DEEPX Docs

🎉 SDK v2.3.3 Released!

Latest release includes: Enhanced Python API, improved model quantization, expanded ModelZoo support, and performance optimizations. View Release Notes →

What's New

Recent Updates

• [v2.3.3] Enhanced Python bindings with improved error handling and type hints
• [v2.3.3] DX-COM: Advanced INT8 quantization for better accuracy preservation
• [v2.3.3] DX-STREAM: New preprocessing elements for video pipeline optimization
• [v2.3.2] ModelZoo expansion: 270+ optimized models across 10+ categories
• [v2.3.0] Docker environment with full toolchain support

See all updates →

---

Explore

Guide

DX-AllSuite

Install DX-AllSuite and run your first NPU model end-to-end — from model download to hardware inference.

Reference

DX-COM

Convert ONNX models into DEEPX-optimized .dxnn binaries using the DX-COM compilation pipeline.

Reference

DX-RT

Deploy and run .dxnn models on DEEPX NPU with the C++ and Python runtime APIs.

Reference

DX-STREAM

Build multi-stream AI video pipelines with DEEPX NPU inference, preprocessing, and postprocessing elements.

Reference

DX-APP

Create C++ and Python applications that integrate DEEPX SDK runtime, examples, and postprocessing utilities.

Resource

Resource

Model Zoo

Browse 270+ pre-optimized models across classification, detection, segmentation, and more.

Resource

SDK Tutorials

Step-by-step tutorials for DX-COM, DX-RT, Python and C++ APIs on GitHub.

Resource

Video Guides

Watch SDK training and deployment walkthroughs on the DEEPX YouTube channel.