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

[docs] Add usage examples to ConvTranspose1d docstring (#165618)

Browse Source 
Fixes #165615

Pull Request resolved: https://github.com/pytorch/pytorch/pull/165618
Approved by: https://github.com/mikaylagawarecki
This commit is contained in:
vishalgoyal316
2025-10-17 19:11:52 +00:00
committed by PyTorch MergeBot
parent a664b299ac
commit 382b0150de
1 changed files with 17 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
torch/nn/modules/conv.py
View File

@ -901,6 +901,23 @@ class ConvTranspose1d(_ConvTransposeNd):
sampled from :math:`\mathcal{U}(-\sqrt{k}, \sqrt{k})` where
:math:`k = \frac{groups}{C_\text{out} * \text{kernel\_size}}`
Examples::
>>> # With square kernels and equal stride
>>> m = nn.ConvTranspose1d(16, 33, 3, stride=2)
>>> input = torch.randn(20, 16, 50)
>>> output = m(input)
>>> # exact output size can be also specified as an argument
>>> input = torch.randn(1, 16, 12)
>>> downsample = nn.Conv1d(16, 16, 3, stride=2, padding=1)
>>> upsample = nn.ConvTranspose1d(16, 16, 3, stride=2, padding=1)
>>> h = downsample(input)
>>> h.size()
torch.Size([1, 16, 6])
>>> output = upsample(h, output_size=input.size())
>>> output.size()
torch.Size([1, 16, 12])
.. _`here`:
https://github.com/vdumoulin/conv_arithmetic/blob/master/README.md