Christoph Heindl

icon indicating a website link https://cheind.github.io/ icon indicating an email [email protected]

icon location Austrian area icon location I am a computer scientist working at the interface of perception, robotics and deep learning.

Results 122 comments of Christoph Heindl

Is py-motmetrics missing any metrics/datasets?

@michih8 any chance you could provide a PR?

Is py-motmetrics missing any metrics/datasets?

@ahrnbom, yes that seems like a good idea. Could you provide a PR?

Docker support

@christosavg seems to be unresponsive. @jvlmdr should we remove the docker support file?

Get ride of np.bool deprecation warning.

@alexlitz did you see my code comment about public API concern?

Get ride of np.bool deprecation warning.

Here https://github.com/cheind/py-motmetrics/pull/155/files/fc06cd2e66c57250d1322457b59a52232c951ee4

different result on Matlab version and Python version

Please run on latest develop branch and report more details.

different result on Matlab version and Python version

@ucohen this is to account for the pixel numbering offset. AFAIK Matlab considers the first pixel to be at (1,1) instead of (0,0)

different result on Matlab version and Python version

link to #115

How to print IDTP, IDFP, IDTN, IDFN and num_detections metrics

Not sure if you have tried but, 1. Have a look at how to compute / print metrics in general [here](https://github.com/cheind/py-motmetrics#computing-metrics) 2. Lookup the metrics you need in [metrics.py](https://github.com/cheind/py-motmetrics/blob/develop/motmetrics/metrics.py) and...

different results from motchallenge devkit

Hey @fguney, @abhineet123! Could you provide a [MWE](https://en.wikipedia.org/wiki/Minimal_working_example), so we could pinpoint the differences?