daodaofr / group_reid Goto Github PK
View Code? Open in Web Editor NEWLearning Multi-Attention Context Graph for Group-Based Re-Identification
Learning Multi-Attention Context Graph for Group-Based Re-Identification
第一,我在一张2080ti显卡上测试过程中发现每张图片都要花费十分钟左右的时间,测试完一轮耗时12天,我能否从test中选取一定数量的实例作为query,这样和最终的精度会差别大吗?第二,我测试完成后发现对于人物识别的mAP指标只有40.4%,和您给出的64.2%差距较大, 我目前还没找到原因。
您好,文章中所提到的数据集CSG在哪里可以得到呢?
(8620, 33600) (8620,) (33600,) (8620,) (33600,)
Traceback (most recent call last):
File "main_group_gcn_siamese_part_half_fulltest_sink.py", line 687, in
main()
File "main_group_gcn_siamese_part_half_fulltest_sink.py", line 232, in main
rank1 = test_gcn_person_batch(model, queryloader, querygalleryloader, galleryloader, args.pool, use_gpu)
File "main_group_gcn_siamese_part_half_fulltest_sink.py", line 676, in test_gcn_person_batch
cmc_p, mAP_p = evaluate_person(distmat_p, q_pids_p, g_pids_p, q_camids_p, g_camids_p)
File "/share/home/shyyx2/Greid/code/group_reid/eval_metrics.py", line 90, in evaluate_person
remove = (g_pids[order] == q_pid) & (g_camids[order] == q_camid)
TypeError: eq() received an invalid combination of arguments - got (numpy.ndarray), but expected one of:
你好,我正在复现这篇论文,但遇到了一个难题。文中用到了iLID-MCTS, DukeMTMC Group,RoadGroup数据集用于对比性能。但我并未能在引用的原论文和网络中找到它们,如dukermtmc数据集已经被撤回。请问是否能够提供这些数据集呢?无论是否能提供,还望您能够回复,这对我的帮助很大
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.