Best Practices for Real-time Intelligent Video Analytics
This video is also available in the GOTO Play video app! Download it to enjoy offline access to our conference videos while on the move.
Katja is a research engineer focusing on deep learning, computer vision and inference optimization.
Larger and more complex Vision AI networks enable better accuracy and precision since they are able to encode more information. This increase in size and complexity is, in turn, naturally associated with trained AI models having lower throughput and larger memory requirements. With that, real-time AI inference is becoming a new great challenge in intelligent video analytics.
NVIDIA’s approach at solving this problem relies on two major components: first, tuning AI models for performance depending on the target deployment hardware platform, and, second, optimizing the use of available GPUs.
From this talk, you will learn how to leverage this approach to achieve real-time inference performance by using software tools like DeepStream SDK, TensorRT and Triton Inference Server.
-
War is Peace, Freedom is Slavery, Ignorance is Strength, Scrum is AgileAllen HolubWednesday Nov 10, 16:10
-
Is Software Engineering Still an Oxymoron?Alan KayMonday Nov 8, 09:30
-
The Future of FlightAnita SenguptaMonday Nov 8, 13:50
-
Continuous Delivery Pipelines: How to Build Better SW FasterDave FarleyWednesday Nov 10, 16:10
-
An Average Working Day on Visionary NASA ProjectsKenneth Harris IIMonday Nov 8, 16:10
-
The Worst Programming Language EverMark RendleTuesday Nov 9, 19:00