tensorflow - Keras错误 “You must feed a value for placeholder tensor ' bidirectional_1/keras_learning_phase'与dtype bool”

对于以下代码段，出现以下错误:



如果我添加辍学层model.add(Dropout(dropout))，它可以工作。有人知道为什么吗？后端是Tensorflow，Keras 2.0.1

def prep_model1(embedding_layer1, embedding_layer2, dropout=0.5):

    model0 = Sequential()
    model0.add(embedding_layer1)
    model0.add(Bidirectional(LSTM(128, return_sequences=False, dropout=dropout)))

    model1 = Sequential()
    model1.add(embedding_layer2)
    model1.add(Bidirectional(LSTM(128, return_sequences=False, dropout=dropout)))

    model = Sequential()
    model.add(Merge([model0, model1], mode='concat', concat_axis=1))
    #model.add(Dropout(dropout))
    model.add(Dense(1, activation='sigmoid'))

    return model

最佳答案

尝试在模型之前导入K并设置学习阶段。

from keras import backend as K

K.set_learning_phase(1) #set learning phase

从this issue

关于tensorflow - Keras错误 “You must feed a value for placeholder tensor ' bidirectional_1/keras_learning_phase'与dtype bool”，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/42969779/