search

nuclearboy95 / Anomaly-Detection-PatchSVDD-PyTorch

246 stars 56 forks source link

Unable to reproduce results for 'leather' #27

Open yeeyangtee opened 9 months ago

yeeyangtee commented 9 months ago

Hello, thank you for the great work and release of trained model weights.

I have managed to run the evaluation script for the wood model and get around 0.95 Image AUROC and 0.92 pixel AUROC, similar to reported results in paper.

However, for the 'leather' model, I only get about 0.501 image AUROC and 0.773 pixel AUROC when using your trained weights. The reported numbers are based on det_64 and seg_64.

Do I need to put any specific settings to reproduce the results? Thanks

nuclearboy95 commented 9 months ago

Hi, thanks for your attention to my work.

AUROC of 0.5 seems like the output anomaly scores are close to random results. Could you check if the ckpt file is not overwritten and properly loaded?