Channel: GOTO Conferences

Category: Science & Technology

Tags: tensorrttriton inference servervideos for developersartificial intelligenceekaterina sirazitdinovagotocomputer sciencedata sciencesoftware engineeringgotoconprogrammingnvidiamlkatja sirazitdinovatritonai networksgotopiaaimachine learningdeepstream sdkgoto copenhagengoto conferencegoto (software conference)deepstreamgotocph

Description: This presentation was recorded at GOTO Copenhagen 2021. #GOTOcon #GOTOcph gotocph.com Ekaterina Sirazitdinova - Data Scientist for Computer Vision, Video Analytics & Deep Learning at NVIDIA ABSTRACT 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 [...] TIMECODES 00:00 Intro 01:23 Why intelligent video analytics? 06:27 Challenges with intelligent video analytics 08:49 Tips & tricks for efficient AI video analytics 09:00 Transfer learning 11:03 Data augmentation 12:19 Automatic mixed precision (AMP) 14:03 Quantization 16:18 Network pruning 18:10 Network graph optimizations 19:51 Kernel auto-tuning 20:52 Dynamic tensor memory upon inference 21:33 Multistream concurent execution 22:04 Free NVIDIA products designed to make your AI App efficient 23:10 NVIDIA's end-to-end AI workflow 25:32 TAO toolkit 28:45 high performance pre-trained vision AI models 30:02 Enabling beyond pre-trained AI models 30:48 Achieving state of the art accuracy for public datasets 31:10 NVIDIA TensorRT 32:48 TensorRT workflow 33:56 Triton inference server 37:12 DeepStream SDK 38:57 DeepStream application architecture 41:23 Pipelin efficiency with zero memory copies 42:19 NVIDIA graph composer 42:32 DeepStream video demo 43:54 Summary 45:18 Developer resources 46:09 Outro Download slides and read the full abstract here: gotocph.com/2021/sessions/1786/best-practices-for-real-time-intelligent-video-analytics RECOMMENDED BOOKS Magnus Ekman • Learning Deep Learning • amzn.to/3D1d8Nz Phil Winder • Reinforcement Learning • amzn.to/3t1S1VZ Kelleher & Tierney • Data Science (The MIT Press Essential Knowledge series) • amzn.to/3AQmIRg Lakshmanan, Robinson & Munn • Machine Learning Design Patterns • amzn.to/2ZD7t0x Lakshmanan, Görner & Gillard • Practical Machine Learning for Computer Vision • amzn.to/3m9HNjP Aurélien Géron • Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow • amzn.to/2XZaQy8 twitter.com/GOTOcon linkedin.com/company/goto- facebook.com/GOTOConferences #NVIDIA #AI #ML #DataScience #AINetworks #ArtificialIntelligence #MachineLearning #DeepStream #DeepStreamSDK #TensorRT #NVIDIATensorRT #Triton #TritonInferenceServer #AIAnalytics #AIVideo #AIVideoAnalytics #DataAugmentation #AMP #AutomaticMixedPrecision Looking for a unique learning experience? Attend the next GOTO conference near you! Get your ticket at gotopia.tech Sign up for updates and specials at gotopia.tech/newsletter SUBSCRIBE TO OUR CHANNEL - new videos posted almost daily. youtube.com/user/GotoConferences/?sub_confirmation=1