vacant-ztz comments

Results 5 comments of


                                            vacant-ztz

roicrop3d_gpu does not obtain any inner ROI point from the pseudo point cloud which throws an error when forwarding batch layer

hello，have you solved the problem? and how?

RuntimeError: CUDA error: device-side assert triggered

hello，have you solved the problem? and how?

ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 12, 1])

hello，have you solved the problem? and how?

ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 12, 1])

I have solved this problem, after checking I found that because I am using a self-built dataset, the image size is not the same as kitti (mine is 1920*1080, kitti's...

ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 12, 1])

If you want to modify the output size of the depth map, first, you need to modify the values of oheight, owidth, cwidth in SFD-TWISE-main/dataloaders/kitti_loader.py and make sure that they...