Jerry Jiarui XU
Jerry Jiarui XU
Hi @acver1 I haven't encountered this issue before. Maybe you could try to reduce the worker number to see if the error still exists.
Hi @ZeWang95 webdataset 0.1 and 0.2 may not compatible in some APIs. And we haven't verify the accuracy of webdataset 0.2.
Hi @XuMengyaAmy Thanks for your interest in our work. (1) The training set should be in webdataset format with image text pairs. The `val` is just for zero-shot image classification...
Hi @XiaominLi1997 The config is here https://github.com/NVlabs/GroupViT/blob/main/configs/default.yml#L90
Hi @XiaominLi1997 Since the training samples are noisy, it may cover a wide range of concepts. Some of them may overlap with our evaluation dataset, e.g. Pascal VOC. But we...
> I also want to know the evaluation part. Does the cls part only include the ImageNet? And the seg part includes Pascal VOC, Pascal Context and COCO? Thank you...
``` +------------+-------+-------+ | Class | IoU | Acc | +------------+-------+-------+ | background | 80.63 | 88.04 | | aeroplane | 38.08 | 91.94 | | bicycle | 31.41 | 82.44...
For the background, we use some threshold to predict. See details here https://github.com/NVlabs/GroupViT/blob/13b786155a1dfffe4703f40d028c92be58e1178d/segmentation/evaluation/group_vit_seg.py#L242
Hi @roysubhankar I used the first one.
Hi @liuxingbin Yes. That's correct. GroupViT could do semantic segmentation on different dataset with the same model.