search

WentianZhang-ML / GatingAno

This is an official pytorch implementation of 'Anomaly Detection via Gating Highway Connection for Retinal Fundus Images'.
4 stars 0 forks source link

About train/test split for image-wise anomaly detection in ADAM dataset #1

Closed xuanli98 closed 7 months ago

xuanli98 commented 7 months ago

Thanks for your great work : Anomaly detection via gating highway connection for retinal fundus images. I have some questions about train/test split for image-wise anomaly detection in ADAM dataset. In your paper: image In ADAM dataset: image The train/test split of normal images (222/89) for image-wise anomaly detection in ADAM dataset could not be found in your code or the offical ADAM dataset. I think I must miss something. Would you like to help me figure out the question? Thank you very much.

WentianZhang-ML commented 7 months ago

Hi, sorry for the late reply.

We simply set "N0001"-"N0089" images in the Non-AMD folder as the test set and the rest as the training set, so as to keep the same IDs with files in the AMD folder.

Please feel free to contact me if you have any questions.

xuanli98 commented 7 months ago

Thank you very much