nuScenes data val OSError: latest.pth is not a checkpoint file

[751565516]

Hi,first, thank you for your outstanding work. When I finish training, and then python ./tools/dist_test.py /home/zj/CenterPoint/configs/nusc/pp/nusc_centerpoint_pp_02voxel_two_pfn_10sweep.py --work_dir work_dirs/nusc_centerpoint_pp_02voxel_two_pfn_10sweep.py --checkpoint work_dirs/nusc_centerpoint_pp_02voxel_two_pfn_10sweep.py/latest.pth --speed_test The following error occurred during the test

(cp) zj@zj-Legion-Y7000-2019-PG0:~/CenterPoint$ python ./tools/dist_test.py /home/zj/CenterPoint/configs/nusc/pp/nusc_centerpoint_pp_02voxel_two_pfn_10sweep.py --work_dir work_dirs/nusc_centerpoint_pp_02voxel_two_pfn_10sweep.py --checkpoint work_dirs/nusc_centerpoint_pp_02voxel_two_pfn_10sweep.py/latest.pth --speed_test No Tensorflow Deformable Convolution not built! 2022-06-22 10:38:42,421 - INFO - Distributed testing: False 2022-06-22 10:38:42,421 - INFO - torch.backends.cudnn.benchmark: False 2022-06-22 10:38:42,467 - INFO - Finish RPN Initialization 2022-06-22 10:38:42,468 - INFO - num_classes: [1, 2, 2, 1, 2, 2] Use HM Bias: -2.19 2022-06-22 10:38:42,572 - INFO - Finish CenterHead Initialization Use Val Set 10 Traceback (most recent call last): File "./tools/dist_test.py", line 211, in main() File "./tools/dist_test.py", line 123, in main checkpoint = load_checkpoint(model, args.checkpoint, map_location="cpu") File "/home/zj/CenterPoint/det3d/torchie/trainer/checkpoint.py", line 200, in load_checkpoint raise IOError("{} is not a checkpoint file".format(filename)) OSError: work_dirs/nusc_centerpoint_pp_02voxel_two_pfn_10sweep.py/latest.pth is not a checkpoint file

Later, I used the model centerpoint_ pillar provided by MODEL Zoo, still get this error.

So,What can I do to solve this problem？

[tianweiy]

The path for checkpoint is wrong. You should not have .py in the path

[751565516]

sorry,I made a low-level mistake.

In addition, I'd like to ask how to carry out detection visualization and tracking visualization?

Thank you very much!