Quande Liu

Results 7 comments of Quande Liu

> Do you understanding it now? I also can't figure it out at this moment. Hi, I also cannot figure it out, and am waiting for the reply. Hi @xuuuuuuchen,...

Dear Vivian, We downloaded the fundus data from [Fundus](https://github.com/EmmaW8/Dofe), which actually has contained the pre-processed (center-cropped) samples. We directly use the pre-processed data for experiments, in which the center-cropped ROI...

Hi Vivian, It seems that you directly resized the original images and labels to 384x384 for network training. In our experiments, the model was trained on the center-cropped ROI regions...

Hi, We did not adopt a validation split, i.e., we directly use the N-1 dataset for training and the remaining one for testing. Thanks, Quande.

Hi @Ezra-Yu ~ Sorry for the late reply. Yes, the problem has been well resoved, many thanks for your help! I shall close this issue. Best.

Hi @rohaantahir , I also met the same question, have you solved it?

Hi, Since different datasets could present large distribution shifts, the model obtained from the validation set in training domains often cannot perform well on the testing domain. We therefore directly...