Fang Li
Fang Li
Seems like no body is maintaining this dataset now.
Thank you for the quick reply! I found the problem just now. It is because the previous checkpoint file came along with the pretrained model.
But now I got another subprocess.CalledProcessError (see attached log file). It seems like GPU out of memory, but maybe a different configuration would solve. My task is only to use...
I just killed the gnome process, free some gpu memory, then it works! That means I do need to use my lab's machine (hard due to the pandemic). Thank you...
I fixed this problem: in faster_rcnn/MSDN.py line 420: boxes = rois.data.cpu().numpy()[keep, 1:5] / im_info[0][2], change to boxes = rois.data.cpu().numpy()[keep, 1:5] / im_info[0][2].numpy(), because im_info[0][2]is a torch.Tensor type, but we need...
change pytorch to a lower version, 0.4 works for me. But after solving this one, there are more issues ahead. Good luck