Skip to content

fix pytorch_default_init() #819

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
Dec 12, 2024
Merged

fix pytorch_default_init() #819

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
86d2a0d
Merge pull request #812 from mlcommons/dev
priyakasimbeg Nov 22, 2024
579a485
fix pytorch_default_init()
EIFY Nov 26, 2024
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
2 changes: 1 addition & 1 deletion algorithmic_efficiency/init_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,6 @@ def pytorch_default_init(module: nn.Module) -> None:
# Perform lecun_normal initialization.
fan_in, _ = nn.init._calculate_fan_in_and_fan_out(module.weight)
std = math.sqrt(1. / fan_in) / .87962566103423978
nn.init.trunc_normal_(module.weight, std=std)
nn.init.trunc_normal_(module.weight, std=std, a=-2 * std, b=2 * std)
if module.bias is not None:
nn.init.constant_(module.bias, 0.)
Loading