8000 What does mean_style & n_source & n_target mean? · Issue #121 · rosinality/style-based-gan-pytorch · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

What does mean_style & n_source & n_target mean? #121

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
Open
brianw0924 opened this issue Apr 28, 2021 · 8 comments
Open

What does mean_style & n_source & n_target mean? #121

brianw0924 opened this issue Apr 28, 2021 · 8 comments

Comments

@brianw0924
Copy link
brianw0924 commented Apr 28, 2021 •
edited
Loading

just wondering what is the parameter in get_mean_style means...

and the function style_mixing, what does n_target, n_source mean?
@brianw0924 brianw0924 changed the title What does mean_style mean? What does mean_style & n_source & n_target mean? Apr 28, 2021
@rosinality
Copy link
Owner

get_mean_styles will calculate average latent codes over gaussian noises.

n_target and n_source means the number of styles originates from and transferred to.

@brianw0924
Copy link
Author
brianw0924 commented Apr 29, 2021 •
edited
Loading

Thanks for replying, I have another question:

I have about 70k real img, how many "number of samples used for each training phases" should I set is the best?

my final output img is 64*64, I set the parameter 35k, and the face still have some distortion (just like a monster)

should I increase "number of samples used for each training phases" ? or should I increase n_critics?

(btw, I'm drawing anime faces)

@rosinality
Copy link
Owner

I think it would be enough to use default phase steps. It is just for transitions between each resolutions, and progressive training. You can train more on your target resolutions. (64px) And it would be better to check FIDs.

@brianw0924
Copy link
Author

thank you.

FID is really good, but there's another threshold in my homework, which is detecting faces for given images

and my output seems generate some abnormal faces (e.g. wrong eye, mouth position...etc)

@rosinality
Copy link
Owner

Are you using truncation and ema generators?

@brianw0924
Copy link
Author
brianw0924 commented May 1, 2021 •
edited
Loading

i didn't find truncation , ema generators in your codes, should I add it?

i just use your original setting, and change the image size

@rosinality
Copy link
Owner

If you are using generate.py, it will use ema generator and truncation. You can try to increase truncation by decreasing style_weight in here: https://github.com/rosinality/style-based-gan-pytorch/blob/master/generate.py#L33

I think there not much things that can be used to vastly increase image quality.

@brianw0924
Copy link
Author

Thanks!!! it works, the image quality dramatically increase!!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@rosinality @brianw0924
0