can i use it to denoise the feature map,like after the cifar-10 through a channel encoder,and then it will output a feature map,can i use it to train the diffusion model(Unet)

zoubohao / DenoisingDiffusionProbabilityModel-ddpm-

This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.

MIT License

1.48k stars 156 forks source link

can i use it to denoise the feature map,like after the cifar-10 through a channel encoder,and then it will output a feature map,can i use it to train the diffusion model(Unet) #35

Open 11langalang opened 8 months ago

11langalang commented 8 months ago

can i use it to denoise the feature map,like after the cifar-10 through a channel encoder,and then it will output a feature map,can i use it to train the diffusion model(Unet) #35

zoubohao commented 4 months ago

I do not understand your question exactly. I think it is ok to do it. But the result of generating may not an image.