Skip to content
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

Fix graphgym example for activation functions #5243

Merged
merged 9 commits into from
Aug 20, 2022
Merged

Fix graphgym example for activation functions #5243

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
b4dffc6
Fix graphgym example for activation functions
M-Lampert Aug 19, 2022
9c2f7a8
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Aug 19, 2022
7f8e93c
Added changelog entry
M-Lampert Aug 19, 2022
123ab53
Apply suggestions from code review
Padarn Aug 20, 2022
10113b9
revert graphgym/custom_graphgym/act/example.py
Padarn Aug 20, 2022
5e2141f
Move and modify changelog entry
M-Lampert Aug 20, 2022
1e53027
Merge branch 'master' into fix-graphgym-example-activations
Aug 20, 2022
1a738c4
Use lambda to register one activation
Aug 20, 2022
a350d9a
Update graphgym/custom_graphgym/act/example.py
Padarn Aug 20, 2022
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
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,5 +158,6 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
- Fixed a bug in which `nn.models.GAT` did not produce `out_channels`-many output channels ([#4299](https://github.com/pyg-team/pytorch_geometric/pull/4299))
- Fixed mini-batching with empty lists as attributes ([#4293](https://github.com/pyg-team/pytorch_geometric/pull/4293))
- Fixed a bug in which `GCNConv` could not be combined with `to_hetero` on heterogeneous graphs with one node type ([#4279](https://github.com/pyg-team/pytorch_geometric/pull/4279))
- Fixed a bug in which the custom activation functions in GraphGym did not work. ([#5243](https://github.com/pyg-team/pytorch_geometric/pull/5243))
### Removed
- Remove internal metrics in favor of `torchmetrics` ([#4287](https://github.com/pyg-team/pytorch_geometric/pull/4287))
6 changes: 4 additions & 2 deletions graphgym/custom_graphgym/act/example.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
from functools import partial

import torch
import torch.nn as nn

Expand All @@ -18,5 +20,5 @@ def forward(self, x):
return x * torch.sigmoid(x)


register_act('swish', SWISH(inplace=cfg.mem.inplace))
register_act('lrelu_03', nn.LeakyReLU(0.3, inplace=cfg.mem.inplace))
register_act('swish', lambda: SWISH(inplace=cfg.mem.inplace))
register_act('lrelu_03', partial(nn.LeakyReLU, 0.3, inplace=cfg.mem.inplace))