search

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

How does this model install the environment #21

Open Kayce001 opened 1 year ago

Kayce001 commented 1 year ago

I got 1308629 segmentation fault (core dumped) when i run Main.py

zoubohao commented 1 year ago

Hi Kayce

You can set the parameter "device" in the Main.py as "cuda:0" or "CPU".

Kayce001 commented 1 year ago

Hi Kayce

You can set the parameter "device" in the Main.py as "cuda:0" or "CPU".

Not only this problem, it is best to write an installation environment document

38green commented 3 weeks ago

I can run the Main.py in the environment with python=3.8 and pytorch=2.4.0