Question

我试图在Tf-learn中创建一个多层LSTM而没有成功。

这样做

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)

我会得到一个列表作为a的输出和训练时的错误：

  /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中进行多层LSTM的正确方法是什么？

Answer 1

你解决了吗？如果没有，试试这个：

.NOTPARALLEL:

T-f中的多层LSTM了解

1 个答案: