Frequently Asked Questions

Find answers to your questions below or contact us anytime. We’re always here to help.

About Edge Impulse

What is Edge Impulse?

Edge Impulse is the leading platform for building, refining and deploying machine learning (ML) models to edge devices. We provide tools to add artificial intelligence (AI) capabilities directly onto the billions of devices that run our world.

How does Edge Impulse help businesses?

Edge Impulse enables organizations to build, deploy, and scale edge AI faster and more seamlessly than ever, accelerating time to market.

What is edge AI?

Edge AI is the process of running AI algorithms on devices at the edge of the network, instead of the cloud. The “edge” refers to the periphery of a network, which includes end-user devices and equipment that connects devices to larger networking infrastructure, such as the internet. Take our free Introduction to Edge AI course to learn more!

Benefits of Edge AI

What are the advantages of adopting edge AI? 

Developing AI models for edge devices addresses well known challenges encapsulated in the acronym BLERP:

  • Bandwidth: By running algorithms on-device, you avoid sending sensor data to the cloud, reducing the level of connectivity required.
  • Latency: On-device algorithms can be much more responsive, since there’s no round-trip to the cloud required.
  • Economics: Reducing connectivity demands can save on both BOM and network communications costs, and removing the need for cloud-hosted AI systems can massively reduce costs.
  • Reliability: The simplicity of on-device AI systems removes all of the connectivity overhead, making them inherently more reliable than those in the cloud, essential applications where safety and user experience are critical.
  • Privacy: Edge AI allows you to benefit from AI without any data leaving the device, ensuring user privacy.

ML/AI models that are optimized for the edge overcome the issues of BLERP by design.

How does Edge Impulse help realize these benefits?

Edge Impulse is a suite of tools that helps you build, test, and deploy edge AI algorithms. It covers the entire workflow, from data collection to model optimization and production monitoring. Edge Impulse increases the velocity of edge AI development while reducing costs and associated risks. 

We have an in-house team of machine learning engineers. Why do we need Edge Impulse?

Edge Impulse isn’t designed to replace machine learning expertise. Instead, it’s designed to assist practitioners in navigating the unique challenges of working with sensor data and resource-constrained hardware. You can think of it as a toolbox of essential items that save you time and allow you to focus on applying your domain expertise. We built the Edge Impulse platform to solve well known edge AI challenges. Here are some of the steps we took with every kind of edge AI developer, engineer, and scientist in mind:

  • Our digital signal processing algorithms are battle-tested and based on the latest research. They’re already optimized for high performance on any class of device. No need to rely on others to port Python feature engineering code to C++.
  • We provide accurate estimates of on-device performance for models, and help you debug compatibility and performance issues. Instantly understand the performance impact of architecture changes; no need to muck around with benchmarking on a physical device or wait for your embedded team to test models.
  • If you have an existing model, we’ll help you select the ideal hardware to run it. If you already know your target hardware, our target-aware hyperparameter optimization framework (EON Tuner) will help you identify the model architectures that meet your latency and memory requirements.
  • Our system handles quantization and other optimizations, allowing you to compare the before and after results and decide which to apply.
  • We convert any saved model format to C++, so you can benefit from vendor-specific optimizations for ultra fast performance, even if your embedded team is unfamiliar with machine learning.
  • We provide embedded-specific model architectures, like FOMO (Fast Objects More Objects) and FOMO-AD (Fast Objects More Objects-Anomaly Detection), which you can’t find anywhere else. Download them as containers to make your own enhancements.
  • Our market-leading Edge Optimized Neural (EON) Compiler, runs models with reduced RAM and flash usage, It supports a diverse range of neural networks from TensorFlow or PyTorch, as well as classical ML models from scikit-learn, LightGBM, or XGBoost. This ensures rapid execution of neural network models for real-time or near-real-time scenarios, all the while maintaining accuracy:

   Up to 70% less RAM usage
   Up to 40% less flash usage
   Faster inference times
   Reduced overall power consumption

Platform Compatibility

How does Edge Impulse ensure compatibility with existing machine learning workflows?

Edge Impulse is designed to integrate thoughtfully with your machine learning workflow, integrating with all major tools and formats. Our Python SDK makes it easy to optimize models for the edge from wherever you prefer to work: inside Jupyter notebooks and training scripts, PyTorch, TensorFlow, or scikit-learn. You can transform a deep learning model into an edge-optimized C++ library with a single line of Python code.

