nagadomi
nagadomi
Older pre-trained models do not have `groups`. This fix has been deleted in 84811a509c2bef04909d1b36cfe1375aaef3181f but it is necessary.
Porting from https://github.com/tesseract-ocr/tesseract/pull/3434 (not merged) . >This Pull Request adds --vertical_fontlist option to tesstrain.sh to specify a list of fontnames to render vertical text. >The format for specifying a list...
from https://github.com/nagadomi/nunif/discussions/28#discussioncomment-7247459 >i have 2 gpus. >Haw can i use all gpu in iw3?
### 🐛 Describe the bug ```python import torch import torch.nn as nn from torch.nn.utils.parametrizations import spectral_norm model = spectral_norm(nn.Linear(3, 3)).cuda() x = torch.zeros((4, 3)).cuda() with torch.autocast(device_type="cuda"): model(x) ``` ``` File...
> I can't reproduce PSNR of bicubic in the paper, Long time ago, I also has the same problem for reproducing superresolution papers. This problem caused by [MATLAB's rgb2ycbcr](https://jp.mathworks.com/help/images/ref/rgb2ycbcr.html?lang=en) for...
### Discussed in https://github.com/nagadomi/nunif/discussions/157 Maybe the current implementation uses BT.601 for yuv420p/yuv444p. Since HD MP4 generally uses BT.709, the color conversion may not be correct. Maybe color_range (pc/tv) is also...
iw3 does not handle metric depth result properly. This is because the results of all models are min-max normalized once and go through many common processing steps. Also, note that...
### 🐛 Describe the bug From https://github.com/pytorch/vision/issues/8587#issuecomment-2849264295 encode_jpeg sometimes generates corrupted JPEG data in multi-threaded environments when passing CUDA tensors. minimal reproducible example ```python import torch import torch.nn as nn...
I think this is a rare case, when the source video's SAR (Sample Aspect Ratio) is not 1:1, it is not copied to the output video, which causes the aspect...