keras LSTM 模型输入和输出维度不匹配

Question

model = Sequential()

    model.add(Embedding(630, 210))
    model.add(LSTM(1024, dropout = 0.2, return_sequences = True))
    model.add(LSTM(1024, dropout = 0.2, return_sequences = True))
    model.add(Dense(210, activation = 'softmax'))

    model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])

    filepath = 'ner_2-{epoch:02d}-{loss:.5f}.hdf5'
    checkpoint = ModelCheckpoint(filepath, monitor = 'loss', verbose = 1, save_best_only = True, mode = 'min')
    callback_list = [checkpoint]

    model.fit(X, y , epochs = 20, batch_size = 1024, callbacks = callback_list)

X：输入向量的形状为 (204564, 630, 1)

y：目标向量的形状为 (204564, 210, 1)

即对于每 630 个输入，必须预测 210 个输出，但代码在编译时抛出以下错误

ValueError                                Traceback (most recent call last)
<ipython-input-57-05a6affb6217> in <module>()
     50 callback_list = [checkpoint]
     51 
---> 52 model.fit(X, y , epochs = 20, batch_size = 1024, callbacks = callback_list)
     53 print('successful')



ValueError: Error when checking model input: expected embedding_8_input to have 2 dimensions, but got array with shape (204564, 630, 1)

请有人解释为什么会出现此错误以及如何解决此问题

Answer 1

消息说：

Your first layer expects an input with 2 dimensions: (BatchSize, SomeOtherDimension). But your input has 3 dimensions (BatchSize=204564,SomeOtherDimension=630, 1).

好吧...从您的输入中删除 1，或在模型中重塑它：

解决方案 1 - 从输入中删除它：

X = X.reshape((204564,630))

解决方案 2 - 添加重塑图层：

model = Sequential()
model.add(Reshape((630,),input_shape=(630,1)))
model.add(Embedding.....)

keras LSTM 模型输入和输出维度不匹配

keras LSTM model input and output dimensions mismatch

machine-learning

mismatch

python-3.x

deep-learning

keras

请有人解释为什么会出现此错误以及如何解决此问题