As a modular toolbox, you can use whichever parts of Edge Impulse you prefer for a given project. Train a model in Python and optimize it for the edge with the Edge Impulse Python SDK, or upload your Numpy or Pandas dataset and run a target-aware hyperparameter sweep that automatically determines the best model architecture for a given hardware target—all from a Python script or notebook.

Edge Impulse does not lock you in: we use standard formats for storing data and models, and you can easily integrate with other MLOps platforms such as Weights & Biases. You can control every feature of Edge Impulse with our REST API, making it easy to automate with systems such as continuous integration as part of your ML pipeline.

Does Edge Impulse integrate with existing platforms/ infrastructure?

Yes, the enterprise version of Edge Impulse can integrate directly with your cloud service to access and transform data.

What are the benefits of integrating Edge Impulse with cloud services?

The benefits of integrating Edge Impulse with cloud services include direct access to and transformation of data. This integration facilitates the management and processing of data from cloud services within the Edge Impulse platform, enhancing the efficiency and capabilities of edge AI solutions.

I already have trained models, can I use Edge Impulse to optimize for edge devices?

If you have your own training code, you can easily wrap it into a container and host it inside Edge Impulse as a custom learning block, benefitting from our target-aware hyperparameter tuning (EON Tuner), and the generous GPU compute included with our enterprise license. You can do the same with custom data transformation and deployment code.

How customizable is the platform to specific use cases?

Edge Impulse is highly customizable to specific use cases. You have full freedom in the models that you design, allowing you to plug in new signal processing blocks and completely new neural networks. Additionally, Edge Impulse supports the creation of custom deployment blocks for your organization, enabling the development of binaries for unreleased products, packaging of impulses as custom libraries, or deployment to private targets.

How do I add new signal processing blocks in Edge Impulse? How can I create custom deployment blocks for my organization?

You can do so by following the instructions here.

Is my edge device/processor/silicon/etc. supported?

Edge Impulse supports any edge AI Hardware that can run C++, and more. This includes a variety of MCU-based hardware and Linux-based hardware. For MCU-based hardware, Edge Impulse provides options like: default firmware, examples for integrating your impulse with custom firmware, integrated deployment options, profiling, and extensive hardware testing.

For Linux-based hardware, options include the Edge Impulse for Linux SDK and Command Line Interfacing (CLI) tooling, deployment options as native linux executables, Edge Impulse Model notable as .eim format, and Docker containers, Linux Inferencing SDKs, and profiling. If your hardware is not listed, you can still use Edge Impulse by uploading data in various formats (e.g., CSV, JPG, WAV) and deploying your trained model as a C++ library, which requires a C++ compiler and sufficient flash/RAM on your device.

Technical Specifications

How can I try out the Edge Impulse platform? 

To try out the Edge Impulse platform, follow our getting started guide.

How scalable is your platform for large-scale deployments?  

Edge Impulse's platform is designed for scalability, especially for startups and enterprises looking to scale edge ML algorithm development from prototype to production. It offers an enterprise version that includes all the tools needed to go from data collection to model deployment, such as a robust dataset builder to future-proof your data, integrations with all major cloud vendors, dedicated technical support, custom DSP and ML capabilities, and full access to the Edge Impulse APIs to automate your algorithm development.

What support is available for large-scale deployment on Edge Impulse?

For startups and enterprises looking to scale edge ML algorithm development from prototype to production, Edge Impulse offers an enterprise version. This includes all of the tools needed to go from data collection to model deployment. For more information, click here.

How do I access the enterprise version of Edge Impulse?

To access the enterprise version of Edge Impulse, you can try it out with the enterprise free trial.
The enterprise version of Edge Impulse offers a range of features designed to scale edge ML algorithm development from prototype to production. These features include a robust dataset builder to future-proof your data, integrations with all major cloud vendors, dedicated technical support, custom DSP and ML capabilities, and full access to the Edge Impulse APIs to automate your algorithm development.

Does Edge Impulse build models for me?

Edge Impulse builds models for you. It provides tools and processes to help you collect and label data, design features, and automatically train machine learning models. You can choose from different machine learning blocks for tasks such as Classification, Anomaly Detection, Regression, Image or Audio Transfer Learning, and Object Detection. Edge Impulse exposes the Keras API in an easy-to-use interface for these tasks, and you can also bring your own architecture/training pipeline as a custom block.

What kind of machine learning models can I build with Edge Impulse?

You can build various types of machine learning models with Edge Impulse, including:

  • Classification
  • Anomaly Detection
  • Regression
  • Image or Audio Transfer Learning
  • Object Detection

Get more information here

How do I deploy my model to an edge device using Edge Impulse?

