faster-rcnn.pytorch icon indicating copy to clipboard operation
faster-rcnn.pytorch copied to clipboard

Published 20 hours ago • verified publisher icon jwyang

Why gt_boxes all 1 in testing?

Open sjytker opened this issue 3 years ago • 2 comments

I run test_net.py and got all 0 results. I have checked all the related issue and nothing could be done. I notice that in roibatchLoader.py, gt_boxes are make all 1 in this code gt_boxes = torch.FloatTensor([1, 1, 1, 1, 1]) in line 210 or so. Is it correct?

sjytker avatar Dec 02 '21 07:12 sjytker

I run test_net.py and got all 0 results. I have checked all the related issue and nothing could be done. I notice that in roibatchLoader.py, gt_boxes are make all 1 in this code gt_boxes = torch.FloatTensor([1, 1, 1, 1, 1]) in line 210 or so. Is it correct?

Do you know why? I'm also wondering

xlhuang132 avatar Dec 15 '21 08:12 xlhuang132

I run test_net.py and got all 0 results. I have checked all the related issue and nothing could be done. I notice that in roibatchLoader.py, gt_boxes are make all 1 in this code gt_boxes = torch.FloatTensor([1, 1, 1, 1, 1]) in line 210 or so. Is it correct?

Do you know why? I'm also wondering

I don't know, maybe the author abandon the repo in this way…… I have finished my job using another repo.

sjytker avatar Dec 17 '21 09:12 sjytker