hahapt

ImportError: /lib/x86_64-linux-gnu/libm.so.6: version `GLIBC_2.27' not found

2

When I try to verify whether MMTracking and the required environment are installed correctly, I run the MOT demo and here comes a error: ImportError: /lib/x86_64-linux-gnu/libm.so.6: version `GLIBC_2.27' not found...

How to evaluate the mAP(fast) in VID task?

1

For VID methods like FGFA and SELSA, the author show the results of mAP(slow), mAP(medium) and mAP(fast) in the paper. When testing with mmtracking, I found here are results of...

Where is the imagenet_vid_val.json?

1

When testing FGFA or SELSA method with ILSVRC dataset, I can't find the `ann_file=data_root + 'annotations/imagenet_vid_val.json'` So where can I get the ann_file for training and testing?

Performance about TransCenter_Lite?

1

Is there any comparison about the TransCenter_V2 and TransCenter_Lite?

I found the model is trained only in person category, can we train it with multi-class like person and car?

I'm confusing about how to draw Figure1, especially Figure1(a)？

Excuse me, I found this work very interesting and try to make it by myself. But I was wondering if you can share the yml for other dataset, such as...

error in ms_deformable_im2col_cuda

2

I have install MultiScaleDeformableAttention package, but here comes two errors and the model is still training: error in ms_deformable_im2col_cuda: no kernel image is available for execution on the device error...

I found the tools/demo.py support the TensorRT inference, so I try to convert it to TensorTR model, but where is the tools/trt.py mentioned in tools/demo.py? `if args.trt: assert not args.fuse,...

在MOT/MOTS推理阶段是否存在类似于feature propagation这样的操作？论文framework图中的reference targets是如何体现在推理阶段的？