It seems your code does not match your description of your workshop paper.

layumi / AICIty-reID-2020

:red_car: The 1st Place Submission to AICity Challenge 2020 re-id track (Baidu-UTS submission)

MIT License

449 stars 109 forks source link

It seems your code does not match your description of your workshop paper. #4

Closed greathope closed 4 years ago

greathope commented 4 years ago

I have read your paper and code roughly, but have few questions. Your code used SE-ResNeXt101, but ResNeXt101 in your paper; your code did not use Block3; your learning rate is 0.02 instead 0.01 in your paper; the lr scheduler is MultiStepLR instead Cosine; the feature dim is 4092 instead 1024; May I ask why?

greathope commented 4 years ago

ok, I found it in your paddlepaddle code, so I just close it.

layumi commented 4 years ago

Thanks @greathope . We have tried different training methods and then combined the trained model. In the paper, we mainly report the method to train the best single model (based on validation score).