23-24 October 2025
Barbican Centre
Europe/London timezone

burn: a little case study on using GstAnalytics from Rust

Not scheduled
5m
Barbican Centre

Barbican Centre

Level 4, Silk Street, London, EC2Y 8DS, UK

Speaker

Sebastian Dröge (Centricular Ltd)

Description

Almost all existing code using the GstAnalytics API is in C or Python: inference elements, tensor decoders and all kinds of infrastructure elements.

In this lightning talk I will talk about my experience writing an inference element around the Rust burn deep-learning / machine-learning framework, writing a tensor decoder for YOLOX in Rust, and how it integrates with the remaining GstAnalytics infrastructure.

burn is a Rust framework that is modeled after the PyTorch API and supports many different CPU/GPU/NPU backends.

Speaker Bio

Sebastian works at Centricular on GStreamer and other projects, and has been working on GStreamer for almost 20 years now.

Duration of the talk 5 minutes (lightning talk)

Primary author

Sebastian Dröge (Centricular Ltd)

Presentation Materials

There are no materials yet.
2025 Host
Technische Universität Wien
2025 Gold Sponsors
AMD
Arm
Collabora
Microsoft
NVIDIA
Snap AR
2025 Silver Sponsors
CodeWeavers
FEX-Emu
Igalia
Qualcomm
The Linux Foundation
2025 Bronze Sponsors
Khronos Group
Libre Computer