top of page

For Detection on NPU & MPU

State of the Art

  • Achieve state-of-the-art results with best-in-class performance using ModelPack for Detection.

  • Avoid common pitfalls of tuning, pruning, quantizing models.  Simply provide your dataset and train from eIQ® Portal.

  • We’ve optimized our models so you can focus on your vision application.

DeepView ModelPack


MobileNet SSD



  • Instantly deploy standard or custom AI models on EVK, Maivin or your own hardware.

  • Fully compatible with eIQ® Toolkit graphical development environment for no-code model training and deployment.

  • Integration with multiple frameworks to deploy your AI application the way you want.

Best in class

  • Achieve industry leading performance with DeepViewRT™ Inference Engine and DeepView™ VisionPack.

  • Ship your product with confidence knowing your vision pipeline is fully optimized for AI compute at the edge.


  • Build your EdgeFirst AI solution with confidence.

  • Long Term Support and stability.

  • Documented code provenance.

  • Field proven reliability.


In Flight

In Planning

DeepView Zoo

DeepView Dataset Zoo

The ModelPack Dataset Zoo provides various example datasets which can be opened directly into eIQ Portal to train a ModelPack model.  Each dataset also provides pre-trained models which can be used directly by VisionPack and full checkpoints to evaluate results in eIQ Portal without the need to re-train.

DeepView Dataset Zoo

Downloadable VisionPack Applications

A collection of EdgeFirst vision applications demos powered by our DeepView VisionPack and DeepView ModelPack. Real-world, easy to run examples you can perform at home or in the office.


Object Detection Model

DeepView object detection models deliver state-of-the-art detection for inanimate objects, people, or animals. Use standalone or with a MobileNet, ResNet, or custom backbone.


Classification Models

DeepView classification models are significantly more advanced than standard reference classification models such as ResNet or MobileNet. Models come pre-trained with high-level features with support for transfer learning to finish training with your dataset.


Pose and Gesture Models

This example showcases the PoseNet model running on the DeepViewRT inference engine to provide a very efficient Pose and Gesture recognition solution.  The demo shows an application built using QML that can detect and overlay an outline of a person or persons’ joints and limbs onto a video feed using a PoseNet model.



DeepView segmentation models generate a pixel-wise mask of the inanimate objects, people, or animals and can be used in conjunction with other DeepView models to perform tracking, identification, and reidentification.


License Plate Recognition (LPR/ANPR)

DeepView license plate recognition models providing an intelligent way to improve your tracking, identification and reidentification to help train and enhance your dataset.


Super Resolution

DeepView super resolution models providing an intelligent way to improve upscaling, defect removal, and compression artifacts.

Stay up to date on all the DeepView AI Middleware releases. Subscribe Today!


The DeepView AppPack provides you with the building blocks and glue for robust, turn-key intelligent vision applications.

dev pack-01.jpg

DeepView DevPack delivers production-grade tools to help you optimize your machine learning models and fine-tune your training data sets.


The DeepView Model Pack provides developers with both public (Open Source) and production ready models. 


The DeepViewRT run time inference engine provides developers with the freedom to quickly deploy ML models to a broad selection of embedded devices 


DeepView Vision Packs provide the vision pipeline solutions for your edge computing and embedded machine learning applications. 

DeepView vision starter kits include the hardware and software you need to accelerate your machine learning development programs from bench-top through field trials and into production.

bottom of page