search

qiaoguan / Person-reid-GAN-pytorch

A Pytorch Implementation of "Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro"(ICCV17)
158 stars 49 forks source link

Why the performance on single gpu is relatively better than multi gpus? #10

Closed zeyu-liu closed 6 years ago

zeyu-liu commented 6 years ago

As the results listed on the table, single gpu training is almost better than multi gpus (with same settings of re-rank/data). So, is this caused by BN? (smaller batchsize may results in more variance)

qiaoguan commented 6 years ago

i think BN is one reason , another reason is pytorch's own problem, its still not perfect enough, some engineering optimizations are not good enough