frozenleaves/pytorch
1
0
Fork 0
mirror of https://github.com/pytorch/pytorch.git synced 2025-10-20 21:14:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

Document the parameter (hx) that RNN actually uses (#140575)

Browse Source 
Fixes https://github.com/pytorch/pytorch/issues/136925

This PR updates the docs to use `hx`, which is the parameter actually used by `RNN`:

629c243c82/torch/nn/modules/rnn.py (L650)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/140575
Approved by: https://github.com/ezyang
This commit is contained in:
Thomas J. Fan
2024-11-14 14:45:17 +00:00
committed by PyTorch MergeBot
parent ebeab262d9
commit 1c669e7c4e
1 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
torch/nn/modules/rnn.py
View File

@ -482,14 +482,14 @@ class RNN(RNNBase):
.. code-block:: python
# Efficient implementation equivalent to the following with bidirectional=False
def forward(x, h_0=None):
def forward(x, hx=None):
if batch_first:
x = x.transpose(0, 1)
seq_len, batch_size, _ = x.size()
if h_0 is None:
h_0 = torch.zeros(num_layers, batch_size, hidden_size)
h_t_minus_1 = h_0
h_t = h_0
if hx is None:
hx = torch.zeros(num_layers, batch_size, hidden_size)
h_t_minus_1 = hx
h_t = hx
output = []
for t in range(seq_len):
for layer in range(num_layers):
@ -525,14 +525,14 @@ class RNN(RNNBase):
:attr:`dropout`. Default: 0
bidirectional: If ``True``, becomes a bidirectional RNN. Default: ``False``
Inputs: input, h_0
Inputs: input, hx
* **input**: tensor of shape :math:`(L, H_{in})` for unbatched input,
:math:`(L, N, H_{in})` when ``batch_first=False`` or
:math:`(N, L, H_{in})` when ``batch_first=True`` containing the features of
the input sequence. The input can also be a packed variable length sequence.
See :func:`torch.nn.utils.rnn.pack_padded_sequence` or
:func:`torch.nn.utils.rnn.pack_sequence` for details.
* **h_0**: tensor of shape :math:`(D * \text{num\_layers}, H_{out})` for unbatched input or
* **hx**: tensor of shape :math:`(D * \text{num\_layers}, H_{out})` for unbatched input or
:math:`(D * \text{num\_layers}, N, H_{out})` containing the initial hidden
state for the input sequence batch. Defaults to zeros if not provided.