search

BingfengYan / CO-MOT

CO-MOT: Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking
65 stars 4 forks source link

Pretrained weights / Batch_size #14

Open btroussel opened 8 months ago

btroussel commented 8 months ago

Hello,

Thank you very much for your work !

I had some questions :

1) Are those trained using the pretrained weights of Deformable DETR (and so with Coco) or are these using only a pretrain of ResNet (and so with ImageNet only ?). It seems I don't get the same results of HOTA and of TETA for BDD100K in my setup.

2) Is the code working with a batch_size > 1, like with Deformable DETR ?

Thanks again for your time !

fengxiuyaun commented 7 months ago

We conducted training on the "r50_deformable_detr_plus_iterative_bbox_refinement-checkpoint.pth". No. However, the code can be modified to support a batch size greater than 1.