Closed Yutong-gannis closed 1 year ago
Hello. I'm sorry for the late response. This code is currently written with only KITTI data in mind and is not compatible with the Nuscenes dataset. I will update you if I have a GPU available in the future. Thank you.
@2gunsu I convert nuscenes dataset to kitti format. But I meet this problem when train
File "/hy-tmp/monocon-pytorch/losses/l1_loss.py", line 17, in l1_loss
assert pred.size() == target.size() and target.numel() > 0
AssertionError
then I print pred
and target
tensor([], device='cuda:0', size=(0, 2), grad_fn=<IndexBackward0>)
tensor([], device='cuda:0', size=(0, 2))
How can I solve this problem.
How can i train monocon on nuscenes dataset?