Bug in ColorJitter

[Kennard123661]

torch_videovision/torchvideotransforms/video_transforms.py

Line 322 in ae4b32b

jittered_img = func(img)

Hi @hassony2 , I think there is a bug here where it should be

        for img in clip:
            for func in img_transforms:
                img = func(img)
            jittered_clip.append(img)

[xmengli]

@Kennard123661

I think you are correct. This is a bug in the code.
Another way is:

        jittered_clip = []
        for img in clip:
            jittered_img = img.copy()
            for func in img_transforms:
                jittered_img = func(jittered_img)
            jittered_clip.append(jittered_img)

I think in this way, the color transformation will be applied for each clip independently.

[LiUzHiAn]

@Kennard123661 , @xmengli999 ,

I agree with you guys, let me make a PR, check it out here :)

[SmallXieGithub]

Hi, I have a question. Should I use ColorJitter for non-RGB modalities?

[Ghelman-A]

Hi, I have a question. Should I use ColorJitter for non-RGB modalities?

Hey! I think some papers have used it with the optical flow and temporal gradient modalities as well:

1. http://openaccess.thecvf.com/content/CVPR2022/html/Xiao_Learning_From_Temporal_Gradient_for_Semi-Supervised_Action_Recognition_CVPR_2022_paper.html
2. https://openaccess.thecvf.com/content/ICCV2021/html/Xiong_Multiview_Pseudo-Labeling_for_Semi-Supervised_Learning_From_Video_ICCV_2021_paper.html