It takes multiple 1080p/30fps streams as input.
The following table shows the end-to-end application performance from data ingestion, decoding, image processing to inference. To reduce development efforts and increase throughput, developers can use highly accurate pre-trained models from TAO Toolkit and deploy with DeepStream. NVIDIA’s DeepStream SDK delivers a complete streaming analytics toolkit for AI-based multi-sensor processing, video, audio and image understanding.ĭeepStream is for vision AI developers, software partners, startups and OEMs building IVA apps and services.ĭeepStream is also an integral part of NVIDIA Metropolis, the platform for building end-to-end services and solutions that transform pixel and sensor data to actionable insights.Īchieving Higher Accuracy & Real-Time Performance Using DeepStreamĭeepStream offers exceptional throughput for a wide variety of object detection, image classification and instance segmentation based AI models.
