Question about the result about eagermot HOT 5 CLOSED

I used the detection results of PointGNN and Motsfusion_RRC.

from eagermot.

Hello @zhaojieting, I also am trying on the same dataset inputs which are PointGNN and Motsfusion_RRC. Could you please explain how MotsFusion_RRC detections are that is about its folder structure? It has 29 folders each in detection and segmentation and some detection files in them. My question is what are these 29 parent folders?

from eagermot.

I could run the script but after 29 sequences, it says file not found!

from eagermot.

As there are only 29 npy files i m getting this error. Could you help me in understanding this?

from eagermot.

@Alfa-Shashank It says you are missing ego motion files, make sure you downloaded and unzipped them as written in https://github.com/aleksandrkim61/EagerMOT#how-to-set-up

@zhaojieting looks like you are missing or incorrectly parsed 2D detections. Go through your custom changes and debug to see what you get as your 2D detection inputs in the tracking code.

Closing for now
Sorry for the late reply, was busy with other stuff and did not get proper notifications. Check out my latest work https://polarmot.github.io/

from eagermot.