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] Support import projected latent and export video in interpolation #167

Merged
merged 9 commits into from
Dec 6, 2021

Conversation

plyfager
Copy link
Collaborator

@plyfager plyfager commented Nov 25, 2021

  • Support import latent produced by stylegan_projector.py.
  • Support export video.
    Other modifications for stylegan3 will be added in a new PR.

@plyfager plyfager requested a review from nbei November 26, 2021 06:34
@plyfager plyfager changed the title [WIP] Support import projected latent and export video in interpolation [Enhancement] Support import projected latent and export video in interpolation Nov 26, 2021
parser.add_argument(
'--export-video',
action='store_true',
help='whether to use cpu device for sampling')
Copy link
Collaborator

Choose a reason for hiding this comment

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

I just think this help information is not correct.

'--proj-latent',
type=str,
default=None,
help='Projection file of Images. Produced by stylegan_projector.py.')
Copy link
Collaborator

Choose a reason for hiding this comment

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

Projection image files.
You may specify the content in this file. After reading the help information, I cannot know what you want to achieve with this argument.

apps/interpolate_sample.py Outdated Show resolved Hide resolved
@codecov-commenter
Copy link

Codecov Report

Merging #167 (0b33e24) into master (a6b767c) will decrease coverage by 0.04%.
The diff coverage is n/a.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #167      +/-   ##
==========================================
- Coverage   75.39%   75.35%   -0.05%     
==========================================
  Files         127      127              
  Lines        8812     8812              
  Branches     1747     1747              
==========================================
- Hits         6644     6640       -4     
- Misses       1734     1736       +2     
- Partials      434      436       +2     
Flag Coverage Δ
unittests 75.35% <ø> (-0.05%) ⬇️

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

Impacted Files Coverage Δ
...chitectures/stylegan/generator_discriminator_v2.py 86.66% <0.00%> (-1.12%) ⬇️
mmgen/models/architectures/stylegan/mspie.py 90.59% <0.00%> (-1.00%) ⬇️
...chitectures/stylegan/generator_discriminator_v1.py 89.83% <0.00%> (ø)

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 a6b767c...0b33e24. Read the comment docs.

@nbei nbei merged commit 53d2286 into open-mmlab:master Dec 6, 2021
LeoXing1996 pushed a commit that referenced this pull request Jul 16, 2022
…erpolation (#167)

* support import latent produce by stylegan_projector

* fix lint

* support export video

* fix PR#167

* remove redundant blank space

* fix lint

Co-authored-by: yangyifei <PJLAB\yangyifei@shai14001042l.pjlab.org>
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.

None yet

3 participants