BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:The Quest for Python Analytics
DTSTART;VALUE=DATE-TIME:20261010T131500Z
DTEND;VALUE=DATE-TIME:20261010T133500Z
DTSTAMP;VALUE=DATE-TIME:20261009T233437Z
UID:indico-contribution-611@indico.freedesktop.org
DESCRIPTION:Speakers: Aaron Boxer (Collabora Inc.)\nAt GStreamer Conferenc
 e 2024 I proposed GStreamer as the ideal nervous system for feeding AI bra
 ins with data. As Python is the dominant language in AI\, a new Python fra
 mework\, gst-python-ml\, was introduced to easily connect PyTorch models w
 ith GStreamer pipelines\, with support for object detection\, tracking\, l
 ocal speech to text and local text to speech.\n\nThis talk covers the many
  new features that have arrived since then\, including segmentation\, dept
 h and pose estimation\, OCR\, optical flow\, vision-language captioning\, 
 Whisper\, and LLMs local and remote. PyTorch is now just one of fifteen di
 fferent inference backends including ONNX\, OpenVINO\, LIteRT and MIGraphX
 \, allowing us to support every conceivable ML model with ease. The framew
 ork is in active use\, powering many of Collabora’s ML demos.\n \nAlong 
 the way\, we will view live demos of new vision and language features\, al
 l running on a humble consumer GPU\, with a focus on sport analytics.\n\nh
 ttps://indico.freedesktop.org/event/14/contributions/611/
LOCATION:Impact Hub Prague
URL:https://indico.freedesktop.org/event/14/contributions/611/
END:VEVENT
END:VCALENDAR