Closed FlyHighest closed 6 years ago
Hi @FlyHighest Do you change the baseline code? I notice that the small batchsize can improve the result.
Thanks for your reply. i change batch size to 10. But the same batch size (10) fails to improve LSRO. I got rank1 0.7993.
@FlyHighest It is possible. We also notice this observation. It also appears in this ICLR paper. For some small datasets, small batchsize can do help to aviod the overfitting.
In fact, we are planning to discuss and investigate the result in our journal paper. P.S. On CUBird dataset, LSRO still works.
Thank you for your kindly attention.
Thank you. It helps a lot. I'm looking forward to your new papers.
I use train_id_net_res_market_new , without GAN data, dataset Market1501, and the final result is r1-5: 0.8216 0.8679 0.8934 0.9068 0.9192 mAP : 0.6038. The evaluation code is '*faster', single query. Is there anyone else who has run the baseline code?