minimal number of samples for stable training -> some issue

openai / improved-diffusion

Release for Improved Denoising Diffusion Probabilistic Models

MIT License

3.21k stars 482 forks source link

minimal number of samples for stable training -> some issue #63

Open NicolasNerr opened 1 year ago

NicolasNerr commented 1 year ago

Hi !

I was wondering if some people tested the diffusion training process with few images ( 1000 or less) and obtained good results ?

I am working with rare pathology images, and I have only 300 of them. I am seeing some unexpected behavior on the generated samples (lack of diversity, color shifts etc...) As far as I am aware, diffusion models work better with low training data points than GANs ?

Thank you

yug125lk commented 10 months ago

Hi, did you solve it? I trained with my custom dataset and got the same problem. My model was overfitted.

liuyisu commented 9 months ago

嗨，你解决了吗？我用我的自定义数据集进行了训练，遇到了同样的问题。我的模型过度拟合。

Hello, I am currently training on my own dataset, but at the beginning, I encountered the following problem. May I ask how to solve it? Thank you very much RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.