emma-sjwang / beal Goto Github PK

I am very sorry, but there is still a problem that bothers me. The input of the test.py script is 800 and Rescale is not executed. Will this affect the results?

When processing target domain dataset(Drishti-GS or RIM-ONE-r3), the mask is different from REFUGE dataset. How to process it? Did you have preprocessing steps? Thanks so much!!!

I have trained the model for several times, while the results are poorer than the paper's.

Thanks for your work. There was a problem with downloading the weights. Is it now possible to download the weights? Or is it my network transmission? I look forward to hearing from you...

Hello, I am more interested in your code, but among the three datasets, the refuge dataset is not available for download right now. Do you have a ready-made dataset?

您好，为什么论文里说没有使用warmup？按照代码里写的，没有使用warmup的话，那么就无法训练判别器了。我看您给的python命令里也没有给warmup-epoch这个参数赋值。
祝好！

I wonder where you defined optim_adv in train.py. Thanks for sharing the source.

Thanh

When training the refuge dataset, the loss_adv does not converge.

Hello, do you mind giving the groundtruth of the REFUGE2018 Glaucoma validation set, the link to Baidu Brain is broken.