chengyiqiu1121
chengyiqiu1121
Hello, Do you figure it out? I have the same question too. I don't know which paper should I read:(
man what can I say😫 recently I suffer this to
> you can try `p2_loss_weight_gamma = 1. `, my result with cifar10 wasn't great either with the default setting but I think you can see a big difference with p2...
> I am faced with the similar problem. Maybe you can try to set the hyper-parameters as the original paper DDPM's. Through this way I get a little better performance,...