You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
(deformable_detr) root@workspace:/dfs/data/code_python/detection_2d/mmdetection# CUDA_VISIBLE_DEVICES=1 tools/dist_train.sh configs/deformable_detr/deformable_detr_r50_16x2_50e_coco.py 1
Traceback (most recent call last):
File "tools/train.py", line 244, in
main()
File "tools/train.py", line 172, in main
init_dist(args.launcher, **cfg.dist_params)
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/mmcv/utils/config.py", line 507, in getattr
return getattr(self._cfg_dict, name)
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/mmcv/utils/config.py", line 48, in getattr
raise ex
AttributeError: 'ConfigDict' object has no attribute 'dist_params'
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 2441) of binary: /dfs/data/anaconda/envs/deformable_detr/bin/python
Traceback (most recent call last):
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/launch.py", line 193, in
main()
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/launch.py", line 189, in main
launch(args)
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/launch.py", line 174, in launch
run(args)
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/run.py", line 710, in run
elastic_launch(
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 131, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 259, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
(deformable_detr) root@workspace:/dfs/data/code_python/detection_2d/mmdetection# CUDA_VISIBLE_DEVICES=1 tools/dist_train.sh configs/deformable_detr/deformable_detr_r50_16x2_50e_coco.py 1
Traceback (most recent call last):
File "tools/train.py", line 244, in
main()
File "tools/train.py", line 172, in main
init_dist(args.launcher, **cfg.dist_params)
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/mmcv/utils/config.py", line 507, in getattr
return getattr(self._cfg_dict, name)
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/mmcv/utils/config.py", line 48, in getattr
raise ex
AttributeError: 'ConfigDict' object has no attribute 'dist_params'
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 2441) of binary: /dfs/data/anaconda/envs/deformable_detr/bin/python
Traceback (most recent call last):
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/launch.py", line 193, in
main()
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/launch.py", line 189, in main
launch(args)
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/launch.py", line 174, in launch
run(args)
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/run.py", line 710, in run
elastic_launch(
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 131, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/dfs/data/anaconda/envs/deformable_detr/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 259, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
tools/train.py FAILED
Failures:
<NO_OTHER_FAILURES>
Root Cause (first observed failure):
[0]:
time : 2022-12-09_15:03:20
host : workspace
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 2441)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html