search

facebookresearch / DetectAndTrack

The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"
Apache License 2.0
1k stars 186 forks source link

py-motmetrics #44

Closed cheind closed 6 years ago

cheind commented 6 years ago

Hi, very nice work! Just discovered that deeply in your code you are refering to this library for pose evaluation https://github.com/cheind/py-motmetrics. Which happens to be a library of mine. It seems like you got it via https://github.com/leonid-pishchulin/poseval/, who refers to it via a submodule. This referall has been lost in your code copy. Would you mind noting a link to the original repository in the Dataset and Evaluation section?

rohitgirdhar commented 6 years ago

Sure, done.

cheind commented 6 years ago

Thanks! One thought: you are mentioning a multi-process optimization for faster processing. Not sure what the slow part of the evaluation was, but py-motmetrics supports different solvers for LAP problems. By default scipy is used, but faster variants such as https://github.com/cheind/py-lapsolver are available. In case you want to try out, just pip install lapsolver and re-run your evaluation.