Commit Graph

8 Commits (1ca6ec52fdb178cf296bbf47ff39d65badacc903)

Author SHA1 Message Date
Ian Wood 1ca6ec52fd fixed weighted average, no explicit treatment of 'neutral' 7 years ago
drevicko 53138e6942 Estimate VAD by weighted average
Does a weighted average of centroids.

If intensity sums to zero for a category, a 'neutral' category is used or 0 if it's not present. I'm not 100% sure this is the best approach, and the name of the "neutral" category perhaps should use some convention?

Note that if there are no categories present, then no VAD (or other dimensional) estimate is returned. It may be better to use the neutral centroid if it's present in this case also.
7 years ago
J. Fernando Sánchez c9e6d78183 Fixed alises, added PAD and FSRE
Closes #13
7 years ago
J. Fernando Sánchez 2288b04c92 Remove iteritems for py2/3 compatibility 7 years ago
J. Fernando Sánchez d8b59d06a4 Converted Ekman2VAD to centroids
* Changed the way modules are imported -> we can now use dotted
  notation (e.g. senpy.plugins.conversion.centroids)
* Refactored ekman2vad's plugin -> generic centroids
* Added some basic tests
7 years ago
J. Fernando Sánchez 453b9f3257 Fixed bugs in Ekman2VAD 7 years ago
J. Fernando Sánchez ba2e18125c Deployment changes
* Docker all the things!
* Make all the things!
* Fixed version.sh
7 years ago
J. Fernando Sánchez 9f6a6f5ecd Loads of changes!
* Added conversion plugins (API might change!)
* Added conversion to the analysis pipeline
* Changed behaviour of --default-plugins (it adds conversion plugins regardless)
* Added emotionModel [sic] and emotionConversion models

//TODO add conversion tests
//TODO add conversion to docs
7 years ago