Open-SCPNet
Open-SCPNet copied to clipboard
Code re-implement for SCPNet
您好!想询问一下,训练过程中的batch_size是trainset.py中的定义为ids_per_batch?还是ids_per_batch和ims_per_id的乘积?谢谢!
while only test my model, i got "keys not found" error, and then mAP & rank1 are very low as a result. even when i do not try to do...
我感觉Partial REID是制作的数据集,感觉好像看到了罗大佬- -,那个Partial-iLIDS感觉是机场视频取帧制作的数据集。所有应该不算是公开哪种能下载到的。
python script/dataset/combine_trainval_sets.py --market1501_im_dir ./Dataset/market1501/images --market1501_partition_file ./Dataset/market1501/partitions.pkl --cuhk03_im_dir ./Dataset/cuhk03/detected/images --cuhk03_partition_file ./Dataset/cuhk03/detected/partitions.pkl --duke_im_dir ./Dataset/duke/images --duke_partition_file ./Dataset/duke/partitions.pkl --save_dir ./Dataset/market1501_cuhk03_duke Traceback (most recent call last): File "script/dataset/combine_trainval_sets.py", line 140, in combine_trainval_sets(im_dirs, partition_files, save_dir) File...
i train the model with your code on combined dataset,when i try to test on single dataset,it occurs size mismatch bug
in this paper, performance like this:  however, in README.md  so, what is the difference between these two works, thanks
The paper claims that you test on two partial ReID datasets, but the repository seems to have no related code?
Is this article using python2, but this version has been discontinued. And one of the Queue modules cannot be installed, can anyone please advise?
Thank you very much for sharing your code. Can you share your transform_cuhksysu.py by the way?Thanks!