Results 4 issues of Kwangyeon Gill

# Ask a Question ### Question I have implemented a custom pytorch CUDA kernel (and CPU kernel) for rotated bounding boxes that is not supported in pytorch. (like this example...

question
runtime

https://github.com/pytorch/vision/blob/6d7851bd5e2bedc294e40e90532f0e375fcfee04/references/segmentation/coco_utils.py#L27-L41 Above seems to assume that objects are not occluded, not merging rles from `frPyObjects`. In such case, i think it must be changed to ```python rles = coco_mask.frPyObjects(polygons, height,...

### Bug description I want to dynamically set `val_check_interval` based on the total number of training steps. Specifically, i calculate val_check_interval using self.trainer.estimated_stepping_batches // 10 in the setup() method, aiming...

bug
needs triage
ver: 2.5.x

### 🐛 Describe the bug ```python from torchvision import models frcnn = models.detection.fasterrcnn_resnet50_fpn_v2(pretrained=True) import io import torch x = torch.rand(4, 3, 224, 224) with io.BytesIO() as f: torch.onnx.export( frcnn, x,...