tyxsspa
tyxsspa
will you release your code meanwhile?
any one can explain lvlb_weight? thanks
@nttstar @SthPhoenix Hi can you explain why GN works for big face? I retrain scrfd_10g_bnkps with specific big face(occupying >80% of image) augumentation and add big face ~20% in each...
> > > > Hi, @tuoyuxiang @SthPhoenix > > I followed the guide above, but the model performance cannot be reproduced. The model performed well on widerface validation dataset, but...
Hi, the training dataset and code are being organized and will be released later.
Hello, the AnyText method itself is not language-specific. However, to be honest, the current model has been trained on a relatively small dataset and 99.7% are in English and Chinese....
Hi， the codes and documentation are being updated and tested now, please wait. This error occurs because you need to prepare the font file yourself, we recommend Arial Unicode MS,...
> even added the font, the same mistakes appeared Hi, please make sure the path and file name of your ttf is exactly: `AnyText/font/Arial_Unicode.ttf`
> PyTorch 2.0.1+cu118 with CUDA 1108 (you have 2.0.1+cpu) Hi, 检查下你安装的pytorch，是不是CPU版的？
Hi, expected in early December, please stay tuned.