imzhangyd

icon indicating an email [email protected]

icon company Institute of Automation, Chinese Academy of Sciences icon location Beijing icon location Today is a gift

Results 6 comments of imzhangyd

Missing key(s) in state_dict: "features.0.weight", "...

I meet the same problem. Have you solved it? @York1996OutLook

undefined symbol: THPVariableClass

Hi, I also have the similar problem. When I finish Install acoording to the instruction, I excute train commond: `python src/train.py with \     mot17 \     deformable \     multi_frame \     tracking...

cannot allocate memory

@jer1ry Hi, I also met this problem after training about 10 epochs. Have you solved it? @timmeinhardt Could you please help me with it?

CUDA out of memory when the sequence last too long

> Hi Tim, thank you very much for your time and attention. Here is what happened to me: When I tried to run the pre-training as TRAIN.md says:" python src/train.py...

Is only the detector (e.g. YOLOX) to be trained in ByteTrack?

@ldtho Yes, it is.

Inference python scripts

@2U1 You're right. Here are logs. How to solve this problem? ```sh 2025-09-08 19:39:31,967 [INFO] base in/out: torch.Size([0]) torch.Size([0]) 2025-09-08 19:39:32,325 [INFO] after peft in/out: torch.Size([0]) torch.Size([0]) 2025-09-08 19:39:32,326 [INFO]...