zzzzzj1994

19G 怎么传送？ 我开个百度网盘吧

the shape of your label is not matched. you should covert your current mask file into gray mode and get the shape like below: ` img size: (4000, 2248) img...

emmm, I think she will not understand chinese ...

@NUS-Tim does the mask file generate more value other than 0 and 1?

please upload the details for sovling the problem.

`ffmpeg -f image2 -i {}/%05d.jpg -b 5000k -c:v mpeg4 {}` decrease params b

`cv2.cvtColor(arr, cv2.COLOR_BGR2RGB)`

@sainivedh thank you , i will look into FastMOT later. I am using FairMOT which is faster than two-stage MOT model, and i think it is what i wanted.

you should modify the code like blow: ``` anchors = model.module.module_list[jj].anchor_vec if multi_gpu else model.module_list[jj].anchor_vec anchors = anchors.to(targets.device) gain[2:] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain gain = gain.to(targets.device)...

Whether you test the script with your custom dataset or not ? If do, you should change the classes and the filter number in the model config file, they should...