Skip to content

Resolving tracing problem on StochasticDepth iterator #4372

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Sep 6, 2021
Merged

Resolving tracing problem on StochasticDepth iterator #4372

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4584807
Resolving tracing problem on StochasticDepth iterator.
datumbox Sep 6, 2021
cf4b29c
Merge branch 'main' into bugs/tracing_stochasticdepth
fmassa Sep 6, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions torchvision/ops/stochastic_depth.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,9 +28,10 @@ def stochastic_depth(input: Tensor, p: float, mode: str, training: bool = True)
return input

survival_rate = 1.0 - p
size = [1] * input.ndim
if mode == "row":
size[0] = input.shape[0]
size = [input.shape[0]] + [1] * (input.ndim - 1)
else:
size = [1] * input.ndim
noise = torch.empty(size, dtype=input.dtype, device=input.device)
noise = noise.bernoulli_(survival_rate).div_(survival_rate)
return input * noise
Expand Down