Traceback (most recent call last):
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 250, in <module>
train_pipeline(root_path)
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 132, in train_pipeline
model = build_model(opt)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/__init__.py", line 26, in build_model
2023-12-13 17:33:40,327 INFO: Using static graph. Make sure that "unused parameters" will not change during training loop.
model = MODEL_REGISTRY.get(opt['model_type'])(opt)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 39, in __init__
self.init_training_settings()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/sr_model.py", line 70, in init_training_settings
self.setup_optimizers()
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 104, in setup_optimizers
Traceback (most recent call last):
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 250, in <module>
self.net_g = self.model_to_device(self.net_g)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 60, in model_to_device
net._set_static_graph()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 948, in __getattr__
type(self).__name__, name))
Traceback (most recent call last):
AttributeError: File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 250, in <module>
'DistributedDataParallel' object has no attribute '_set_static_graph'
train_pipeline(root_path)
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 132, in train_pipeline
model = build_model(opt)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/__init__.py", line 26, in build_model
train_pipeline(root_path) model = MODEL_REGISTRY.get(opt['model_type'])(opt)
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 132, in train_pipeline
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 39, in __init__
self.init_training_settings()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/sr_model.py", line 70, in init_training_settings
model = build_model(opt)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/__init__.py", line 26, in build_model
self.setup_optimizers()
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 104, in setup_optimizers
model = MODEL_REGISTRY.get(opt['model_type'])(opt)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 39, in __init__
self.net_g = self.model_to_device(self.net_g)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 60, in model_to_device
self.init_training_settings()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/sr_model.py", line 70, in init_training_settings
net._set_static_graph()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 948, in __getattr__
self.setup_optimizers()
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 104, in setup_optimizers
self.net_g = self.model_to_device(self.net_g)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 60, in model_to_device
net._set_static_graph()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 948, in __getattr__
type(self).__name__, name))
AttributeError: 'DistributedDataParallel' object has no attribute '_set_static_graph'
type(self).__name__, name))
AttributeError: 'DistributedDataParallel' object has no attribute '_set_static_graph'
Traceback (most recent call last):
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 250, in <module>
train_pipeline(root_path)
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 132, in train_pipeline
model = build_model(opt)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/__init__.py", line 26, in build_model
model = MODEL_REGISTRY.get(opt['model_type'])(opt)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 39, in __init__
self.init_training_settings()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/sr_model.py", line 70, in init_training_settings
self.setup_optimizers()
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 104, in setup_optimizers
self.net_g = self.model_to_device(self.net_g)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 60, in model_to_device
net._set_static_graph()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 948, in __getattr__
type(self).__name__, name))
AttributeError: 'DistributedDataParallel' object has no attribute '_set_static_graph'
THPModule_npu_shutdown success.
THPModule_npu_shutdown success.
THPModule_npu_shutdown success.
THPModule_npu_shutdown success.
Killing subprocess 25590
Killing subprocess 25591
Killing subprocess 25592
Killing subprocess 25593
Traceback (most recent call last):
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/distributed/launch.py", line 340, in <module>
main()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/distributed/launch.py", line 326, in main
sigkill_handler(signal.SIGTERM, None) # not coming back
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/distributed/launch.py", line 301, in sigkill_handler
raise subprocess.CalledProcessError(returncode=last_return_code, cmd=cmd)
subprocess.CalledProcessError: Command '['/home/ma-user/anaconda3/envs/Pytorch-1.8.1/bin/python', '-u', '/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py', '--local_rank=3', '-opt', '/home/ma-user/work/main/IART-main/options/IART_REDS_N16_600K.yml', '--launcher', 'pytorch']' died with <Signals.SIGSEGV: 11>.
