We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent a86f344 commit 543f1b4Copy full SHA for 543f1b4
docs/chapter06_RNN/6.5_rnn-pytorch.md
@@ -36,7 +36,7 @@ rnn_layer = nn.RNN(input_size=vocab_size, hidden_size=num_hiddens)
36
<div align=center>循环神经网络(以LSTM为例)的输出</div>
37
38
39
-来看看我们的例子,输出形状为(时间步数, 批量大小, 输入个数),隐藏状态h的形状为(层数, 批量大小, 隐藏单元个数)。
+来看看我们的例子,输出形状为(时间步数, 批量大小, 隐藏单元个数),隐藏状态h的形状为(层数, 批量大小, 隐藏单元个数)。
40
41
``` python
42
num_steps = 35
0 commit comments