DEEPSTREAM REFERENCE APPLICATION System Configuration & Performance for 25x 720p streams
26
KPIs FOR PERFORMANCE
27
MOTIVATION
28
METHODOLOGY FOR PERFORMANCE ANALYSIS
29
THROUGHPUT MEASUREMENT
30
LATENCY MEASUREMENT USING GST-LOGS
31
PERFORMANCE BEST PRACTICES
32
CUSTOM PLUGIN FOR OBJECT DETECTION Implement custom TensorRT plugin layers for your network topology Integrate your TensorRT based object detection model in DeepStream
33
YOLO V2 OVERVIEW
34
DARKNET TO TENSORRT
35
TENSORRT PLUGIN FACTORY
36
CREATING APPLICATIONS WITH DEEPSTREAM Object detection and counting
37
DEEPSTREAM MODULAR APPLICATION
38
START DEVELOPING WITH DEEPSTREAM
Description:
Discover how to leverage AI-based video analytics applications using DeepStream SDK 2.0 for Tesla to transform video into valuable insights for smart cities. Explore the modular plugin architecture and scalable framework for application development, featuring frequently used plugins for multi-stream decoding/encoding, scaling, color space conversion, and tracking. Dive into topics such as IVA in smart cities, DeepStream software stack, metadata structure, pipeline architecture, and NVIDIA-accelerated plugins. Learn about efficient memory management, reference applications for vehicle detection and tracking, configuration files, and performance best practices. Gain insights on implementing custom TensorRT plugin layers, integrating object detection models, and creating modular applications with DeepStream. Download the NVIDIA DeepStream SDK and accompanying webinar slides to start developing powerful video analytics solutions.
Streamline Deep Learning for Video Analytics with DeepStream SDK 2.0