layer in your model. 

堆疊的代碼兩種型號如下：

model = ResNet50(include_top=False, weights='imagenet') 

top_model = Sequential() 
top_model.add(Flatten(input_shape=model.output_shape[1:])) 
top_model.add(Dense(256, activation='relu')) 
top_model.add(Dropout(0.5)) 
top_model.add(Dense(1, activation='sigmoid')) 
top_model.load_weights(top_model_weights_path) 

model = Model(input=model.input, output=top_model(model.output)) 

Answer 1

RESNET與include_top最後一層= False選項已經變平並且不需要另一個平坦化層。

Answer 2

在實例化Resnet時，您必須顯式地使用input_shape。 model = ResNet50(include_top=False, weights='imagenet',input_shape=(224,224,3))

如果您有theano作爲後端必須設置爲第一頻道的數量： model = ResNet50(include_top=False, weights='imagenet',input_shape=(3,224,224))