Willy Fitra Hendria

+1

+1

> @willyfh, is this ready for the review? @samet-akcay I have implemented the MVTec Loco dataset and SPRO metric, and I have added the unit test for both. However, I...

> This PR is already big, I think it would also be easier for the reviewers if you auspro is a separate one @samet-akcay ah, I see. Okay, I will...

> @willyfh , I would be very interested in getting the AUsPRO metric working. I would be happy to collaborate with you on this one if you're willing to :)...

Now this PR is ready for review :) @samet-akcay

Thanks, @samet-akcay, for your comments and questions. I've provided responses to them. For some, before moving forward with any changes, I'd appreciate your confirmation on certain points. Also, I would...

@blaz-r thanks for your comments and questions! There is an important point that would be changed based on the discussions. The merged tensor for the multi masks, i.e., `masks`, seems...

@jpcbertoldo thanks for your comments! I have provided responses to them. I have managed to pass list of tensor from the dataset to the metrics. I have few questions. >I'm...

> Image size stays the same, because the image loaded is still in its original size, same with the final anomaly map. The models that support tiling will then use...