
Meet Deci at CVPR and Enter Our Raffle for a Chance to Win an Amazon Gift Card

We’re exhibiting at CVPR on June 18-22, 2003 at the Vancouver Convention Center. Book a meeting with Deci’s experts to learn how Deci’s Automated Neural Architecture Construction (AutoNAC) Engine can empower your team to build highly accurate and efficient models for your computer vision applications.
Reserve your spot in the raffle and drop by booth 1517 to see if you win! 🎁
*The raffle will take place at Deci's booth (1517) on June 21
Don't Miss the Excitement at Booth 1517!

See Deci's E2E Deep Learning Platform in Action
- Learn more about how we can help you achieve your specific goals
- Get a walkthrough of Deci’s platform where you can perform the end-to-end deep learning development cycle – from creating your own model and choosing the relevant public dataset, to selecting the right hardware and defining optimization KPIs
Discover the Power of YOLO-NAS, a Model Generated by AutoNAC
See for yourself how YOLO-NAS:
- Runs at unparalleled accuracy and speed, outperforming other well-known models.
- Is fully compatible with high-performance inference engines like NVIDIA® TensorRT™ and supports INT8 quantization.
- Leverages cutting-edge techniques, such as attention mechanisms, quantization aware blocks, and reparametrization at inference time.
- Is easy to fine-tune to achieve SOTA results using Google Colab Notebook with the SuperGradients open-source library.
Talk with Deci's Experts 1-on-1
Get a free consultation session and learn how other leading AI teams are collaborating with Deci to solve edge AI design and deployment challenges

Ran Zilberstein
VP Engineering
LinkedIn →

Shani Perl
AI Product Manager
LinkedIn →

Natan Bagrov
Computer Vision Team Lead
LinkedIn →

Harpreet Sahota
DevRel Manager
LinkedIn →

Dan Bochman
Deep Learning Engineer
LinkedIn →
AutoNAC (Neural Architecture Search Engine)
Automatically find the architecture that delivers the highest accuracy for your specific speed, size, and inference hardware targets
Tailored for Your Task & Performance Goals
Run a multi-objective search to generate an architecture optimized for several parameters (accuracy, throughput, latency, model size, and memory footprint)
Hardware Aware Neural Architecture Search
Take hardware constraints into account to unlock optimal efficiency that hit your performance targets
Outperforms any SOTA Computer Vision Model
Deliver the best accuracy and speed for your specific use case that outperform SOTA open-source neural networks