Skip to content

[Fix]: Fix optimizer 'ValueError' when using PReLU activation. #2444

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 3 commits into from
Dec 6, 2022
Merged

[Fix]: Fix optimizer 'ValueError' when using PReLU activation. #2444

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4290c68
fix optimizer ValueError when using PReLU activation.
KeiChiTse Nov 22, 2022
847e8e6
Merge branch '2.x' of github.com:open-mmlab/mmcv into fix-ffn-build-act
KeiChiTse Nov 22, 2022
5be3818
fix lint error
KeiChiTse Nov 22, 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
9 changes: 3 additions & 6 deletions mmcv/cnn/bricks/transformer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -588,24 +588,21 @@ def __init__(self,
ffn_drop=0.,
dropout_layer=None,
add_identity=True,
init_cfg=None,
**kwargs):
init_cfg=None):
super().__init__(init_cfg)
assert num_fcs >= 2, 'num_fcs should be no less ' \
f'than 2. got {num_fcs}.'
self.embed_dims = embed_dims
self.feedforward_channels = feedforward_channels
self.num_fcs = num_fcs
self.act_cfg = act_cfg
self.activate = build_activation_layer(act_cfg)

layers = []
in_channels = embed_dims
for _ in range(num_fcs - 1):
layers.append(
Sequential(
Linear(in_channels, feedforward_channels), self.activate,
nn.Dropout(ffn_drop)))
Linear(in_channels, feedforward_channels),
build_activation_layer(act_cfg), nn.Dropout(ffn_drop)))
in_channels = feedforward_channels
layers.append(Linear(feedforward_channels, embed_dims))
layers.append(nn.Dropout(ffn_drop))
Expand Down