I am sorry to trouble you but i am actually a juinor at a University in China who are learning and researching in diffusion model, i found that in the paper you don't give a clear direction of how to use cluster method to get the mean and std of Gaussians of the dataset, i am not so experienced so i am quite confused and don't know how to do it.
Can you give me a hand and show me how to do it through clustering method?
Also, in the code you gave, the Accelerate has some problems, because the update, some of the name of the variables in the train.py are deprecated, like "logging_dir" should be “project_dir”.
I am sorry to trouble you but i am actually a juinor at a University in China who are learning and researching in diffusion model, i found that in the paper you don't give a clear direction of how to use cluster method to get the mean and std of Gaussians of the dataset, i am not so experienced so i am quite confused and don't know how to do it. Can you give me a hand and show me how to do it through clustering method? Also, in the code you gave, the Accelerate has some problems, because the update, some of the name of the variables in the train.py are deprecated, like "logging_dir" should be “project_dir”.