|
楼主 |
发表于 2022-10-1 04:05:55
|
显示全部楼层
本帖最后由 迷失的翼 于 2022-10-1 04:06 编辑
我有换个了版本
现在提示这个错误,但是我已经装了cuda10.1了,你知道这个怎么解决吗?
Traceback (most recent call last):
File "demo.py", line 88, in <module>
processer = FaceEnhancement(in_size=args.in_size, model=args.model, use_sr=args.use_sr, sr_model=args.sr_model, channel_multiplier=args.channel_multiplier, narrow=args.narrow, key=args.key, device='cuda' if args.use_cuda else 'cpu')
File "G:\GPEN2048_1修復\face_enhancement.py", line 18, in __init__
self.facedetector = RetinaFaceDetection(base_dir, device)
File "G:\GPEN2048_1修復\face_detect\retinaface_detection.py", line 28, in __init__
self.net = self.net.to(device)
File "G:\GPEN2048_1修復\_internal\Python37\lib\site-packages\torch\nn\modules\module.py", line 852, in to
return self._apply(convert)
File "G:\GPEN2048_1修復\_internal\Python37\lib\site-packages\torch\nn\modules\module.py", line 530, in _apply
module._apply(fn)
File "G:\GPEN2048_1修復\_internal\Python37\lib\site-packages\torch\nn\modules\module.py", line 530, in _apply
module._apply(fn)
File "G:\GPEN2048_1修復\_internal\Python37\lib\site-packages\torch\nn\modules\module.py", line 552, in _apply
param_applied = fn(param)
File "G:\GPEN2048_1修復\_internal\Python37\lib\site-packages\torch\nn\modules\module.py", line 850, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
File "G:\GPEN2048_1修復\_internal\Python37\lib\site-packages\torch\cuda\__init__.py", line 172, in _lazy_init
torch._C._cuda_init()
RuntimeError: CUDA driver initialization failed, you might not have a CUDA gpu.
|
|