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

[Enhancement] Make forward logic more clear for GAN models #1670

Conversation

LeoXing1996
Copy link
Collaborator

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

The forward function for GAN models is unclear. Therefore we modify them in this PR.

Modification

Revise the forward logic for GAN models.

Who can help? @ them here!

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

Before PR:

  • I have read and followed the workflow indicated in the CONTRIBUTING.md to create this PR.
  • Pre-commit or linting tools indicated in CONTRIBUTING.md are used to fix the potential lint issues.
  • Bug fixes are covered by unit tests, the case that causes the bug should be added in the unit tests.
  • New functionalities are covered by complete unit tests. If not, please add more unit test to ensure the correctness.
  • The documentation has been modified accordingly, including docstring or example tutorials.

After PR:

  • If the modification has potential influence on downstream or other related projects, this PR should be tested with some of those projects.
  • CLA has been signed and all committers have signed the CLA in this PR.

@LeoXing1996 LeoXing1996 self-assigned this Feb 27, 2023
Copy link
Collaborator

@zengyh1900 zengyh1900 left a comment

Choose a reason for hiding this comment

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

Any operations for packing and unpacking datasamples should be apart from the implementation of the algorithm.

mmedit/models/base_models/base_conditional_gan.py Outdated Show resolved Hide resolved
mmedit/models/base_models/base_conditional_gan.py Outdated Show resolved Hide resolved
mmedit/models/base_models/base_gan.py Outdated Show resolved Hide resolved
mmedit/models/base_models/base_gan.py Outdated Show resolved Hide resolved
mmedit/models/editors/eg3d/eg3d.py Outdated Show resolved Hide resolved
mmedit/models/editors/pggan/pggan.py Outdated Show resolved Hide resolved
mmedit/models/editors/singan/singan.py Outdated Show resolved Hide resolved
mmedit/models/editors/singan/singan.py Show resolved Hide resolved
mmedit/models/editors/singan/singan.py Show resolved Hide resolved
mmedit/models/editors/singan/singan.py Show resolved Hide resolved
@LeoXing1996 LeoXing1996 force-pushed the leoxing/revise-gan-forward branch from 1e947f3 to ba85fbd Compare February 28, 2023 06:40
@codecov
Copy link

codecov bot commented Feb 28, 2023

Codecov Report

❗ No coverage uploaded for pull request base (refactor-metric-loop-and-preprocessor@799e1f8). Click here to learn what that means.
Patch has no changes to coverable lines.

❗ Current head d8464ff differs from pull request most recent head d829bdb. Consider uploading reports for the commit d829bdb to get more accurate results

Additional details and impacted files
@@                           Coverage Diff                            @@
##             refactor-metric-loop-and-preprocessor    #1670   +/-   ##
========================================================================
  Coverage                                         ?   87.80%           
========================================================================
  Files                                            ?      399           
  Lines                                            ?    26368           
  Branches                                         ?     4114           
========================================================================
  Hits                                             ?    23152           
  Misses                                           ?     2329           
  Partials                                         ?      887           
Flag Coverage Δ
unittests 87.80% <0.00%> (?)

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

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report at Codecov.
📢 Do you have feedback about the report comment? Let us know in this issue.

Copy link
Collaborator

@zengyh1900 zengyh1900 left a comment

Choose a reason for hiding this comment

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

we leave the loop for EditDataSample insideSinGAN in future PR.

@zengyh1900 zengyh1900 merged commit e2b0922 into open-mmlab:refactor-metric-loop-and-preprocessor Feb 28, 2023
LeoXing1996 added a commit that referenced this pull request Feb 28, 2023
* make forward logic more clear for GAN models

* revise eg3d inferencer unit test

* polish length calculate and split operation for EditDataSample

* revise forward pipeline for BaseGAN and BaseCondGAN

* revise forward pipeline for EG3D

* revise forward pipeline for PGGAN

* remove useless comments from SinGAN

* remove is_stacked property from EditDataSample
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants