hongyang
Add Vim Mode
It's such a wonderful editor. Could you add vim mode in it?
We try to get the performance using resnet101 in your paper. But the final performance is a little worse than the reported result. I wonder is there any problems in...
https://github.com/uber-research/UPSNet/blob/2ced987576a98dc16c5a580839b657948644d44d/upsnet/operators/modules/mask_matching.py#L52 In this line, you just use "gt_masks[[i], :, :] != 0" to judge whether a pixel belongs to the instance. But the picture is padded using 255. I think...
I think your work is wonderful. I have some questions about the implement. The paper said that choosing class agnostic is for simplicity. I want to know whether it's important...
Thank you for your sharing the detnet59 pretrained model. I want to know why the mAP in COCO2017 is much lower than the result reported in the original paper?