hh23333
hh23333
> when i try to train model on CUHK-SYSU using muti gpus.mAP is 89.15,R1 is 89.79 without adjustment of any parameters. > After that, I tried the following > (1)...
Got it, Thanks!
> I have follow your code,but **it does not work on my GPU** it only run in CPU @miss-rain, hi, I meet the same problem. Have you solved it?
> * 没有在MOT的数据集上面测试过，但是在MOT的数据集上训练目标检测，效果比Crowdhuman差， > * 比FairMOT等one-stage的方法性能提升幅度巨大，一般来说私有检测器性能对跟踪影响最大，详细你可以观察一下MOT Public和Private赛道的精度对比。 > * 这个方案速度比较慢，推理FPS为5以下，即1S跑5张以下。 您好,想问一下,您没在MOT上测试过,是在什么数据集比FairMoT效果好的
@xjhjinhui @xiaoweihappy123 I also only got 49.73 rank1 accuracy on Parital-reID dataset and 57.14 rank1 on Partial-iLIDS. Have you ever explored any setting or solution to get the performance that...
Graph matching is not used in testing, the goal of graph matching is only to generate the pseudo-lable for training the visibility predictor. When testing, visibility score is calculated by...
@jpainam @chenxiangzZ Hi, About the data structure, I set root=PVPM_experiments/data, and there was no error report when I reproduced the experiment. For the experiment result, I reproduced it on my...
@jpainam The only reason I can think of is that the versions of python are different, which would make some operation get different results, for example, 2/3 get 0 in...
@jpainam @chenxiangzZ In order to find the reason for the low results, I reproduced the experiment on another device(ubuntu16.04, GPU2080Ti, and mine is ubuntu18.04 with GPU1080Ti) following the instruction in...
emmm...., I directly clone it to the new device. emmm.., Try to train the pvpm with my provided PCB baseline model directly?