yxgeee / MMT

[ICLR-2020] Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification.
https://yxgeee.github.io/projects/mmt
MIT License
473 stars 72 forks source link

A question about precision #43

Open CCA8290 opened 3 years ago

CCA8290 commented 3 years ago

I ran your source code (DBSCAN) directly, All hyperparameters follow the paper and Github repository, When using a Tesla V100, the highest accuracy on Duke-Market is mAP: 68.5%. When I use two 2080Ti, the accuracy reaches mAP: 73%. May I ask Why is this? Maybe BN? Maybe triplet loss? The conditions of the laboratory do not allow me to use multiple graphics cards all the time. I look forward to your reply.