Commit graph

18 commits

Author SHA1 Message Date
Ruben van de Ven
5deac894a5 change minor log annoyance 2023-04-05 17:17:35 +02:00
Denver Dash
5618eb5390
Bugfix (#122)
* bug in multitracker - img_size param passed to Darknet init but no img_size parameter expected.

* Various minor bug fixes
2020-03-20 19:45:22 +08:00
Parthesh Soni
24f351d1b5
Documentation (#95)
* Added documentation

* Added docstrings and comments

* Removed unused imports

* Removed unused imports

* Added functionality of saving checkpoints during training process

* Update train.py

* Update multitracker.py
2020-03-14 10:24:27 +08:00
Falak
2eff9c00b1
Update utils.py (#93)
* Update utils.py

* Revert change in computation
2020-02-17 15:11:10 +08:00
Zhongdao
c40826179b 1.Accelerate the association step.
2.Provide more trained models with different input resoulution.
2020-01-29 21:45:07 +08:00
Christian Clauss
e6c39ef673 non_max_suppression(): Remove unsupported options (#74)
Fixes #33  Delete all the code that is related to __soft_nms__ as recommended at https://github.com/Zhongdao/Towards-Realtime-MOT/issues/33#issuecomment-572886297
2020-01-10 14:36:47 +08:00
Zhongdao
68aee10042 test multi-embedding 2020-01-10 00:44:38 +08:00
Zhongdao
be116014d6 replace maskrcnn-benchmark nms with torchvision nms 2020-01-09 22:48:17 +08:00
Zhongdao
59419367fd cleanup 2019-10-11 17:26:59 +08:00
Zhongdao
4276457d25 training data 2019-10-11 14:32:39 +08:00
Zhongdao
81ae5e7248 add gif demo 2019-10-02 19:25:59 +08:00
lynn
a830e47ecd Merge branch 'master' of https://github.com/Zhongdao/Towards-Realtime-MOT
..
2019-09-29 13:14:05 +08:00
lynn
514b4fb554 test 2019-09-29 13:13:23 +08:00
Zhongdao
e47a5ae246 add video demo 2019-09-28 11:40:41 +08:00
Zhongdao
acc0a09d0f can save video output now 2019-09-27 16:58:09 +08:00
Zhongdao
6033216d63 add bbox.so 2019-09-27 13:41:52 +08:00
Zhongdao
2a3d46dbc8 update gitignore 2019-09-27 13:40:32 +08:00
Zhongdao
28514de87b setup 2019-09-27 13:37:47 +08:00