search

ai-med / relaynet_pytorch

Pytorch Implementation of retinal OCT Layer Segmentation (with trained models)
MIT License
87 stars 30 forks source link

about dataset #1

Closed zhewang95 closed 6 years ago

zhewang95 commented 6 years ago

Great job! But I have a problem about the 2015_BOE_Chiu dataset, when I load the Subject_0x.mat file into matlab R2017a, all the variables are NaN. Do any one has idea about that?

zhewang95 commented 6 years ago

Oh, turns out that not all the numbers are NaN.

hwei-hw commented 6 years ago

Hello！@abhi4ssj I have some doubt in the process of data when I implement it and hope to get your reply. The dataset consists of 110 annotated SD-OCT B-scan images obtained from 10 patients suffering from DME (11 B-scans per patient) and you split the dataset into non-overlapping subsets of 8 patients for training and held out 2 patients for testing. That's means we have 7 patients for training, 1 patient for validation and 2 patients for testing? And if yes, I don't know whether you can tell me which 2 patients are used for testing? I will be very grateful if you can help me and I will cite your paper in the next work.

ZeyuFu commented 5 years ago

@Atomwh can I ask how did you get the gt_id.mat file?