This is the codebase for Removing Anomalies as Noises for Industrial Defect Localization.
This repository is based on openai/guided-diffusion. Please refer to the vanilla installation.
- Pretrained 256x256 guided-diffusion model: 256x256_diffusion.pt
Put your MVTecAD dataset in the ./data/MVTecAD folder.
For MVTecAD examples, run
bash train.sh MVTecAD $catogory 64
To test the AUROC/AUPRO performance of trained models, run
bash test.sh $category