Arash Zarindast

Train on custom dataset

3

Dear author, I am trying to train your model on my custom dataset i am using following command !python src/train.py with deformable tracking resume=r50_deformable_detr-checkpoint.pth output_dir=models/custom_dataset_train_deformable mot_path=data/custom_dataset train_split=train val_split=val epochs=20 i...

Train on kitti dataset

1

I was wondering how that can be possible for me to train your model on KITTI dataset. I am trying to track vehicles. I was also wondering about the backbone...

How can i reduce the batch size or anything like that so that i wont get such errors?

help to evaluate on custom dataset

1

I am using the structure mentioned in comment number #29 with following command to run !python TrackEval/scripts/run_mot_challenge.py --DO_PREPROC False --BENCHMARK cam1 --SPLIT_TO_EVAL all --TRACKERS_TO_EVAL bytetrack this is the error i...

BYTETracker with another detector result

3

when im trying to use from yolox.tracker.byte_tracker import BYTETracker tracker = BYTETracker(args) for image in images: dets = detector(image) online_targets = tracker.update(dets, info_imgs, img_size) with detection result from another detector...