TencentARC/GFPGAN
1
0
Fork 0
mirror of https://github.com/TencentARC/GFPGAN.git synced 2026-02-04 08:14:41 +00:00
Code Issues 476 Packages Projects Releases 8 Wiki Activity

results are strange while testing on whole img #37

New Issue
Closed
opened 2026-01-29 21:38:56 +00:00 by claunia · 7 comments
claunia commented 2026-01-29 21:38:56 +00:00
Owner
Copy Link

Originally created by @tachikoma777 on GitHub (Jul 29, 2021).

Hi, I'm using pretrain model for testing, while testing on align cropped faces, the results are promising.
However, while testing as whole img the results are wrong, seems the detection is not working well because in results cmp folder there is no faces or sereval faces in one img.

I didn't change the code, is there anything wrong the whole img testing? Thanks in advance.

Originally created by @tachikoma777 on GitHub (Jul 29, 2021). Hi, I'm using pretrain model for testing, while testing on align cropped faces, the results are promising. However, while testing as whole img the results are wrong, seems the detection is not working well because in results cmp folder there is no faces or sereval faces in one img. I didn't change the code, is there anything wrong the whole img testing? Thanks in advance.
claunia commented 2026-01-29 21:38:58 +00:00
Author
Owner
Copy Link

@xinntao commented on GitHub (Aug 3, 2021):

  1. If no face is detected, it will restore it.
  2. As the current model also enhances colors, when putting faces back to the whole image, the results are not good. We will release a model w/o changing colors.
@xinntao commented on GitHub (Aug 3, 2021): 1. If no face is detected, it will restore it. 2. As the current model also enhances colors, when putting faces back to the whole image, the results are not good. We will release a model w/o changing colors.
claunia commented 2026-01-29 21:38:59 +00:00
Author
Owner
Copy Link

@tachikoma777 commented on GitHub (Aug 4, 2021):

  1. If no face is detected, it will restore it.
  2. As the current model also enhances colors, when putting faces back to the whole image, the results are not good. We will release a model w/o changing colors.

But I use default test img in original project, it will be strange if no face is detected. results are as follows:
image

@tachikoma777 commented on GitHub (Aug 4, 2021): > 1. If no face is detected, it will restore it. > 2. As the current model also enhances colors, when putting faces back to the whole image, the results are not good. We will release a model w/o changing colors. But I use default test img in original project, it will be strange if no face is detected. results are as follows: ![image](https://user-images.githubusercontent.com/6949661/128117648-e9e62199-995f-4edc-a8c4-499fb3ef511f.png)
claunia commented 2026-01-29 21:39:01 +00:00
Author
Owner
Copy Link

@tachikoma777 commented on GitHub (Aug 4, 2021):

By the way, I have i small question about the Channel-Split SFT, which is how the F_prior is splited in chanels? How many channel F_prior have? Thanks!

@tachikoma777 commented on GitHub (Aug 4, 2021): By the way, I have i small question about the Channel-Split SFT, which is how the F_prior is splited in chanels? How many channel F_prior have? Thanks!
claunia commented 2026-01-29 21:39:03 +00:00
Author
Owner
Copy Link

@xinntao commented on GitHub (Aug 4, 2021):

  1. If no face is detected, it will restore it.
  2. As the current model also enhances colors, when putting faces back to the whole image, the results are not good. We will release a model w/o changing colors.

But I use default test img in original project, it will be strange if no face is detected. results are as follows:
image

Did you use the colab demo?
It seems that there must be something wrong with face detection.~

@xinntao commented on GitHub (Aug 4, 2021): > > 1. If no face is detected, it will restore it. > > 2. As the current model also enhances colors, when putting faces back to the whole image, the results are not good. We will release a model w/o changing colors. > > But I use default test img in original project, it will be strange if no face is detected. results are as follows: > ![image](https://user-images.githubusercontent.com/6949661/128117648-e9e62199-995f-4edc-a8c4-499fb3ef511f.png) Did you use the colab demo? It seems that there must be something wrong with face detection.~
claunia commented 2026-01-29 21:39:05 +00:00
Author
Owner
Copy Link

@xinntao commented on GitHub (Aug 4, 2021):

By the way, I have i small question about the Channel-Split SFT, which is how the F_prior is splited in chanels? How many channel F_prior have? Thanks!

Half the original channels~

@xinntao commented on GitHub (Aug 4, 2021): > By the way, I have i small question about the Channel-Split SFT, which is how the F_prior is splited in chanels? How many channel F_prior have? Thanks! Half the original channels~
claunia commented 2026-01-29 21:39:06 +00:00
Author
Owner
Copy Link

@tachikoma777 commented on GitHub (Aug 5, 2021):

  1. If no face is detected, it will restore it.
  2. As the current model also enhances colors, when putting faces back to the whole image, the results are not good. We will release a model w/o changing colors.

But I use default test img in original project, it will be strange if no face is detected. results are as follows:
image

Did you use the colab demo?
It seems that there must be something wrong with face detection.~

No, I tested on local side. After I recheck the crop region and found that for every input the detection region is always the left up 512*512 block. I tested on both moblienet and resnet detection model.
Is there something wrong with facexlib? I tested both v0.1.3.1 and v0.1

@tachikoma777 commented on GitHub (Aug 5, 2021): > > > 1. If no face is detected, it will restore it. > > > 2. As the current model also enhances colors, when putting faces back to the whole image, the results are not good. We will release a model w/o changing colors. > > > > > > But I use default test img in original project, it will be strange if no face is detected. results are as follows: > > ![image](https://user-images.githubusercontent.com/6949661/128117648-e9e62199-995f-4edc-a8c4-499fb3ef511f.png) > > Did you use the colab demo? > It seems that there must be something wrong with face detection.~ No, I tested on local side. After I recheck the crop region and found that for every input the detection region is always the left up 512*512 block. I tested on both moblienet and resnet detection model. Is there something wrong with facexlib? I tested both v0.1.3.1 and v0.1
claunia commented 2026-01-29 21:39:08 +00:00
Author
Owner
Copy Link

@xinntao commented on GitHub (Aug 6, 2021):

I have updated the model without colorization. Colab demo: https://colab.research.google.com/drive/1sVsoBd9AjckIXThgtZhGrHRfFI6UUYOo

For your problem, I have not encountered this issue on my side.

@xinntao commented on GitHub (Aug 6, 2021): I have updated the model without colorization. Colab demo: https://colab.research.google.com/drive/1sVsoBd9AjckIXThgtZhGrHRfFI6UUYOo For your problem, I have not encountered this issue on my side.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
pull-request
Mirrored from GitHub Pull Request
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
claunia
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: TencentARC/GFPGAN#37
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?