Yunhao Li

Hello! I'd like to confirm that if I want to train TransTrack for multi-object tracking, do I only need to modify tracker.py in the model code? Since the Tracker class...

I have now realized that the issue is not related to "different objects sharing the same description" mentioned earlier, but rather to poor training performance when using a smaller VG...

> pip install -e . 这个操作直接把torch1.11.0，mmcv2.0.0 卸载了，然后自动安装了mmcv-lite-2.2.0， torch-2.3.0， 运行模型又报错:"AssertionError: MMCV==2.2.0 is used but incompatible. Please install mmcv>=2.0.0rc4,

What do you mean '_do not need to build this project_'? Does that mean I only need to install the requiremnets but do not need run '_pip install -e ._'?