To deploy your model to an edge device using Edge Impulse, follow these steps:

Navigate to the Deployment page in your Edge Impulse project.

Choose from a variety of deployment options depending on your target device. These options include deploying as a C++ library, Arduino library, WebAssembly package, Python library, Docker container, or directly to mobile phones/computers.

For deploying as a customizable library or pre-built firmware, select your desired option, configure it if necessary, and then click Build at the bottom of the page.

If deploying to Linux-based devices, you can use Edge Impulse for Linux.

This tool allows you to collect data from any microphone or camera, use SDKs to collect new data from any sensor, and run impulses with full hardware acceleration.

To deploy using a Docker container, select the "Docker container" option within the Deployment section, which packages your signal processing, configurations, and learning blocks into a single container that exposes an HTTP inference server

To run your impulse directly on your computer or mobile phone, select the appropriate option and follow the instructions provided here.

Can I combine/stack models?

Edge Impulse facilitates multi-impulse deployment, enabling the combination or stacking of multiple models to enhance overall performance and functionality. The deployment block for multi-impulse configurations can be accessed within Edge Impulse Studio. By leveraging this feature, users can seamlessly integrate multiple models to address complex use cases and achieve superior outcomes.

The deployment block can be found here. To add it to your organization, head to this page: Edge Impulse Studio -> Organizations -> Custom blocks -> Deployment blocks.

Please note that the script works with EON compiled projects only and anomaly detection blocks have not been tested.

Data Security and Privacy

What type of data does Edge Impulse collect and what are the data sources?

Edge Impulse can handle data from a wide range of sources, including new development boards or devices that have been in production for years. The types of data it can collect include data from various sensors, such as accelerometers, microphones, cameras, and custom sensors. Data can be posted to the ingestion service directly from devices (if they have an IP connection) or through an intermediate protocol like a phone application. Additionally, Edge Impulse supports importing data in various formats, including JPG, PNG images, MP4, AVI video files, WAV audio files, CBOR/JSON files in the Edge Impulse data acquisition format, and CSV files.

How do I use the data forwarder to collect data from sensors? What formats are supported for importing data into Edge Impulse? How can I label and import data that has already been collected?

The answers to these questions can be found in the Porting Guide and Data documentation.

How does Edge Impulse secure my data?

Edge Impulse is SOC II Compliant. Our commitment to SOC II compliance shows we care about where your sensitive data lives. We implement controls, risk assessment processes, and policies to protect this data, and ultimately your organization and customers. We see it as the first line of cyber security defense in the model development process. Your data is precious and we intend to safeguard it so it can realize its true value in the real world.

Edge Impulse stores data in storage buckets that you link to your organization. You can use AWS S3 buckets, Google Cloud Storage, or any S3-compatible bucket. You need to provide the bucket name, region, endpoint, and access and secret keys to connect your bucket. A green dot indicates a successful connection.

How can I import data into my Edge Impulse project?

You can import data into your Edge Impulse project by following these steps:

  • Collect/import data: You can collect data directly from your sensors or import existing datasets. Edge Impulse provides tools for collecting data from various sensors, such as recording audio, capturing images, or reading sensor values. You can also import data from storage buckets by linking your organization with AWS S3 buckets, Google Cloud Storage, or any S3-compatible bucket.
  • Use your mobile phone: You can use your mobile phone to import image data into Edge Impulse. After connecting your phone to your project, you can start capturing images directly through a special UI for collecting images quickly.
  • Use the OpenMV Cam H7 Plus: To import data collected with the OpenMV Cam H7 Plus, you can set up your environment, collect images, and then send the dataset to Edge Impulse. This involves using the OpenMV IDE to capture images and then exporting the dataset to your Edge Impulse project.
  • Upload data directly: If you have a dataset collected through a different method, you can upload the data directly to Edge Impulse. This can be done visually through the studio or via the CLI. It's recommended to use square images for image datasets.

What format does Edge Impulse Support for data import?
  • JPG, PNG images
  • MP4, AVI video files
  • WAV audio files
  • CBOR/JSON files in the Edge Impulse data acquisition format
  • CSV files

Learn more here

How do I manage datasets in Edge Impulse?

To manage datasets in Edge Impulse, follow these steps:

  • Link Storage Buckets: First, link your organization with one or several storage buckets. Choose from AWS S3 buckets, Google Cloud Storage, or any S3-compatible bucket. Fill in the form with your bucket name, region, endpoint, access, and secret keys.
  • Create a New Dataset: Navigate to the Datasets tab and click on + Add new dataset. Fill out the form and click on Create dataset.

