🐛 Describe the bug
Docs read that C is dropped, which does not occur for (C, H, W)
import torch
torch.manual_seed(0)
ipt = torch.ones((2, 3, 4))
print(torch.nn.Dropout2d(p=0.5)(ipt))
tensor([[[2., 2., 2., 2.],
[0., 0., 0., 0.],
[0., 0., 0., 0.]],
[[2., 2., 2., 2.],
[2., 2., 2., 2.],
[0., 0., 0., 0.]]])
but does for (N, C, H, W)
torch.manual_seed(0)
print(torch.nn.Dropout2d(p=0.5)(ipt[None]))
tensor([[[[2., 2., 2., 2.],
[2., 2., 2., 2.],
[2., 2., 2., 2.]],
[[0., 0., 0., 0.],
[0., 0., 0., 0.],
[0., 0., 0., 0.]]]])
It appears Dropout2d is instead implementing Dropout1d for (N, C, T).
Versions
1.10.0 via Anaconda; Windows 10
cc @ezyang @gchanan @zou3519 @bdhirsh @albanD @mruberry @jbschlosser @walterddr @kshitij12345
🐛 Describe the bug
Docs read that
Cis dropped, which does not occur for(C, H, W)but does for
(N, C, H, W)It appears
Dropout2dis instead implementingDropout1dfor(N, C, T).Versions
1.10.0 via Anaconda; Windows 10
cc @ezyang @gchanan @zou3519 @bdhirsh @albanD @mruberry @jbschlosser @walterddr @kshitij12345