路缘石致密层形状误差

我正在使用keras创建一个LSTM模型。在训练中,我犯了这个错误。

ValueError: Error when checking target: expected dense_4 to have shape (1,) but got array with shape (34,)

这是我的模型

model = Sequential()

model.add(Embedding(max_words, embedding_dim, input_length=maxlen))    
model.add(LSTM(128, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))

model.add(Dense(units = 34 ,activation='softmax'))

model.layers[0].set_weights([embedding_matrix])
model.layers[0].trainable = False

model.compile(optimizer='rmsprop',loss='sparse_categorical_crossentropy',metrics=['acc'])

模型摘要:

Layer (type)                 Output Shape              Param #   
=================================================================
embedding_2 (Embedding)      (None, 15, 50)            500000    
_________________________________________________________________
lstm_2 (LSTM)                (None, 128)               91648     
_________________________________________________________________
dense_3 (Dense)              (None, 64)                8256      
_________________________________________________________________
dropout_2 (Dropout)          (None, 64)                0         
_________________________________________________________________
dense_4 (Dense)              (None, 34)                2210      
=================================================================
Total params: 602,114
Trainable params: 102,114
Non-trainable params: 500,000
_________________________________________________________________

我叫fit

history = model.fit(X_train, y_train,epochs=100,batch_size=128)

y_train 是一个带有形状的热编码标签 (299, 34) . X_train 有型的 (299, 15) .

我不确定 为什么模型在寻找形状(1,)正如我所看到的 dense_4 (Dense) 输出形状为`(无,34)。