GraphNN-Multi-Object-Tracking issues

Test set with YOLOV4

1

Hi @selflein , I'm trying to do testing using a test set on which I've used YOLOV4; the output format is the same as MOT16, so I think I need...

MaddaRe

Having trouble in reproducing the result in inference.ipynb

11

I tried to reproduce the result of MOT16-02 in inference.ipynb by using the provided pretrained weight. But got this result. IDF1 IDP IDR Rcll Prcn GT MT PT ML FP...

Sternights

how can i use anthor reid model in this work

1

hi, thank you for the wonderful work and offer the code for us. If I train a separate ReID model, then I want to add this model in the code,...

szh91

'Namespace' object has no attribute 'preprocessed_dir'

1

parser.add_argument('--preprocessed_dir', type=str...., ) all_tracks = get_track_dict(Path(args.preprocessed_dir), Path(args.net_weights)) ##the all_tracks nedds args.preprocessed_dir, but it is preprocessed_sequences in parser. so this makes a error is 'Namespace' object has no attribute 'preprocessed_dir'

AIgiraffe

How to train the model?

Thank you so much for sharing the implementation. I tried to train the model by the original setting of this implementation but the results are not good. Do you use...

hungminhsu

How to Modify for Multiple Target Tracking

2

Hi, thanks for sharing this valuable code. I just want to learn if we can modify your approach to train on our custom datasets, which may contain multiple classes other...

bayraktare