Index out of bounds about deepglobalregistration

[dorucia]

For more information, it stochastically throws a different type of error like this one.

Traceback (most recent call last):
  File "train.py", line 76, in <module>
    main(config)
  File "train.py", line 55, in main
    trainer.train()
  File "dgr/core/trainer.py", line 135, in train
    self._train_epoch(epoch)
  File "dgr/core/trainer.py", line 241, in _train_epoch
    rot_error = batch_rotation_error(pred_rots, gt_rots)
  File "dgr/core/metrics.py", line 32, in batch_rotation_error
    assert len(rots1) == len(rots2)
AssertionError

My environment is PyTorch 1.5.0, CUDA 10.1.243, python 3.7, ubuntu 18.04, and installed gcc7 as shown in Readme

[dorucia]

Found a bug or an issue

For the CollationFunctionFactory in the base_loader.py,
right before collate_pair_fn returns, I printed xyz0, xyz1, and len_batch like this

for x0, x1, lens in zip(xyz0, xyz1, len_batch):
        print('collate xyz0 {}, xyz1 {}, lenb {}'.format(x0.shape, x1.shape, lens))

    return {
        'pcd0': xyz0,
        'pcd1': xyz1,
        'sinput0_C': coords_batch0,
        'sinput0_F': feats_batch0,
        'sinput1_C': coords_batch1,
        'sinput1_F': feats_batch1,
        'correspondences': matching_inds_batch,
        'T_gt': trans_batch,
        'len_batch': len_batch,
        'extra_packages': extra_packages,
    }

and the output is

collate xyz0 torch.Size([473, 3]), xyz1 torch.Size([473, 3]), lenb [473, 473]
collate xyz0 torch.Size([412, 3]), xyz1 torch.Size([414, 3]), lenb [412, 414]
collate xyz0 torch.Size([304, 3]), xyz1 torch.Size([298, 3]), lenb [459, 463]
collate xyz0 torch.Size([459, 3]), xyz1 torch.Size([463, 3]), lenb [411, 407]
collate xyz0 torch.Size([411, 3]), xyz1 torch.Size([407, 3]), lenb [402, 398]
collate xyz0 torch.Size([402, 3]), xyz1 torch.Size([398, 3]), lenb [269, 264]
collate xyz0 torch.Size([339, 3]), xyz1 torch.Size([334, 3]), lenb [339, 334]
collate xyz0 torch.Size([427, 3]), xyz1 torch.Size([425, 3]), lenb [427, 425]
collate xyz0 torch.Size([358, 3]), xyz1 torch.Size([362, 3]), lenb [358, 362]
collate xyz0 torch.Size([369, 3]), xyz1 torch.Size([345, 3]), lenb [296, 295]
collate xyz0 torch.Size([296, 3]), xyz1 torch.Size([295, 3]), lenb [335, 313]
collate xyz0 torch.Size([335, 3]), xyz1 torch.Size([313, 3]), lenb [366, 371]

as we can see, the shape of xyz0 and xyz1 does not match with lenb for some lines.

[lombardm]

Hi,

I have the same issue, can you please tell me if you solved this and how?

Thanks in advance

[pranavgundewar]

I am facing a similar issue as well. How did you solve this?