微調Keras中的Inception_v3時的ValueError

我想微調Keras中的預先訓練的Inceptionv3中的多標籤（17）預測問題。微調Keras中的Inception_v3時的ValueError

下面的代碼：

# create the base pre-trained model 
base_model = InceptionV3(weights='imagenet', include_top=False) 

# add a new top layer 
x = base_model.output 
predictions = Dense(17, activation='sigmoid')(x) 

# this is the model we will train 
model = Model(inputs=base_model.input, outputs=predictions) 

# we need to recompile the model for these modifications to take effect 
# we use SGD with a low learning rate 
from keras.optimizers import SGD 
model.compile(loss='binary_crossentropy', # We NEED binary here, since categorical_crossentropy l1 norms the output before calculating loss. 
       optimizer=SGD(lr=0.0001, momentum=0.9)) 

# Fit the model (Add history so that the history may be saved) 
history = model.fit(x_train, y_train, 
      batch_size=128, 
      epochs=1, 
      verbose=1, 
      callbacks=callbacks_list, 
      validation_data=(x_valid, y_valid))

但我鑽進了以下錯誤消息，並且有麻煩破譯它是說：

ValueError: Error when checking target: expected dense_1 to have 4 dimensions, but got array with shape (1024, 17)

這似乎有事情做與它不不喜歡我爲標籤作爲目標的熱門編碼。但是，我如何獲得4個維度的目標？

來源

2017-06-13 Clark Chong

看來，https://stackoverflow.com/questions/41764041/fine-tuning-pretrained-model-in-keras可能有答案？ –

或者https://stackoverflow.com/questions/43386463/keras-vgg16-fine-tuning?rq=1 –

事實證明，從https://keras.io/applications/複製的代碼不能即裝即用。以下職位已經幫助我： Keras VGG16 fine tuning

我需要做的修改如下：

添加輸入形狀模型定義base_model = InceptionV3(weights='imagenet', include_top=False, input_shape=(299,299,3))，並
添加展平（）層以張化張量輸出： x = base_model.output x = Flatten()(x) predictions = Dense(17, activation='sigmoid')(x)

然後模型適合我！

來源

2017-06-14 01:19:29

微調Keras中的Inception_v3時的ValueError

回答

相關問題