Release Notes

0.2.1 (2016/01/25)

• Minor bug fixes and improved error messages.
• Add a LFW classification experiment and an outlier detection script.

0.2.0 (2016/01/19)

• See this blog post for an overview and the GitHub Milestone for a high-level issue summary.
• Training improvements from resulting in an accuracy increase from 76.1% to 92.9%, which are from Bartosz Ludwiczuk's ideas and implementations in this mailing list thread. These improvements also reduce the training time from a week to a day.
• Nearly halved execution time thanks to Hervé Bredin's suggestions and sample code for image alignment in Issue 50.
• Hosted Python API Documentation.
• Docker automated build online.
• Initial automatic tests written in tests.
• Tests successfully passing in the Docker automated build in Travis.
• Add util/profile-pipeline.py to profile the overall execution time on a single image.

0.1.1 (2015/10/15)

• Fix debug mode of NaiveDlib alignment.
• Add util/prune-dataset.py for dataset processing.
• Correct Docker dependencies.

0.1.0 (2015/10/13)

• Initial release.