search

Julian-Wyatt / AnoDDPM

CVPR Workshop paper - AnoDDPM: Anomaly Detection with Denoising Diffusion Probabilistic Models using Simplex Noise
https://julianwyatt.co.uk/anoddpm
MIT License
154 stars 27 forks source link

about the training time cost #24

Closed Henry0528 closed 7 months ago

Henry0528 commented 11 months ago

First thank you for your excellent work. I have the question that how long did it take to train the model. I used the same GPU (Titan XP) as mentioned in the paper, and it took me more than one day to train the model on the single subset "leather" on the MVTec dataset. Can I do changes to accelerate my training?

  1. I try to change the batch size since I find there's still a lot of memory room on GPU but facing some code error. It seems something in simplex noise code only support batchsize=1
  2. I want to reduce the epoch which is now 3000 to 500 to reduce the training time, but I have no idea whether it will do harm to the final performance
Julian-Wyatt commented 10 months ago

Hi Henry

Due to time constraints when originally working on the project I wasn't able to fix those. If you're able to increase the batch size, it should speed the model up; further 500 epochs should give good outputs but not necessarily perfect if memory serves.