Jiapeng Wu
Jiapeng Wu
Hello, Now I want to try multi-class MOT, but I met the assert error: `in util/box_ops.py: assert (boxes1[:, 2:] >= boxes1[:, :2]).all()` When I trained the single class, it happened...
Hello, Now I solved this issue. To train in multi-class, you only need to modify a few codes. 1. change the 'num_classes' in models/init.py. e.g., I want to track objects...
I'm still training, and it seems good. Thank u very much for your excellent work. After some epochs I plan to add some code of showing the class name in...
I think you should convert your own dataset to COCO-style first, so you can get the key of 'frame_id'
@kikirizki Hello, sorry to bother you. I'm tracking cars in visdrone dataset, may I ask you what batch size and lr you chose? My mAP is always 0 and it...
Hello. I've already solved this problem just now. If you're testing it on MOT16, The reason is that you should fix the path in track.py: Firstly, in line 206, the...
No it cannot. Because the classification branch is used to classify different identities.
1. 我的cython_bbox版本是0.1.3, 您的版本是? 2. 应用的话, 首先需要修改里面的路径变量, 包括track.py的和tracker_dataloader.py中的. 之后您需要在track.py读取检测结果的部分作修改, 确保跟踪器可以读取检测的目标的类别, 位置和置信度~
这个问题确实没有遇到过... 我这里auto anchor都是好的. 现在这个问题您解决了吗?
天呐，竟然有0边界框？这个我没遇到过，是训练过程中出现的吗？ 另外video的问题应该已经修复，您可以再试试~