Seokeon Choi

Results 4 comments of Seokeon Choi

Unfortunately, the number of images for training on the A Large-Scale ReID benchmark exceeds 100,000, which takes a long time to train. We recommend that you do a cross-domain re-id...

I'm not sure where the bottleneck is. If you want to get results faster, please stop learning early or experiment on a smaller benchmark.

Multi-gpu is not currently supported. I may update later, but I don't know when.

I'm researching this work, so I agree with the importance of maintaining benchmarks. However, I am immersed in research and try to post benchmarks a little later.