唐孟 comments

Results 4 comments of


                                            唐孟

Training code or references for training the latent diffusion model on a custom dataset

Have find the suitable training code?We can have a communication. Thanks a lot!

Some of the results are full of noise.

> I had the same issue when I adopted the colorization data loader to my own MR Image translation task. When I removed the normalization in the transforms, the noise...

Whether to use a lr scheduler when training from the scratch?

Hello, you can solve your problem like this. Write code in class Palette(BaseModel): self.optG = torch.optim.Adam(list(filter(lambda p: p.requires_grad, self.netG.parameters())), **optimizers[0]) self.optimizers.append(self.optG) ******************* from torch.optim.lr_scheduler import LambdaLR self.scheduler = LambdaLR(self.optG, lr_lambda=lambda...

question about NAN

> When I train the model with learning rate:0.0001,after several echos,I got "d_loss: nan, g_loss: nan" ,how can I deal with this situation? > Thanks a lot! I meet the...