tensorflow - T-fLearn 中的多层 LSTM

Question

我试图在 Tf-learn 中创建一个多层 LSTM，但没有成功。

这样做时

a = tflearn.lstm(_input, dropout=0.8, n_units=200, return_seq=True, dynamic=True)
b = tflearn.lstm(a, dropout=0.8, n_units=200, return_seq=False, dynamic=True)

我将得到一个列表作为输出a和训练时的错误：

  /usr/local/lib/python2.7/distpackages/tensorflow/python/ops/gradients.py:90: UserWarning: 
 Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
 "Converting sparse IndexedSlices to a dense Tensor of unknown shape. "

在 Tf-learn 中做多层 LSTM 的正确方法是什么？

Answer 1

你解决了吗？如果没有，试试这个：

a = tflearn.lstm(_input, 200)
b = tflearn.dropout(a, 0.8)
c = tflearn.lstm(b, 200)
d = tflearn.dropout(c, 0.8)