Deployment
Last updated
Was this helpful?
Last updated
Was this helpful?
After training and validating your model, you can now deploy it to any device. This makes the model run without an internet connection, minimizes latency, and runs with minimal power consumption.
The Deployment page consists of a variety of deployment options to choose from depending on your target device. Regardless of whether you are using a or not, you can deploy your impulse to any device. The C++ library and Edge Impulse SDK enable the model to run without an internet connection on the device, minimize latency, and with minimal power consumption.
Model version: Quantized (int8) vs unoptimized (float32) versions.
There are 6 main deployment options currently supported by Edge Impulse:
From the Deployment page, select the Search deployment options search box to select and configure a deployment option:
These deployment options let you turn your impulse into a fully optimized source code that can be further customized and integrated with your application. The customizable library packages all of your signal processing blocks, configuration and machine learning blocks into a single package with all available source code. Edge Impulse supports the following libraries (depending on your dataset's sensor type):
Library
Description
C++ Library
Arduino Library
WebAssembly
Cube.MX CMSIS-PACK
DRP-AI Library
OpenMV Library
Ethos-U Library
Simplicity Studio Component
TensorRT Library
TIDL-RT Library
Tensai Flow Library
To deploy your model using ready-to-go binaries, select your target device and click "build". Flash the downloaded firmware to your device then run the following command:
The impulse runner shows the results of your impulse running on your development board. This only applies to ready-to-go binaries built from the studio.
If your training and testing datasets include a sensor data type that is not supported by a deployment target, the search box will include these greyed out with a Not supported label:
If you are developing for Linux-based devices, you can use Edge Impulse for Linux for deployment. It contains tools that let you collect data from any microphone or camera, can be used with the Node.js, Python, Go and C++ SDKs to collect new data from any sensor, and can run impulses with full hardware acceleration - with easy integration points to write your own applications.
Deploying Edge Impulse models as a Docker container allows for packaging signal processing, configurations, and learning blocks into a single container that exposes an HTTP inference server. This method is ideal for environments supporting containerized workloads, facilitating deployment on gateways or in the cloud with full hardware acceleration for most Linux targets. Users can initiate deployment by selecting the "Docker container" option within the Deployment section of their Edge Impulse project.
You can run your impulse directly on your computer/mobile phone without the need of an additional app. To run on your computer, click Launch in browser. To run on your mobile phone, scan the QR code and click Switch to classification mode.
Download the most recent build from your project's deployment page under Latest build:
The EON Compiler lets you run neural networks using less RAM, and saving flash resource, while retaining the same accuracy compared to LiteRT (previously Tensorflow Lite) for Microcontrollers.
You can also select whether to run the unquantized float32 or the quantized int8 models. To compare model accuracy, run model testing in your project by clicking Run model testing.
To have a peek at how your impulse would utilize compute resources of your target device, Edge Impulse also gives an estimate of latency, flash, and RAM to be consumed by your target device even before deploying your impulse locally. This can save you a lot of engineering time, and costs incurred by recurring iterations and experiments.
You can also select different options on the deployment page:
Compiler options: TFLite vs . The EON Compiler also comes with an extra option: EON Compiler (RAM optimized) to reduce the RAM even further when possible.
Deploy as a
Deploy as a - for fully supported development boards
Use for Linux targets
Deploy as a
Run directly on your
Create a (Enterprise feature)
A portable C++ library with no external dependencies, which can be compiled with any modern C++ compiler.
An Arduino library with examples that runs on most Arm-based Arduino development boards.
A WebAssembly package that can be run in browsers or other JavaScript environments.
A CMSIS-PACK library for integrating Edge Impulse models with STM32CubeMX for STM MCUs.
Generate machine learning models using DRP-AI TVM with the DRP-AI Translator for use on Renesas RZ/ products.
An OpenMV library for vision-based projects, enabling efficient deployment on OpenMV cameras.
A C++ library for running machine learning models on Arm Ethos-U NPUs, optimized for low-power applications.
A C/C++ library package with Simplicity Studio Component file (SLCC) for integration with Silicon Labs' tools.
A library optimized for running inference on the GPU of NVIDIA Jetson devices using TensorRT.
A deployment option for generating machine learning models to use with Texas Instruments Deep Learning Accelerator (TIDL) on TI processors.
A library using Tensai Flow for running inference in building custom applications.
For these deployment options, you can use a ready-to-go binary for your development board that bundles signal processing blocks, configuration and machine learning blocks into a single package. This option is available for .
For a deep dive into deploying your impulse to Linux targets using Edge Impulse for Linux, you can visit the .
See how to .
When building your impulse for deployment, Edge Impulse gives you the option of adding another layer of optimization to your impulse using the .
Depending on your neural network architecture, we can also provide one extra layer of optimization with the .
