SOTS

SOTS copied to clipboard

Thank you for your excellent work! I would like to ask whether the code for heatmap visualization of CSTrack can be shared.

hanzi326

关于评估结果的问题

4

您好 我使用这个代码发现复现不出论文中的结果，差距还有点大，您可以给我一些好的建议吗 谢谢

zhengbangyan

CCN

1

Where is the CCN class used in cstrack

MOTnew

I really appreciate your great work and sharing OMC. Would you mind sharing HOTA and IDsw of OMC on the MOT16/17/20 test results which are not available from the paper?...

HYUNJS

Thanks for your contributions. (1) I train the OMC according to training and testing turorial. When I train with the re-check network,if I use best.pt, the MOTA on MOT16 test...

wxy932

crowdhuman training problem

1

Hi, first of all thank you for your excellent work. I encountered some problems when trying to train, when running train_cstrack.py, training crowdhuman, then only GIou Loss, id loss is...

majun19970125

How to train AutoMatch on custom dataset?

1

Thanks for publishing your work. I have my own dataset of 2000 images and ground truth. Can we you help me in structure of train.json and train dataset folder.

jayantkulkarni10j

关于代码的问题

2

请问，训练的时候为什么没有验证呢？如果要加入验证的部分都需要修改哪些地方或添加哪些东西才能比较快的完成验证部分呢？我想要训练一个automatch的模型。另外还想问一下det的数据集里面没有看到val部分的数据集呢，我发现解压之前的train.json与解压以后得到的train.json完全不一样呢，是其中有一个是val数据吗？

bulingda

Hello, why do you calculate bbox like this?

2

https://github.com/JudasDie/SOTS/blob/5b9be9168053b2445f3a54931fdffb591c8d79b1/lib/dataset/siamese_builder.py#L202 Especially lines 211 to 214, the scale_z What does it mean?

yangzijia

Hi. Thank you for your great work. I just want to ask if you did minus the center_x and center_y by 1. Because the MOT dataset's coordinates are 1-based indexing,...

sieumap43