OSError: [WinError 1455] 页面文件太小,无法完成操作。

FCN网络遇到问题

D:\other_envs\FCNSS02\python.exe E:/deep_learn_code/13FCNSS/vision-bf843c664b8ba0ff49d2921237500c77d82f2d04/references/segmentation/train.py
Not using distributed mode
Namespace(aux_loss=False, batch_size=8, dataset='voc', device='cuda', dist_url='env://', distributed=False, epochs=30, lr=0.01, model='fcn_resnet101', momentum=0.9, output_dir='.', pretrained=False, print_freq=10, resume='', test_only=False, weight_decay=0.0001, workers=4, world_size=1)
Downloading http://172.30.240.3:8081/IXC97f0f51450af4e63474a491b34f4ccc9_10.10.56.2/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar to ../VOCdevkit/VOC2007/VOCtrainval_11-May-2012.tar
100.0%
Extracting ../VOCdevkit/VOC2007/VOCtrainval_11-May-2012.tar to ../VOCdevkit/VOC2007/
Using downloaded and verified file: ../VOCdevkit/VOC2007/VOCtrainval_11-May-2012.tar
Extracting ../VOCdevkit/VOC2007/VOCtrainval_11-May-2012.tar to ../VOCdevkit/VOC2007/
D:\other_envs\FCNSS02\lib\site-packages\torchvision\models\_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead.
  warnings.warn(
D:\other_envs\FCNSS02\lib\site-packages\torchvision\models\_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=None`.
  warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet101-63fe2227.pth" to C:\Users\Administrator/.cache\torch\hub\checkpoints\resnet101-63fe2227.pth
100.0%
Traceback (most recent call last):
  File "", line 1, in <module>
  File "D:\other_envs\FCNSS02\lib\multiprocessing\spawn.py", line 116, in spawn_main
    exitcode = _main(fd, parent_sentinel)
  File "D:\other_envs\FCNSS02\lib\multiprocessing\spawn.py", line 125, in _main
    prepare(preparation_data)
  File "D:\other_envs\FCNSS02\lib\multiprocessing\spawn.py", line 236, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "D:\other_envs\FCNSS02\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
    main_content = runpy.run_path(main_path,
  File "D:\other_envs\FCNSS02\lib\runpy.py", line 265, in run_path
    return _run_module_code(code, init_globals, run_name,
  File "D:\other_envs\FCNSS02\lib\runpy.py", line 97, in _run_module_code
    _run_code(code, mod_globals, init_globals,
  File "D:\other_envs\FCNSS02\lib\runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "E:\deep_learn_code\13FCNSS\vision-bf843c664b8ba0ff49d2921237500c77d82f2d04\references\segmentation\train.py", line 5, in <module>
    import torch
  File "D:\other_envs\FCNSS02\lib\site-packages\torch\__init__.py", line 129, in <module>
    raise err
OSError: [WinError 1455] 页面文件太小,无法完成操作。 Error loading "D:\other_envs\FCNSS02\lib\site-packages\torch\lib\shm.dll" or one of its dependencies.

解决方法:通过高级系统设置里面的高级修改虚拟内存大小。
OSError: [WinError 1455] 页面文件太小,无法完成操作。_第1张图片

OSError: [WinError 1455] 页面文件太小,无法完成操作。_第2张图片
注意:1 需要明白是那个驱动器,不要甚至错了。2 自定义大小需要根据可用大小进行设置。
OSError: [WinError 1455] 页面文件太小,无法完成操作。_第3张图片

你可能感兴趣的:(U-net,python,深度学习,人工智能)