ares123-CN

请问一下：1.代码中，Focal loss好像没有样本（标签）进行判断是否为正负样本来调整alpha的值？2.loss计算中好像只对置信度进行focal loss的计算损失值，那对分类概率可以使用focal loss来计算损失值吗？

can you tell me the model hyperparams(arch) of model v1

1

the pretrained model weights of model v1 have not the hyperparams(arch),like res_unet.MultiScaleResUNet(in_nc=101,out_nc=3,flat_layers=(2,2,2,2),ngf=128)

Hello, MarekKowalski. Thank you for this good work. now i want to swap source face to the target one. So should i create candide.npz of the target face. And Maybe...

train code and the performance of the testset

1

Hi! Could you release your train code?thank you in adcance! And tested the testset with your model ,the performance is not obvious

Minimum GPU VRAM for training

2

Amazing job, I wonder the minimum GPU VRAM for training, image size is 512 and batch size is one or two

about train code

1

Hi! Could you release the training code about your work? thank you in advance!