Skip to content

Fix extension for apply custom dataset which has jpg extension#60

Open
saintrealchoi wants to merge 93 commits intoadvimman:mainfrom
saintrealchoi:main
Open

Fix extension for apply custom dataset which has jpg extension#60
saintrealchoi wants to merge 93 commits intoadvimman:mainfrom
saintrealchoi:main

Conversation

@saintrealchoi
Copy link

Hello! First of all, Thank you for Awesome project.

I want to use your code on my images. but, when it has 'jpg' extension shell script do not recognize files.
So, I fix it for all images which have other extension

Thank you!

cohimame and others added 25 commits October 17, 2021 15:51
* cleaner configs

* visualizer genearalize

* visualizer genearalize

* lama-celeba configs

* optimizers config and celeba readme upd

* noop vis in predict.py

* default optimizers config

* default opt fixed

Co-authored-by: Aleksei Silvestrov <a.silvestrov@samsung.net>
I just copy the code in the folder `saicinpainting`  to my code repository, since I just want to adopt `FFC_BN_FLU` layer in my net. Then it occurs an error:
```bash
  File "C:\Users\xx\tmp\saicinpainting\utils.py", line 104, in <module>
    def register_debug_signal_handlers(sig=signal.SIGUSR1, handler=print_traceback_handler):
AttributeError: module 'signal' has no attribute 'SIGUSR1'
```

This patch fixes the error.
Huggingface spaces web demo
* fix optimizers config file for all hydras

* fix optimizers config file for all hydras
* own dataset readme

* own dataset readme

* own dataset readme

* own dataset readme

* own dataset readme

* own dataset readme

* own dataset readme

* my dataset full roadmap

* my dataset full roadmap

* my dataset full roadmap

* my dataset full roadmap

* more details

* more details

* more details
Probably fix the error running on windows
@windj007
Copy link
Collaborator

windj007 commented Dec 6, 2021

Hi! Thank you for your contribution! Could you please change the default values to .png so the default behaviour is not changed after your fix?

@saintrealchoi
Copy link
Author

Thank you for the review! I fix default values from .jpg to .png. :)

@jf1957
Copy link

jf1957 commented Jan 30, 2026

I would like to kindly ask you some questions regarding training on the CelebA dataset. Specifically, based on LaMa-Fourier, what small modifications or fine-tuning strategies could be applied to slightly improve the final performance metrics?

I am currently working on my undergraduate graduation thesis, and these suggestions would be extremely helpful to my research. I would sincerely appreciate it if you could share some advice or insights.

Thank you very much for your time and help. @saintrealchoi @windj007 @senya-ashukha @elimohl @cohimame

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.

9 participants