Mohamed Lamnouar

Hi @dbogunowicz thank you so much for reply, if I don't have mistake, you can correct me I think there is a huge difference between yolov5 and yolox, because yolov5...

Torchreid just for person re-identification, you can use other model for object detection like SSD, or Faster RCNN, or Yolo for extract the bounding box.

You're welcome any time

@Thangbluee you can modify loss parameter in torchreid.models.build_model like this one "example" `model = torchreid.models.build_model( name = 'osnet_x0_5', num_classes = datamanager.num_train_pids, loss = 'triplet', pretrained = True ) ` and...

Thank you so much for reply, it's already done, but not yet it's same problem

Hi @chengqianma I have same problem, do you have solve this issue or not yet Thank you

Hi, I hope all is fine, I think this is very challenge for you if you need to learn new things and improve your skills sorry about this reply, but...

you need just to understand the input of byteTrack and the output of Yolov7 and try to match between them it's very useful challenge for you.

You can use dataSet from website motchallenge for predictions after that you can use Metrics from repository Traceval for evaluating your results.

Hi, I didn't occurred this problem according of training, but when I was tried to test our model after converted using trt, I found same problem how can I solve...