
DeepView™
Development Pack

DeepView DevPack delivers production-grade tools to help you optimize your machine learning models and fine-tune your training data sets. The tools are flexible enough to use in your in-house model development workflow and provide even greater benefits when used in conjunction with NXP’s eIQ Toolkit and eIQ Portal to accelerate and ease your model development process.



Starter DevPack
Model Insights
Detailed reports showing accuracy and loss compared to input model to help developers gain a deep understanding of quantization behavior. Provides insights on your model’s dynamic range to help predict the conversion efficiency from per channel to per tensor quantization.
Model Explainability
Framework which extends an RTM model with encoding to support attention mapping. Tools to provide runtime analysis and profiling of graph features with greatest impact on model’s predictions. Heatmap visualization to provide developer with context on the multiclass support.
Model Training Accelerator
eIQ Portal Add-On providing developers with the ability to automate parallel training jobs on remote compute platforms. Integrated Framework for leveraging on prem server compute resources, GPU farms and external cloud infrastructure
MI
ME
MTA
MI
ME
MTA
MI
ME
MTA
Available
In Flight
In Planning
The DeepView AppPack provides you with the building blocks and glue for robust, turn-key intelligent vision applications.
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.
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