mirror of
https://github.com/TencentARC/GFPGAN.git
synced 2026-04-18 20:00:54 +00:00
unexpected EOF, expected 273069 more bytes. #240
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @YosAwed on GitHub (Aug 29, 2022).
Hello,
I updated latest source code, but still I have an issue. I tried all three version pretrain data (V1, V1.2, V1.3) but all data was corrupted?
Any thought?
(base) PS C:\Users\xxxxx\gfpgan> python inference_gfpgan.py -i inputs\whole_imgs -o results -v 1.3 -s 2
Traceback (most recent call last):
File "inference_gfpgan.py", line 155, in
main()
File "inference_gfpgan.py", line 103, in main
restorer = GFPGANer(
File "C:\Users\xxxxx\gfpgan\gfpgan\utils.py", line 76, in init
self.face_helper = FaceRestoreHelper(
File "C:\Users\xxxxx\anaconda3\envs\base\lib\site-packages\facexlib\utils\face_restoration_helper.py", line 98, in init
self.face_det = init_detection_model(det_model, half=False, device=self.device)
File "C:\Users\xxxxx\anaconda3\envs\base\lib\site-packages\facexlib\detection_init_.py", line 20, in init_detection_model
load_net = torch.load(model_path, map_location=lambda storage, loc: storage)
File "C:\Users\xxxxx\anaconda3\envs\base\lib\site-packages\torch\serialization.py", line 713, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "C:\Users\xxxxx\anaconda3\envs\base\lib\site-packages\torch\serialization.py", line 938, in _legacy_load
typed_storage._storage._set_from_file(
RuntimeError: unexpected EOF, expected 273069 more bytes. The file might be corrupted.
@YosAwed commented on GitHub (Aug 31, 2022):
The file size of GFPGANv1.3.pth : 348,632,874 bytes. I got this file many times, but it seems to be same.
@Evilom commented on GitHub (Aug 31, 2022):
i got the same problem, waiting for the resolution
@YosAwed commented on GitHub (Sep 1, 2022):
Hi! I found the cause. The problem caused by insufficient downloading data in
:\Users\username\anaconda3\envs\ldo\Lib\site-packages\facexlib\weights
Here are
detection_Resnet50_Final.pth : 109,497,761 bytes
parsing_parsenet.pth : 85,331,193 byes
Please check the file size. If it is lower than above value. You can download these files directly from
https://github.com/xinntao/facexlib/releases/download/v0.2.2/
I downloaded form above URL and it worked.
@huozhong-in commented on GitHub (Sep 1, 2022):
I'm using torch-nightly build for "mps" GPU mode, that file must not the same size...
File "/opt/homebrew/Caskroom/miniconda/base/envs/ldm/lib/python3.10/site-packages/torch/serialization.py", line 989, in _legacy_load typed_storage._storage._set_from_file( RuntimeError: unexpected EOF, expected 132688554 more bytes. The file might be corrupted.please change the method for torch version detection.
@Evilom commented on GitHub (Sep 1, 2022):
this problem occured when i use stable diffusion webUI,then i found the parsing_parsenet.pth in stable-diffusion-main\src\facexlib\facexlib\weights is less then 83332kb,and i download it from you url, and it works now, thanks