请教大佬 这属于什么问题 属于版本问题吗
点赞
收藏
回复
分享
举报
已解决
Traceback (most recent call last):
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 250, in <module>
train_pipeline(root_path)
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 132, in train_pipeline
model = build_model(opt)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/__init__.py", line 26, in build_model
2023-12-13 17:33:40,327 INFO: Using static graph. Make sure that "unused parameters" will not change during training loop.
model = MODEL_REGISTRY.get(opt['model_type'])(opt)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 39, in __init__
self.init_training_settings()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/sr_model.py", line 70, in init_training_settings
self.setup_optimizers()
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 104, in setup_optimizers
Traceback (most recent call last):
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 250, in <module>
self.net_g = self.model_to_device(self.net_g)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 60, in model_to_device
net._set_static_graph()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 948, in __getattr__
type(self).__name__, name))
Traceback (most recent call last):
AttributeError: File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 250, in <module>
'DistributedDataParallel' object has no attribute '_set_static_graph'
train_pipeline(root_path)
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 132, in train_pipeline
model = build_model(opt)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/__init__.py", line 26, in build_model
train_pipeline(root_path) model = MODEL_REGISTRY.get(opt['model_type'])(opt)
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 132, in train_pipeline
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 39, in __init__
self.init_training_settings()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/sr_model.py", line 70, in init_training_settings
model = build_model(opt)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/__init__.py", line 26, in build_model
self.setup_optimizers()
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 104, in setup_optimizers
model = MODEL_REGISTRY.get(opt['model_type'])(opt)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 39, in __init__
self.net_g = self.model_to_device(self.net_g)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 60, in model_to_device
self.init_training_settings()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/sr_model.py", line 70, in init_training_settings
net._set_static_graph()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 948, in __getattr__
self.setup_optimizers()
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 104, in setup_optimizers
self.net_g = self.model_to_device(self.net_g)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 60, in model_to_device
net._set_static_graph()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 948, in __getattr__
type(self).__name__, name))
AttributeError: 'DistributedDataParallel' object has no attribute '_set_static_graph'
type(self).__name__, name))
AttributeError: 'DistributedDataParallel' object has no attribute '_set_static_graph'
Traceback (most recent call last):
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 250, in <module>
train_pipeline(root_path)
File "/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py", line 132, in train_pipeline
model = build_model(opt)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/__init__.py", line 26, in build_model
model = MODEL_REGISTRY.get(opt['model_type'])(opt)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 39, in __init__
self.init_training_settings()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/basicsr/models/sr_model.py", line 70, in init_training_settings
self.setup_optimizers()
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 104, in setup_optimizers
self.net_g = self.model_to_device(self.net_g)
File "/home/ma-user/work/main/IART-main/models/recurrent_mixprecision_model.py", line 60, in model_to_device
net._set_static_graph()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 948, in __getattr__
type(self).__name__, name))
AttributeError: 'DistributedDataParallel' object has no attribute '_set_static_graph'
THPModule_npu_shutdown success.
THPModule_npu_shutdown success.
THPModule_npu_shutdown success.
THPModule_npu_shutdown success.
Killing subprocess 25590
Killing subprocess 25591
Killing subprocess 25592
Killing subprocess 25593
Traceback (most recent call last):
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/distributed/launch.py", line 340, in <module>
main()
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/distributed/launch.py", line 326, in main
sigkill_handler(signal.SIGTERM, None) # not coming back
File "/home/ma-user/anaconda3/envs/Pytorch-1.8.1/lib/python3.7/site-packages/torch/distributed/launch.py", line 301, in sigkill_handler
raise subprocess.CalledProcessError(returncode=last_return_code, cmd=cmd)
subprocess.CalledProcessError: Command '['/home/ma-user/anaconda3/envs/Pytorch-1.8.1/bin/python', '-u', '/home/ma-user/work/main/IART-main/recurrent_mix_precision_train.py', '--local_rank=3', '-opt', '/home/ma-user/work/main/IART-main/options/IART_REDS_N16_600K.yml', '--launcher', 'pytorch']' died with <Signals.SIGSEGV: 11>.
请教大佬 这属于什么问题 属于版本问题吗