Nwoye Chinedu

Multi-class Multi-object Tracking

2

Hello, nice work by the way. Can this work be trained for multi-class-multi-object tracking such as tracking multiple cars, multiple persons and multiple dogs at the same time?

Output video cannot play

2

Just running the code, the output video is 10 790 bytes and invalid. I guess, no inference is done.

Which of the HOTA implementation is classification-aware?

OutOfMemoryError

3

I have OOM error during inference but not during training. This happens even with batch size of 1 and even with increasing the GPU memory. `torch.cuda.OutOfMemoryError: CUDA out of memory....

AssertionError: Error: all query identities do not appear in gallery

5

Hi, Thank you for providing this code. I have a question: In https://github.com/NirAharon/BoT-SORT/blob/main/fast_reid/fastreid/data/datasets/mot20.py: Line 50: `self.query_dir = osp.join(self.data_dir, 'query')` Line 52: `self.extra_gallery_dir = osp.join(self.data_dir, 'images')` Line 65: `query = lambda:...

Using 4x4 matrix: How do you ensure that two rows does not have their maximum values at the same column indexes?

Hi Thank you for this code, but I can see some code errors in https://github.com/CaptainEven/MCMOT-ByteTrack/blob/DarknetCfg/tutorials/fairmot/tracker.py (line 255-274) In line 258: ``` dets, inds = mot_decode(hm, wh, reg=reg, ltrb=self.opt.ltrb, K=self.opt.K) ```...

NaN Loss

2

There are so much NaN in loss. The train script, skip optimizing whenever NaN is in the tensor. What causes these NaN values?

This pull request is to add a support for CholecTrack20 dataset. The modification includes: 1. **TrackEval/doc/CholecTrack20-format.txt** : Added a new text file describing the result file format. 2. **TrackEval/trackeval/datasets/cholectrack.py**: Added...