checkpoints/CHECKPOINT.pth 1

[hdonghun]

bash tools/dist_test.sh configs/ntu60_xsub/j.py checkpoints/CHECKPOINT.pth 1 --eval top_k_accuracy --out result.pkl
Where can I find this? -> CHECKPOINT.pth

Or, should I do it like this?
bash tools/dist_test.sh configs/ntu60_xsub/j.py checkpoints/ntu120_xsub_joint_best.pth1 --eval top_k_accuracy --out result.pkl

However, this error happens, what am I missing?
error log :
bash tools/dist_test.sh configs/ntu120_xsub/j.py checkpoints/ntu120_xsub/j_1/best_top1_acc_epoch_141.pth 1 --eval top_k_accuracy --out result.pkl

• CONFIG=configs/ntu120_xsub/j.py

• CHECKPOINT=checkpoints/ntu120_xsub/j_1/best_top1_acc_epoch_141.pth

• GPUS=1
  ++ dirname tools/dist_test.sh

• MKL_SERVICE_FORCE_INTEL=1
  ++ dirname tools/dist_test.sh

• PYTHONPATH=tools/..:

• CUDA_VISIBLE_DEVICES=0

• python -m torch.distributed.launch --nproc_per_node=1 --master_port=14485 tools/test.py configs/ntu120_xsub/j.py -C checkpoints/ntu120_xsub/j_1/best_top1_acc_epoch_141.pth --launcher pytorch --eval top_k_accuracy --out result.pkl
  /home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/torch/distributed/launch.py:207: FutureWarning: The module torch.distributed.launch is deprecated
  and will be removed in future. Use torchrun.
  Note that --use-env is set by default in torchrun.
  If your script expects --local-rank argument to be set, please
  change it to read from os.environ['LOCAL_RANK'] instead. See
  https://pytorch.org/docs/stable/distributed.html#launch-utility for
  further instructions

  main()
  /home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/mmcv/init.py:20: UserWarning: On January 1, 2023, MMCV will release v2.0.0, in which it will remove components related to the training process and add a data transformation module. In addition, it will rename the package names mmcv to mmcv-lite and mmcv-full to mmcv. See https://github.com/open-mmlab/mmcv/blob/master/docs/en/compatibility.md for more details.
  warnings.warn(
  2025-11-13 17:31:59,649 - protogcn - INFO - 50919 videos remain after valid thresholding
  /home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via init_process_group or barrier . Using the current device set by the user.
  warnings.warn( # warn only once
  [rank0]:[W1113 17:31:59.054641934 ProcessGroupNCCL.cpp:4718] [PG ID 0 PG GUID 0 Rank 0] using GPU 0 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can pecify device_id in init_process_group() to force use of a particular device.
  load checkpoint from local path: checkpoints/ntu120_xsub/j_1/best_top1_acc_epoch_141.pth
  [rank0]: Traceback (most recent call last):
  [rank0]: File "/home/mhncity/Desktop/handonghun/protogcn/ProtoGCN/tools/test.py", line 252, in
  [rank0]: main()
  [rank0]: File "/home/mhncity/Desktop/handonghun/protogcn/ProtoGCN/tools/test.py", line 235, in main
  [rank0]: outputs = inference_pytorch(args, cfg, data_loader)
  [rank0]: File "/home/mhncity/Desktop/handonghun/protogcn/ProtoGCN/tools/test.py", line 164, in inference_pytorch
  [rank0]: load_checkpoint(model, args.checkpoint, map_location='cpu')
  [rank0]: File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/mmcv/runner/checkpoint.py", line 638, in load_checkpoint
  [rank0]: checkpoint = _load_checkpoint(filename, map_location, logger)
  [rank0]: File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/mmcv/runner/checkpoint.py", line 572, in _load_checkpoint
  [rank0]: return CheckpointLoader.load_checkpoint(filename, map_location, logger)
  [rank0]: File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/mmcv/runner/checkpoint.py", line 314, in load_checkpoint
  [rank0]: return checkpoint_loader(filename, map_location) # type: ignore
  [rank0]: File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/mmcv/runner/checkpoint.py", line 334, in load_from_local
  [rank0]: checkpoint = torch.load(filename, map_location=map_location)
  [rank0]: File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/torch/serialization.py", line 1524, in load
  [rank0]: raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
  [rank0]: _pickle.UnpicklingError: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
  [rank0]: (1) In PyTorch 2.6, we changed the default value of the weights_only argument in torch.load from False to True. Re-running torch.load with weights_only set to False will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
  [rank0]: (2) Alternatively, to load with weights_only=True please check the recommended steps in the following error message.
  [rank0]: WeightsUnpickler error: Unsupported global: GLOBAL numpy.core.multiarray.scalar was not an allowed global by default. Please use torch.serialization.add_safe_globals([numpy.core.multiarray.scalar]) or the torch.serialization.safe_globals([numpy.core.multiarray.scalar]) context manager to allowlist this global if you trust this class/function.

[rank0]: Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
[rank0]:[W1113 17:32:00.391155371 ProcessGroupNCCL.cpp:1479] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
E1113 17:32:01.134000 340892 torch/distributed/elastic/multiprocessing/api.py:874] failed (exitcode: 1) local_rank: 0 (pid: 340930) of binary: /home/mhncity/Desktop/handonghun/protogcn/protogcn/bin/python
Traceback (most recent call last):
File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/torch/distributed/launch.py", line 207, in
main()
File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/typing_extensions.py", line 3004, in wrapper
return arg(*args, **kwargs)
File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/torch/distributed/launch.py", line 203, in main
launch(args)
File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/torch/distributed/launch.py", line 188, in launch
run(args)
File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/torch/distributed/run.py", line 883, in run
elastic_launch(
File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 139, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/mhncity/Desktop/handonghun/protogcn/protogcn/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 270, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

tools/test.py FAILED

Failures:
<NO_OTHER_FAILURES>

Root Cause (first observed failure):
[0]:
time : 2025-11-13_17:32:01
host : mhncity-desktop
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 340930)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html

[firework8]

Thanks for your interest.

Checkpoints are the addresses of folders you create or select yourself.
CHECKPOINT.pth can be found here, and you should place it in the corresponding folder.
If training can proceed normally, then the test should be fine too.

Additionally, I noticed you omitted a space in the command ntu120_xsub_joint_best.pth1.
You can also double-check the CUDA_VISIBLE_DEVICES in tools/dist_test.sh to avoid device conflicts.

Hope this helps.