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.

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

Add light-weight MLP #372

Merged
merged 11 commits into from
Mar 8, 2024
Merged

Add light-weight MLP #372

merged 11 commits into from
Mar 8, 2024

Conversation

weihua916
Copy link
Contributor

No description provided.

@github-actions github-actions bot added the nn label Mar 6, 2024
@weihua916 weihua916 self-assigned this Mar 6, 2024
Copy link

codecov bot commented Mar 6, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 93.52%. Comparing base (94bf7a3) to head (dbc4ee1).

Additional details and impacted files
@@            Coverage Diff             @@
##           master     #372      +/-   ##
==========================================
+ Coverage   93.45%   93.52%   +0.06%     
==========================================
  Files         122      124       +2     
  Lines        6401     6451      +50     
==========================================
+ Hits         5982     6033      +51     
+ Misses        419      418       -1     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@weihua916 weihua916 requested review from rusty1s and yiweny March 7, 2024 03:33
torch_frame/nn/models/mlp.py Outdated Show resolved Hide resolved
@weihua916 weihua916 merged commit 893678f into master Mar 8, 2024
14 checks passed
@weihua916 weihua916 deleted the mlp branch March 8, 2024 05:16
)

self.mlp = Sequential()
norm_cls = LayerNorm if normalization == "layernorm" else BatchNorm1d
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You don't respect no normalization here.

Comment on lines +97 to +98
if (isinstance(param, Linear) or isinstance(param, BatchNorm1d)
or isinstance(param, LayerNorm)):
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

if hasattr(self, 'reset_parameters'):

channels (int): The number of channels in the backbone layers.
out_channels (int): The number of output channels in the decoder.
num_layers (int): The number of layers in the backbone.
col_stats(dict[str,Dict[:class:`torch_frame.data.stats.StatType`,Any]]):
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

missing white space.

weihua916 added a commit that referenced this pull request Mar 14, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants