projects / platform / upstream / pytorch.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: ba8c1fc) | patch
Change MaxUnpool to accept tensors with 0-dim batch sizes. (#64082)
authorSameer Deshmukh <sameer.deshmukh93@gmail.com>
Wed, 8 Sep 2021 15:40:01 +0000 (08:40 -0700)
committerFacebook GitHub Bot <facebook-github-bot@users.noreply.github.com>
Wed, 8 Sep 2021 15:41:09 +0000 (08:41 -0700)
commit7205ca02107059443bddd14322d2b9ed8562c60b
treea4a4aac806eecea115bb964cc262f83eea590635tree | snapshot
parentba8c1fc64854b2c6b3c76244bd228d9e2c6f5682commit | diff
Change MaxUnpool to accept tensors with 0-dim batch sizes. (#64082)

Summary:
Part of the fix for https://github.com/pytorch/pytorch/issues/38115.

Changes the `MaxUnpool` module to work with 0-dimensions batch sizes.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/64082

Reviewed By: mrshenli

Differential Revision: D30793907

Pulled By: jbschlosser

fbshipit-source-id: d21aa665be5aa18f592b39ef7b4e3cbc632e21ed
aten/src/ATen/native/MaxUnpooling.cpp diff | blob | history
aten/src/ATen/native/cuda/MaxUnpooling.cu diff | blob | history
test/test_nn.py diff | blob | history
Domain: Machine Learning / ML Framework;