Xuanchi Ren

> Dear Wrong Wang, > > Thank you for your interest in our work. We will upload the codes about AD in the next few days. > > Best Wishes,...

In my view, as the authors state in the paper, they make the longer side of the coarsest image to be 25px, and actually all the discriminator's receptive field is...

@dianshan14 Yes. The patch is actually what a patch discriminator can see.

@xinhong-ho Actually I don't see this sentence. The caption of figure 9 is "A model with a small number of scales only captures textures. As the number of scales increases,...

Hi, Sorry for the late reply. 1. You can use your own music. You just need to read your own music file (Mono is required) and reshape it to (XX,50,1600)....

Hi, the upper and the lower is ground truth and generated. And you can refer to ./dataset/dataset_usage.ipynb to see the details of the Json file I provide. And you just...

> Hi, what does 1600 mean? 16000 hz per second and we have 1600 hz per 0.1 second.

> > Hi, > > Sorry for the late reply. > > > > 1. You can use your own music. You just need to read your own music file...

> could you give me some audio samples?thanks Hi, I think you can use the samples of the json files as I provided. Or I think you can use your...

@wtnan2003 Please refer to [dataset_usage](https://github.com/xrenaa/Music-Dance-Video-Synthesis/blob/master/dataset/dataset_usage.ipynb). This is the structure of the json file and indicates how to load the json file. Acutally, you can just split the music and openpose...