torch_videovision

torch_videovision copied to clipboard

Hi @hassony2 The last line in the RandomResizedCrop should be changed from https://github.com/hassony2/torch_videovision/blob/785a810d1df2ccab6901fb98b38e358433e7b17a/torchvideotransforms/video_transforms.py#L312 to ` return F.resize_clip(imgs,self.size,self.interpolation)` for the cropping to be applied as well.

Ghelman-A

Right now the following code `from torchvideotransforms import video_transforms, volume_transforms` `video_transform_list = [video_transforms.RandomRotation(30),` `video_transforms.RandomCrop((200, 200))` `volume_transforms.ClipToTensor()]` `transforms = video_transforms.Compose(video_transform_list)` from the "How to use" section returns an error, due to...

RodGal-2020

Hi, there is a bug in ColorJitter as posted in issue #8. I've fixed here.

LiUzHiAn

Bug in ColorJitter

4

https://github.com/hassony2/torch_videovision/blob/ae4b32b4dc76f97387ae74c9c652bffb7ba05697/torchvideotransforms/video_transforms.py#L322 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) ```

Kennard123661

bomri

https://github.com/hassony2/torch_videovision/blob/ae4b32b4dc76f97387ae74c9c652bffb7ba05697/torchvideotransforms/tensor_transforms.py#L58 `cropped = tensor[:, :, y1:y1 + h, x1:x1 + h]` -> `cropped = tensor[:, :, y1:y1 + h, x1:x1 + w]`

josiahcoad

Thanks for the nice implementation! It would be nice if you make it comparable with accimage ( https://github.com/pytorch/accimage ).... Currently it assume numpy or Pillow image.

apple2373