Use COCO Mask Parsing from pycocotools

[david-csnmedia]

🚀 The feature

The CocoDetection v2 transform wrapper attempts to decode the mask itself, but pycocotools provides a high performance implementation already. We have had to copy from master, this _dataset_wrapper.py because of a bug related to the handling of these masks that was fixed in master but not installable using pip yet.

https://github.com/pytorch/vision/blob/main/torchvision/tv_tensors/_dataset_wrapper.py#L402

Seeing torchvision.datasets.CocoDetection has self.coco as a COCO() object, let's use it.

       coco_ann = dataset.coco.imgToAnns[image_id]

        if "masks" in target_keys:
            target["masks"] = tv_tensors.Mask(
                    torch.stack([
                        torch.from_numpy(dataset.coco.annToMask(ann))
                        for ann in coco_ann
                    ])
                )

Motivation, pitch

There have already been bugs related to this, and there's no need to reinvent the wheel. Instead, let's use the existing implementation.

Alternatives

No response

Additional context

No response

[NicolasHug]

Thanks for opening the issue @david-csnmedia . I'm happy for you to open a PR and see if the tests are passing