QianYang

您好，遇到相同的问题。能否麻烦把下载链接发到邮箱 [email protected], 非常感谢

@zanghao2 Here is a simple implementation. Hope it helps. https://gist.github.com/QQQYang/e535f336813b44d72d3b1d6184bf4586

@chenfeima This is my train_cnn.prototxt. But I have not achieved good performance on my own dataset. Maybe it needs some fixes. If you find some errors in the prototxt file,...

@chenfeima I have updated the prototxt file to keep consistent with the RankLoss above. You can check the train.prototxt again.

@chenfeima My strategy is the same with you. I did not test on public datasets, but got poor performance on my own dataset. The RankLoss is written according to the...

@cocowf Yes, you have to compile them first on Linux. Feel free to use the train.prototxt.

@chenfeima I did not spend much time on adjusting hyperparameters. So I cannot give any advice. What I have done is preparing two train.prototxt with different learning rate respectively. In...

@lhCheung1991 I just tested on my own dataset.

Hi @VietTralala , I encountered the same issue. Have you solved the problem?

> hello,do you know that now? Environment of python 2.7, tensorflow 1.14.0, pytorch 1.1.0 and Matlab 2016b is okay to run the project