MagicSource

I have trained about 1000 epochs, not fully trained, but the result seems impressive. I upload several examples on Mandrain, for anyone interested: [中文语音合成实例.zip](https://github.com/jaywalnut310/vits/files/7939548/default.zip)

@otaheri when will it be released?

@ZwwWayne thank u. it would be better add vis support since we want see it's visualization result to verify the mask quality.

Thanks, this work is very meaningfull, cause original can not even predict single image, If you worked out, update repo let me know, I'd like to follow this project.

@ Would you add some test image result for current made? Have some sample result could be better I think.

I have trained original summer2winter and apple2orange, both get in some level fair result, at least the resolution are more clear.

@vanhuyz Hi, I also managed predict using original torch version and reconstruct a production version, here is the repo https://github.com/jinfagang/pytorch_cycle_gan, I have some results, seems original still more clear, what...

This is my email [email protected], you can send me some information

BTW, the original prototxt 1 and 2 has different num_class: 1： ``` layer { name: "mask_score" type: "Convolution" bottom: "pool5_2_conv6_relu" # top: "mask_score" param { lr_mult: 1.0 decay_mult: 1.0 }...

What's the first prototxt 18 stands for? Isn't that only 1 class? What if wanna training on 2 or more classes?