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

Jump to bottom

Add model: multilayer perceptrons. #226

Merged
merged 2 commits into from
Mar 25, 2021
Merged

Add model: multilayer perceptrons. #226

merged 2 commits into from
Mar 25, 2021

Conversation

Yshuo-Li
Copy link
Collaborator

Add multilayer perceptrons, which is the imnet model employed by LIIF.

@codecov
Copy link

codecov bot commented Mar 16, 2021 •
edited

Codecov Report

Merging #226 (85ec6f5) into master (ad517d4) will decrease coverage by 0.19%.
The diff coverage is 79.31%.

❗ Current head 85ec6f5 differs from pull request most recent head bf55d34. Consider uploading reports for the commit bf55d34 to get more accurate results
Impacted file tree graph

@@            Coverage Diff             @@
##           master     #226      +/-   ##
==========================================
- Coverage   81.69%   81.49%   -0.20%     
==========================================
  Files         149      150       +1     
  Lines        7102     7059      -43     
  Branches     1052     1056       +4     
==========================================
- Hits         5802     5753      -49     
- Misses       1179     1185       +6     
  Partials      121      121
Flag Coverage Δ
unittests 81.49% <79.31%> (-0.20%) ⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
mmedit/models/components/refiners/mlp_refiner.py 77.77% <77.77%> (ø)
mmedit/models/components/refiners/__init__.py 100.00% <100.00%> (ø)
...ackbones/encoder_decoders/pconv_encoder_decoder.py 43.47% <0.00%> (-2.36%) ⬇️
mmedit/models/base.py 82.75% <0.00%> (-2.09%) ⬇️
...ones/encoder_decoders/two_stage_encoder_decoder.py 53.84% <0.00%> (-1.16%) ⬇️
...dels/backbones/encoder_decoders/encoders/resnet.py 66.01% <0.00%> (-0.97%) ⬇️
...s/backbones/encoder_decoders/gl_encoder_decoder.py 81.48% <0.00%> (-0.67%) ⬇️
mmedit/datasets/pipelines/normalization.py 88.88% <0.00%> (-0.59%) ⬇️
mmedit/models/mattors/base_mattor.py 81.72% <0.00%> (-0.58%) ⬇️
mmedit/models/mattors/indexnet.py 84.37% <0.00%> (-0.48%) ⬇️
... and 19 more

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update ad517d4...bf55d34. Read the comment docs.

innerlee
innerlee reviewed Mar 17, 2021
View reviewed changes
mmedit/models/components/refiners/mlp.py Outdated
logger = get_root_logger()
load_checkpoint(self, pretrained, strict=strict, logger=logger)
elif pretrained is None:
pass
Copy link
Contributor

Choose a reason for hiding this comment

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

Why it is passed

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Because pretrained is None means no pretrained model for MLP and there is no special parameter initialization method for MLP.

Copy link
Contributor

Choose a reason for hiding this comment

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

Okay

Copy link
Contributor

Choose a reason for hiding this comment

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

@nbei what do you think

@innerlee
Copy link
Contributor

On the locaiton of the file: is it a kind of refiner?

@Yshuo-Li
Copy link
Collaborator Author

On the locaiton of the file: is it a kind of refiner?

I am not sure where should the file locate.
Can you give me a suggest? Thank you.

@innerlee innerlee merged commit d23a94d into open-mmlab:master Mar 25, 2021
@Yshuo-Li Yshuo-Li deleted the mlp branch April 8, 2021 08:17
Yshuo-Li added a commit to Yshuo-Li/mmediting that referenced this pull request Jul 15, 2022
@Yshuo-Li
Add model: multilayer perceptrons. (open-mmlab#226)
246aac1 
* Add model: multilayer perceptrons.

* Rename mlp, from 'MLP' to 'MLPRefiner.'

Co-authored-by: 李尹硕 <SENSETIME\liyinshuo@cn0014004493l.domain.sensetime.com>
Co-authored-by: liyinshuo <liyinshuo@sensetime.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@innerlee innerlee innerlee approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
2 participants
@Yshuo-Li @innerlee