XINXIN GE

Hi, I saw some parameters in your 'hparams.py', including min_level_db, ref_level_db, fmin and fmax. You said that we should increase or decrease the value based on the dataset. I want...

Hi, I am interested in your paper and work. However, I cannot find any code related to hair classification that has been described in your paper. Could you please share...

About training code

19

Great job! We want to train the network based on our own datasets, could you please tell us when you will release the training code of Audio2exp or Audio2Pose?

Expression transfer

2

Hi, I am quite impressed by your work. The results are amazing on face swapping. I looked many images that shown on your project homepage. But I have some issues...

Hi, thanks for sharing this excellent work. I want to train this work on my own dataset, Can u tell me how the loss changes during training and testing? I'm...

Test on chinese videos

1

I tried my own videos based on the Colab. The result seems not correct. Do you have any suggestions if I want to train it based on my own datasets?

Missing 'wider_face_train_bbx_gt.txt'

2

您好，感谢您分享并开源了此项技术！我遇到一些棘手的问题，我已下载您提供的数据集。但当我运行'python data/convert.py'，它出现了Error('FileNotFoundError: [Errno 2] No such file or directory: 'wider_face_split/wider_face_train_bbx_gt.txt''). 期待您的回复并告知我数据预处理的流程及输入网络要求的图片尺寸方便我使用自己的数据集进行测试！

Thanks for sharing your great work! When I tried the ipynb file 'xvector_ext_and_lda_scatter.ipynb', the output of net_xvec is NaN. Can u help me to address this issue?

Test with my own images

1

Hi, thanks for sharing your code with us. When I utilize your pretrained model, the code does not work. It said that 'DataLossError (see above for traceback): Unable to open...

I can get the UV map using Densepose but I need the body coordinates. Can u share the preprocessing code?