CenterTrack
CenterTrack copied to clipboard
xingyizhou
Simultaneous object detection and tracking using center points.
/home/mts/anaconda3/envs/CenterTrack/bin/python /home/mts/Desktop/Pycharmpj/CenterTrack/src/demo.py tracking --load_model ../models/coco_tracking.pth --demo ../image/images --gpu 0 /home/mts/anaconda3/envs/CenterTrack/lib/python3.6/site-packages/sklearn/utils/linear_assignment_.py:22: FutureWarning: The linear_assignment_ module is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead. FutureWarning) Running tracking...
Everyone seems to be having trouble with issue about GPU compilation of DCNv2, so I added a Dockerfile that works correctly. I have confirmed the operation in the following environment....
Like tranditional KCF or LK track algorithm, they can track any object by input box. It seems CenterTrack is also kind of tracking-by-detection? So it can only detect and track...
I used the script nuScenes_3Ddetection_e140.sh in the CenterTrack/experiments, but I can't reimplement the result in the model zoo with a mAP about 0.30~.When I run the command "python test.py ddd...
Hi,author! I follow the instructions in [DATA.md](https://github.com/xingyizhou/CenterTrack/blob/master/readme/DATA.md) to setup the kitti datasets, Run python convert_kitti_to_coco.py in tools to convert the annotation into COCO format. But there is no convert_kitti_to_coco.py in...
Hello This version of DCN wouldn't compile for me (errors right away): https://github.com/CharlesShang/DCNv2 ``` (CenterTrack2) cat@cat-GF63-Thin-9SCX:~/code/CenterTrack2/src/lib/model/networks/DCNv2$ ls dcn_v2.py __init__.py LICENSE make.sh README.md setup.py src testcpu.py testcuda.py (CenterTrack2) cat@cat-GF63-Thin-9SCX:~/code/CenterTrack2/src/lib/model/networks/DCNv2$ ./make.sh running...
thanks your great works! amodel_offset(amodel_offset_x, amodel_offset_y) is 3D offset(offset from 2D center point)?
according to the src\lib\dataset\generic_dataset.py code: hm ->ct_int ret['reg'][k] = ct - ct_int ret['amodel_offset'][k] = amodel_center - ct_int so, in inference, should be: ct_int: hm ct: ret['reg'][k] + ct_int = ret['reg'][k]...
hello @xingyizhou I have my custom detection model trained on yolov5 at ```.pth``` format. Can I just feed that model for test via ```python demo.py tracking --load_model ../models/coco_tracking.pth --demo /path/to/image/or/folder/or/video...
Metadata
Owner
Metadata
Simultaneous object detection and tracking using center points.