DCT-NET.Pytorch
DCT-NET.Pytorch copied to clipboard
unofficial implementation of DCT-Net: Domain-Calibrated Translation for Portrait
十分感谢你的贡献,但我有几个问题想要咨询一下。 我发现你在训练ccn的时候没有做论文中提到的blend操作,Geometry expansion module我也没有找到,这是有什么原因吗? 另外论文作者提到他用相同的模型对头部和背景进行了两次推理,只是对头部模型进行了额外的优化,但在你复现中似乎只有一个模型并且只做了一次推理,是有什么改动吗? 另外show中展示的效果似乎不是很好,有更好的效果图可以分享一下吗?谢谢
Hi @LeslieZhoa ! How can you compare the dictionary and the float? https://github.com/LeslieZhoa/DCT-NET.Pytorch/blob/b303f416c2caf05114fd38f10b0570df903b4462/trainer/ModelTrainer.py#L124 This method is called here: https://github.com/LeslieZhoa/DCT-NET.Pytorch/blob/b303f416c2caf05114fd38f10b0570df903b4462/trainer/ModelTrainer.py#L96 But the val_loss obtained in CCNTrainer.evalution is an empty dictionary: https://github.com/LeslieZhoa/DCT-NET.Pytorch/blob/b303f416c2caf05114fd38f10b0570df903b4462/trainer/CCNTrainer.py#L196-L206...
thanks. a nice work!
What is the image size used for training CCN, Why can't the matrix be multiplied when I input 1024 in training, and The problem of ' 'Nan or Inf found...
生成人脸都比较好,就是处理整图背景表现出有一块一块的黑色的
 Are the following training results correct? Can the CCN stage be directly adopted https://github.com/rosinality/stylegan2-pytorch? to train, or what changes did you make in the CCN stage In...
Trained for 9 epochs, 4000 times,  
   What's the matter with these black heads?
非常感谢作者伟大的工作,我尝试用ttn代码训练(ccn,face expression estimator等都没发现啥问题),大概训练了50epoch,但是效果不太理想。是训练时间过短还是有其他原因。