Closed xuanli98 closed 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.
Thank you very much
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: In ADAM dataset: 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.