mmtracking
mmtracking copied to clipboard
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
Since the code is public, i am really so much impressed. I wanted to ask that is there any possibility to export json of the detected object with the bounding...
requirements/build.txt: requires numba==0.53.0. But that version has been pulled, and trying to pip install it results with: " ERROR: Could not find a version that satisfies the requirement numba==0.53.0 (from...
when I train the model of temporal roi align some minutes it will provide this error cannot reshape tensor of 0 elements into shape [0, 16, -1] because the unspecified...
I install MMCV 1.3.17 in my enviorment, but the program just use the MMCV 1.3.12 in ~/.local/bin/python3.7/ , How to fix it?
I tested SELSA with temporal ROI on my custom dataset but it doesn't work well on far objects, I tried to use YOLOX model instead of the Faster R-CNN detector,...
Hi! Could you please tell me how can I use ByteTrack or QDTrack to implement multi-classes MOT? It seems that the existing configurations are only for one-class(pedestrian). I wonder if...
**Describe the bug** RuntimeError: expected scalar type Float but found Half **Reproduction** ```none python tools/test.py configs/mot/bytetrack/bytetrack_yolox_x_crowdhuman_mot17-private.py --eval track ``` 2. Did you make any modifications on the code or config?...
If i use youtubevis-2021 dataset, but the 2021-competetion had been finished. Where i can upload the zip file?
Hello! Sorry for disturbing again, but I have new problems, and it confuse me a lot. It appears that dist_test/dist_train cannot work. When I run the dist_test.sh using the command:...