如何解决LSTM自动编码器目标形状问题
我尝试运行自动编码器LSTM的示例，但是代码不一致并且发生错误：
print(f'X Training shape: {X_train.shape}')
print(f'X Testing shape: {X_test.shape}')
model = Sequential()
model.add(LSTM(128,return_sequences=False,input_shape=(X_train.shape[1],X_train.shape[2])))
model.add(Dropout(rate=0.2))
model.add(RepeatVector(X_train.shape[1]))
model.add(LSTM(128,return_sequences=True))
model.add(Dropout(rate=0.2))
model.add(Timedistributed(Dense(X_train.shape[2])))
model.compile(optimizer='adam',loss='mae')
model.summary()
history = model.fit(X_train,y_train,epochs=1,batch_size=32,validation_split=0.1,callbacks=[keras.callbacks.EarlyStopping(monitor='val_loss',patience=3,mode='min')],shuffle=False)
X Training shape: (7029,30,1)
X Testing shape: (1734,1)
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
lstm_46 (LSTM) (None,128) 66560
_________________________________________________________________
dropout_46 (Dropout) (None,128) 0
_________________________________________________________________
repeat_vector_26 (RepeatVect (None,128) 0
_________________________________________________________________
lstm_47 (LSTM) (None,128) 131584
_________________________________________________________________
dropout_47 (Dropout) (None,128) 0
_________________________________________________________________
time_distributed_20 (Timedis (None,1) 129
=================================================================
Total params: 198,273
Trainable params: 198,273
Non-trainable params: 0
_________________________________________________________________
...
ValueError: Error when checking target: expected time_distributed_22 to have shape (30,1) but got array with shape (1,1)
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。
