我正在尝试在Keras中实现一个卷积自编码器，其中的层类似于下面这样。我的数据有1108行和29430列。

def build(features, embedding_dims, maxlen, filters, kernel_size):    m = keras.models.Sequential()    m.add(Embedding(features, embedding_dims, input_length=maxlen))    m.add(Dropout(0.2))    m.add(Conv1D(filters, kernel_size, padding='valid', activation='relu', strides=1, input_shape=(len(xx), features) ))    m.add(MaxPooling1D())    m.add(Conv1D(filters, kernel_size, padding='valid', activation='relu', strides=1, input_shape=(None, len(xx), features) ))    m.add(UpSampling1D())    m.summary()    m.compile(optimizer="adagrad", loss='mse', metrics=['accuracy'])    return mearly = keras.callbacks.EarlyStopping(        monitor='val_loss', patience=10, verbose=1, mode='min')model = build(len(xx[0]), 60, 11900, 70, 3)model.fit(xx, xx, batch_size=4000, nb_epoch=10000,validation_split=0.1,     callbacks=[early])

然而，我收到一个错误，显示ValueError: Error when checking input: expected embedding_1_input to have shape (None, 11900) but got array with shape (1108, 29430)。为什么第一层会期望形状为(None, maxlen)，而不是数据的实际大小呢？

我还会展示我的模型摘要：

_________________________________________________________________Layer (type)                 Output Shape              Param #   =================================================================embedding_1 (Embedding)      (None, 11900, 60)         714000    _________________________________________________________________dropout_1 (Dropout)          (None, 11900, 60)         0         _________________________________________________________________conv1d_1 (Conv1D)            (None, 11898, 70)         12670     _________________________________________________________________max_pooling1d_1 (MaxPooling1 (None, 5949, 70)          0         _________________________________________________________________conv1d_2 (Conv1D)            (None, 5947, 70)          14770     _________________________________________________________________up_sampling1d_1 (UpSampling1 (None, 11894, 70)         0         =================================================================Total params: 741,440Trainable params: 741,440Non-trainable params: 0_________________________________________________________________

回答：

我通过在Embedding层中添加input_shape字段解决了这个特定错误，如下所示：

m.add(Embedding(features, embedding_dims, input_length=maxlen, input_shape=(features, ) ))

features是特征的数量（29430）。