-
Notifications
You must be signed in to change notification settings - Fork 707
Closed
Description
Thanks for your bug report. We appreciate it a lot.
Checklist
- I have searched related issues but cannot get the expected help.
- I have read the FAQ documentation but cannot get the expected help.
- The bug has not been fixed in the latest version.
Describe the bug
On windows 10, then convert a model or test a model with some config, the process may fail.
Reproduction
With below setting when convert a model
MODEL_CFG=$MMSEG/configs/fcn/fcn_r18-d8_512x1024_80k_cityscapes.py
MODEL_PTH=$PTH_DIR/fcn_r18-d8_512x1024_80k_cityscapes_20201225_021327-6c50f8b4.pth
Environment
Windows 10, nvidia 2070s, torch1.8.1+cu111
Error traceback
Traceback (most recent call last):
File "<string>", line 1, in <module>
File "C:\Users\cx\miniconda3\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "C:\Users\cx\miniconda3\lib\multiprocessing\spawn.py", line 125, in _main
prepare(preparation_data)
File "C:\Users\cx\miniconda3\lib\multiprocessing\spawn.py", line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\cx\miniconda3\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File "C:\Users\cx\miniconda3\lib\runpy.py", line 265, in run_path
return _run_module_code(code, init_globals, run_name,
File "C:\Users\cx\miniconda3\lib\runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "C:\Users\cx\miniconda3\lib\runpy.py", line 87, in _run_code
exec(code, run_globals)
File "E:\pjlab\dev-v0.4.0\tools\test.py", line 4, in <module>
from mmcv import DictAction
File "C:\Users\cx\miniconda3\lib\site-packages\mmcv\__init__.py", line 4, in <module>
from .fileio import *
File "C:\Users\cx\miniconda3\lib\site-packages\mmcv\fileio\__init__.py", line 2, in <module>
from .file_client import BaseStorageBackend, FileClient
File "C:\Users\cx\miniconda3\lib\site-packages\mmcv\fileio\file_client.py", line 15, in <module>
from mmcv.utils.misc import has_method
File "C:\Users\cx\miniconda3\lib\site-packages\mmcv\utils\__init__.py", line 22, in <module>
import torch
File "C:\Users\cx\miniconda3\lib\site-packages\torch\__init__.py", line 123, in <module>
raise err
OSError: [WinError 1455] 页面文件太小,无法完成操作 Error loading "C:\Users\cx\miniconda3\lib\site-packages\torch\lib\cudnn_cnn_infer64_8.dll" or one of its dependencies
Bug fix
Found the link which describe a similar error.
https://stackoverflow.com/questions/64837376/how-to-efficiently-run-multiple-pytorch-processes-models-at-once-traceback
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels