TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType

[yuanfuture]

Hello, first of all, thank you very much for your outstanding work, I have some questions to consult, the model has been configured according to the requirements, and the model can be trained normally, and can achieve similar results as in the paper, but I encountered the following problems when reasoning, may I ask why? Thank you very much! By the way, the statements I execute at inference time are : python test.py --cfg_file cfgs/kitti_models/sfd.yaml --batch_size 1

Traceback (most recent call last):
File "test.py", line 204, in
main()
File "test.py", line 200, in main
eval_single_ckpt(model, test_loader, args, eval_output_dir, logger, epoch_id, dist_test=dist_test)
File "test.py", line 60, in eval_single_ckpt
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=dist_test)
File "/media/SFD/pcdet/models/detectors/detector3d_template.py", line 355, in load_params_from_file
if not os.path.isfile(filename):
File "/home/miniconda3/envs/Basics-L/lib/python3.8/genericpath.py", line 30, in isfile
st = os.stat(path)
TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType