Closed MinGiSa closed 1 month ago
Hello!
We used the pre-trained diffusion model provided by BeatGans for anomaly synthesis, so the resolution of the synthesis depends on BeatGans. If you want to train a 512*512 diffusion model, you need to download the weights from BeatGans and then modify the input_size
and unet(classifier) structure
in experiments/MVTec-AD/diffusion.yaml
and experiments/MVTec-AD/classifier.yaml
. The unet(classifier) structure
should refer to the settings in BeatGans.
@cnulab thank you !
Thank you for sharing your good work. By the way, is there a way to generate anomaly synthesis images in sizes other than 256x256, such as 512x512 or 512x1024?