假设这是我的模型:
_________________________________________________________________
Layer (type) Output Shape Param # =================================================================
embedding_16 (Embedding) (None, 10, 500) 71500 _________________________________________________________________
lstm_31 (LSTM) (None, 10, 500) 2002000 _________________________________________________________________
dropout_15 (Dropout) (None, 10, 500) 0 _________________________________________________________________
time_distributed_16 (None, 10, 500) 250500 _________________________________________________________________
softmax (Activation) (None, 10, 500) 0 =================================================================
但是我想进入最后一层:
softmax (Activation) (None, 100, 1000) 0
我已经尝试了几个小时。我不知道这是否可行。我不认为您可以更改LSTM的输出大小(看一下它的模型),但是我是否可以添加一个图层,以便每个输入生成10个输出?
简单地说,假设我想让我的模型为我输入的每个单词生成10个单词。希望我能解释一下。