Wiktor Muroń

@cansik If you need to know which detections (from current frame) were matched with which single object trackers, you can look at matches here: https://github.com/wmuron/motpy/blob/master/motpy/tracker.py#L399 - just make them accessible...

I think that the problem is you want to load the model that was trained with a different `seq_length` parameter than you setup. You have to make sure that `setup_inference`...

As you can see [here](https://github.com/tinghuiz/SfMLearner/blob/master/test_kitti_pose.py) right after the network inference, the pose predictions are dumped to files (using `dump_pose_seq_TUM` function). The pose predictions correspond to 5 camera poses - for...