AI-powered video analytics development and deployment effort.
Watch a compilation of clips demonstrating how you can use Deci in a variety of video analytics use cases.
Object Detection | Object Tracking
A defense firm required processing high-res images for object detection and tracking on an NVIDIA Jetson Xavier NX, aiming to operate at 10 Watt mode with a 10 FPS throughput. Using Deci the company was able to increase throughput by 3.1x on their existing devices and launch the new solution.
Object Detection
A security company aimed to process more live video feeds in real-time on their NVIDIA Jetson Xavier NX. Despite the increased feed count, their YOLOX object detection model fell short of the needed 192 fps throughput for an 8-frame batch.
Employing Deci’s AutoNAC engine, they achieved a 1.7X speed boost, hitting the 192 fps target with a 1% mAP accuracy gain, allowing them to double their video stream handling from 4 to 8 and enhance their video analytics solution’s scale and profit.
Lior Hakim, Co-Founder & CTO
Hour One
Deci is used by AI-powered video analytics solution providers to develop and optimize a wide range of applications. Here are some examples.
Smart Cities
Security
Industrial and Manufacturing
Retail and Logistics
Agriculture
Robotics
The Deci platform is used by data scientists and machine learning engineers to build, optimize, and deploy highly accurate and efficient models to production. Teams can easily develop production grade models and gain unparalleled accuracy and speed tailored for any performance targets and hardware environment. Deci is powered by AutoNAC (Automated Neural Architecture Construction), the most advanced and commercially scalable Neural Architecture Search engine in the market. AutoNAC performs a multi-constraints search to find the architecture that delivers the highest accuracy for any performance targets and hardware environment.
Build accurate & efficient architectures tailored to your hardware and application’s performance targets with Deci’s Neural Architecture Search engine.
Easily compile and quantize your models (FP16/INT8) and evaluate different production settings with a click of a button.
Train models with SuperGradients. Leverage custom recipes and advanced training techniques (e.g. knowledge distillation, quantization-aware training) with one line of code.
Deploy your models with Infery, Deci’s simple-to-use, unified, model inference API. Streamline deployment and boost serving performance with parallelism and concurrent execution. Compatible with multiple frameworks and hardware.
Deci is ISO 27001
Certified
from transformers import AutoFeatureExtractor, AutoModelForImageClassification
extractor = AutoFeatureExtractor.from_pretrained("microsoft/resnet-50")
model = AutoModelForImageClassification.from_pretrained("microsoft/resnet-50")