这是我的模型代码:

encoder = Embedding(input_dim=dataset.shape[0],output_dim=300, mask_zero=True, input_length=12,embeddings_initializer='uniform')encoder = LSTM(epochs, input_shape=(train_X.shape[1], train_X.shape[2]), return_sequences=True, unroll=True)encoder_last = encoder[:,-1,:]

我遇到了以下错误:

---------------------------------------------------------------------------TypeError                                 Traceback (most recent call last)<ipython-input-88-3967dfedaa44> in <module>      1 encoder = Embedding(input_dim=dataset.shape[0],output_dim=300, mask_zero=True, input_length=12,embeddings_initializer='uniform')      2 encoder = LSTM(epochs, input_shape=(train_X.shape[1], train_X.shape[2]), return_sequences=True, unroll=True)----> 3 encoder_last = encoder[:,-1,:]TypeError: 'LSTM' object is not subscriptable

我该如何修复这个问题?

回答：

我想你是要将LSTM层应用于Embedding层的输出，然后取LSTM的最后一个输出。因此，首先你需要调用（即应用）你定义的层到某些张量（即某个层的输出）上，像这样:

inp = Input(shape=...)encoder = Embedding(...)(inp)  # 在输入上调用嵌入层encoder = LSTM(...)(encoder)   # 在嵌入层的输出上调用LSTM层

这样，层之间就连接起来了。然后你需要使用Lambda层来切片LSTM层的输出:

encoder_last = Lambda(lambda x: x[:,-1,:])(encoder)