Search

Evaluation Kits

Ensemble E7 AI/ML AppKit

Get started with the Ensemble E7 AI/ML AppKit

The Ensemble E7 AI/ML AppKit (AK-E7-AIML) enables quick software development and evaluation for Endpoint Machine Learning use cases. Powered by an Alif Ensemble E7 fusion processor with four compute cores (two Arm Cortex-M55 and two Cortex-A32), and two machine learning accelerator coprocessors (two Arm Ethos-U55 microNPUs) with ample memory and peripherals, this kit is the ideal platform to build Endpoint ML projects that input sensor data and leverage ML in an extremely power-efficient way. On board is a camera/image sensor for snapshots or video input, plus motion and sound sensors to round out a variety of Endpoint ML use case scenarios. Several pre-built applications are available for the AI/ML AppKit so you can quickly get started.

GitHub

We use GitHub to publish our device driver and OS packs, as well as demo applications, examples and more. You can access our repositories here.

AI/ML AppKit User Guide – With J-Link On-Board

(v1.3) This User Guide will get you up and running with your AI/ML AppKit with J-Link On-Board (revision D3 or above) which, with its integrated camera, display, and microphones, is ideal for developing applications using audio, video, or graphics libraries.

AI/ML AppKit User Guide

(v1.3) This User Guide will get you up and running with your AK-E7-AIML which, with its integrated camera, display, and microphones, is ideal for developing applications using audio, video, or graphics libraries.

Ensemble AI/ML AppKit Pre-Built Demos

(v2.0 & v3.0) This archive contains pre-built binary files for some AI/ML demos for the AK-E7-AIML. Download the version appropriate to the camera module installed on your AppKit.

Alif Security Toolkit

(v1.104.001) The Alif Security Toolkit is for use with the Ensemble devices or evaluation kits. After downloading your Toolkit, be sure to update your board to the same version by running the updateSystemPackage utility.

ML Evaluation Kit Repo

Alif Semiconductor Repository forked from the ARM ml-embedded-evaluation-kit from https://git.mlplatform.org/ml/ethos-u/ml-embedded-evaluation-kit.git.

AI/ML Design Flows

(v1.0) This white paper describes the steps of how a machine learning model that was trained and converted to a TFLite (quantized) format, needs to be further processed so it can take advantage of the Ethos U55 NPU accelerators in Alif Ensemble devices.

AI/ML AppKit Schematics

Schematics for the AK-E7-AIML.

Camera Module Adapter Board Schematics

This is a reference design of an adapter board from the IAS camera module connector on the Alif AppKit and DevKit, to the HM0360 & 15-pin Arducam connectors used on Raspberry Pi boards.

AI/ML AppKit Altium Project Files

This zip is a set of Altium project files for the PCB used in the AK-E7-AIML.

AI/ML AppKit Bill of Materials

This is the bill of materials for the AK-E7-AIML.

E7 Hardware Reference Manual

(v2.8) Fusion Processor with quad cores up to 160MHz, 400MHz, and 800MHz operation capable of running combinations of Linux and/or RTOS, large memory, secure enclave, many peripherals, and AI/ML NPUs accelerators up to 250 GOPS performance.

E7 Datasheet

(v2.11) Fusion Processor with quad cores up to 160MHz, 400MHz, and 800MHz operation capable of running combinations of Linux and/or RTOS, large memory, secure enclave, many peripherals, and AI/ML NPUs accelerators up to 250 GOPS performance.

Ensemble Software Reference Manual

(v1.8) Software Reference manual for the entire family of Ensemble scalable and compatible MCUs and fusion processors.

X

(Required)
This field is for validation purposes and should be left unchanged.