2025-06-26 16:12:03,164 - mmdet - INFO - Saving checkpoint at 12 epochs
[ ] 0/81, elapsed: 0s, ETA:/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/_tensor.py:575: UserWarning: floor_divide is deprecated, and will be removed in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values.
To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). (Triggered internally at ../aten/src/ATen/native/BinaryOps.cpp:467.)
return torch.floor_divide(self, other)
[ ] 1/81, 0.3 task/s, elapsed: 3s, ETA: 273s/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/core/bbox/coders/fut_nms_free_coder.py:78: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
self.post_center_range = torch.tensor(
/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/core/bbox/coders/map_nms_free_coder.py:82: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
self.post_center_range = torch.tensor(
[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 81/81, 4.5 task/s, elapsed: 18s, ETA: 0s
Traceback (most recent call last):
File "tools/train.py", line 266, in <module>
main()
File "tools/train.py", line 255, in main
custom_train_model(
File "/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/VAD/apis/train.py", line 21, in custom_train_model
custom_train_detector(
File "/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/VAD/apis/mmdet_train.py", line 194, in custom_train_detector
runner.run(data_loaders, cfg.workflow)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 127, in run
epoch_runner(data_loaders[i], **kwargs)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 54, in train
self.call_hook('after_train_epoch')
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/mmcv/runner/base_runner.py", line 307, in call_hook
getattr(hook, fn_name)(self)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/mmcv/runner/hooks/evaluation.py", line 267, in after_train_epoch
self._do_evaluate(runner)
File "/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/core/evaluation/eval_hooks.py", line 88, in _do_evaluate
key_score = self.evaluate(runner, results)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/mmcv/runner/hooks/evaluation.py", line 361, in evaluate
eval_res = self.dataloader.dataset.evaluate(
File "/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/datasets/nuscenes_vad_dataset.py", line 1781, in evaluate
all_metric_dict[key] += results[i]['metric_results'][key]
KeyError: 0
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 2522198) of binary: /home/wangbaihui/anaconda3/envs/vad/bin/python
/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py:367: UserWarning:
**********************************************************************
CHILD PROCESS FAILED WITH NO ERROR_FILE
**********************************************************************
CHILD PROCESS FAILED WITH NO ERROR_FILE
Child process 2522198 (local_rank 0) FAILED (exitcode 1)
Error msg: Process failed with exitcode 1
Without writing an error file to <N/A>.
While this DOES NOT affect the correctness of your application,
no trace information about the error will be available for inspection.
Consider decorating your top level entrypoint function with
torch.distributed.elastic.multiprocessing.errors.record. Example:
from torch.distributed.elastic.multiprocessing.errors import record
@record
def trainer_main(args):
# do train
**********************************************************************
warnings.warn(_no_error_file_warning_msg(rank, failure))
Traceback (most recent call last):
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/run.py", line 702, in <module>
main()
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 361, in wrapper
return f(*args, **kwargs)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/run.py", line 698, in main
run(args)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/run.py", line 689, in run
elastic_launch(
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 116, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 244, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
***************************************
tools/train.py FAILED
=======================================
Root Cause:
[0]:
time: 2025-06-26_16:12:28
rank: 0 (local_rank: 0)
exitcode: 1 (pid: 2522198)
error_file: <N/A>
msg: "Process failed with exitcode 1"
=======================================
Other Failures:
<NO_OTHER_FAILURES>
***********2025-06-26 16:12:03,164 - mmdet - INFO - Saving checkpoint at 12 epochs
[ ] 0/81, elapsed: 0s, ETA:/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/_tensor.py:575: UserWarning: floor_divide is deprecated, and will be removed in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values.
To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). (Triggered internally at ../aten/src/ATen/native/BinaryOps.cpp:467.)
return torch.floor_divide(self, other)
[ ] 1/81, 0.3 task/s, elapsed: 3s, ETA: 273s/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/core/bbox/coders/fut_nms_free_coder.py:78: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
self.post_center_range = torch.tensor(
/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/core/bbox/coders/map_nms_free_coder.py:82: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
self.post_center_range = torch.tensor(
[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 81/81, 4.5 task/s, elapsed: 18s, ETA: 0s
Traceback (most recent call last):
File "tools/train.py", line 266, in <module>
main()
File "tools/train.py", line 255, in main
custom_train_model(
File "/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/VAD/apis/train.py", line 21, in custom_train_model
custom_train_detector(
File "/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/VAD/apis/mmdet_train.py", line 194, in custom_train_detector
runner.run(data_loaders, cfg.workflow)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 127, in run
epoch_runner(data_loaders[i], **kwargs)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 54, in train
self.call_hook('after_train_epoch')
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/mmcv/runner/base_runner.py", line 307, in call_hook
getattr(hook, fn_name)(self)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/mmcv/runner/hooks/evaluation.py", line 267, in after_train_epoch
self._do_evaluate(runner)
File "/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/core/evaluation/eval_hooks.py", line 88, in _do_evaluate
key_score = self.evaluate(runner, results)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/mmcv/runner/hooks/evaluation.py", line 361, in evaluate
eval_res = self.dataloader.dataset.evaluate(
File "/media/wangbaihui/1ecf654b-afad-4dab-af7b-e34b00dda87a/mmdetection3d/VAD/projects/mmdet3d_plugin/datasets/nuscenes_vad_dataset.py", line 1781, in evaluate
all_metric_dict[key] += results[i]['metric_results'][key]
KeyError: 0
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 2522198) of binary: /home/wangbaihui/anaconda3/envs/vad/bin/python
/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py:367: UserWarning:
**********************************************************************
CHILD PROCESS FAILED WITH NO ERROR_FILE
**********************************************************************
CHILD PROCESS FAILED WITH NO ERROR_FILE
Child process 2522198 (local_rank 0) FAILED (exitcode 1)
Error msg: Process failed with exitcode 1
Without writing an error file to <N/A>.
While this DOES NOT affect the correctness of your application,
no trace information about the error will be available for inspection.
Consider decorating your top level entrypoint function with
torch.distributed.elastic.multiprocessing.errors.record. Example:
from torch.distributed.elastic.multiprocessing.errors import record
@record
def trainer_main(args):
# do train
**********************************************************************
warnings.warn(_no_error_file_warning_msg(rank, failure))
Traceback (most recent call last):
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/run.py", line 702, in <module>
main()
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 361, in wrapper
return f(*args, **kwargs)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/run.py", line 698, in main
run(args)
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/run.py", line 689, in run
elastic_launch(
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 116, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/wangbaihui/anaconda3/envs/vad/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 244, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
***************************************
tools/train.py FAILED
=======================================
Root Cause:
[0]:
time: 2025-06-26_16:12:28
rank: 0 (local_rank: 0)
exitcode: 1 (pid: 2522198)
error_file: <N/A>
msg: "Process failed with exitcode 1"
=======================================
Other Failures:
<NO_OTHER_FAILURES>
***********