Adding Data to Your Project:

  • For Default datasets, navigate in your bucket following the directory structure. Use the "+ New folder" button to add data, and drag and drop your files and folders to upload them to your bucket.
  • For Clinical datasets, the clinical view lets you easily manage your data, but to import data, you will need to set up an ingestion pipeline or upload them directly to your bucket.
  • Import Data into a Project: Go to the Actions...->Import data into a project, select the project you wish to import to, and configure how to label this data. This step imports the data into the project and optionally creates a new label for each file in the dataset.
  • Previewing Data: Edge Impulse has added a data preview feature, allowing you to visualize certain types of data directly within the organization data tab. Supported data types include tables (CSV/Parquet), images, PDFs, audio files (WAV/MP3), and text files (TXT/JSON).

More info on datasets here.

How does Edge Impulse handle IP rights?

You own your data, period. Have confidence that when you upload reference data from your cloud or on-premise environment to Edge Impulse to train your model that it will automatically be deleted upon completion at your discretion. Any data in transit is secured using SSL/TLS. This information is spelled out in our ToS.

Company Information

Where is Edge Impulse headquartered?

We’re headquartered in San Jose, CA.

What pricing options are available with Edge Impulse?

See our pricing page for more information.

Who are Edge Impulse customers?

Our customers span across multiple industries including healthcare, industrial, and a variety of other applications.

Does Edge Impulse offer consulting services?

No, Edge Impulse does not offer consulting services.

Pricing

What does commercial use mean?

Commercial use is using the Edge Impulse platform in whole or in part with an intention for cost savings, revenue generation or other commercial advantage

What does non-commercial use mean?

Non-commercial use is use solely for exploratory work, research or demo purposes that is not used in whole or in part for cost savings or revenue generation in any use case, product or service, and that is not primarily intended for or directed towards commercial advantage

Can I transition from a Professional license to an Enterprise License?

Yes, and if you upgrade to an Enterprise Plan and regenerate your “Output”, you will be granted ownership of all your Output.

Do I own the data I upload to Edge Impulse?

Yes, all users on the platform continue to own all rights, title and interest in and to the non-public data they upload to the Edge Impulse website - defined as “Customer Data” subject to a license back to Edge Impulse during the subscription term for compliance purposes only.

Do I own output generated by utilizing the Edge Impulse platform?

In the case of Community and Professional Plans, Output is owned by Edge Impulse, and you are granted a license to the Output as long as the user is in compliance with the Terms of Service (”ToS”).  Enterprise Plan customers own their Output.

What rights does Edge Impulse have to my Output?

Edge Impulse ONLY has a right to user Output for compliance purposes. Edge Impulse does NOT have any rights to publish or distribute any Output generated by the user.

What are the main differences between Community and Professional Plan?

Community Plan:

Free

  • Ideal for students and independent developers focused on Edge AI exploration.
  • Highly restricted access to compute resources and enterprise grade features and compute time.
  • Non-commercial use only

Professional Plan:

  • Ideal for individual developers to formalize exploration of Edge AI specific use cases
  • Increased feature set over the Community Plan including NVIDIA TAO models
  • Commercial use - when Output is used in an entity with less than 15 FTE’s (FTE = Full-time employees and Full-time and Part-time contractors)

See the Pricing Page for a comparison chart.

What are the main differences between Professional and Enterprise Plans?

Enterprise includes additional features, needed for robust edge AI deployment, which are not included in the Pro Plan:  

  • Full Suite of Enterprise Features
  • Commercial Use
  • Ownership of Output
  • Unlimited Compute Time Per Job
  • Unlimited DSP file size
  • Organization Level Tools
  • EON Compiler: BYOM or RAM Optimization Mode
  • Private Processing Blocks
  • FOMO-AD, DALL-E, HRV DSP
  • Premium Support offerings
What level of support do I get?

The Professional Plan includes email support that triggers a support ticket and access to the Edge Impulse Developer Relations Forum with priority for quick answers. You will also have access to our complete library of documentation and Getting Started guides. The Enterprise Plan includes access to Premium support.

What constitutes a job?

A ‘job’ refers to a model training job scheduled within Edge Impulse’s infrastructure.

Are there hard limits?

Yes. Training job limits: 20 min/job for Community Plan and the 60 min/job for Professional Plan are hard limits.
Memory limits: DSP, CPU and GPU memory limits are hard limits. There is no job limit on the Enterprise Plan.

If I have a Professional Plan can I still access an Enterprise Trial?

Yes, absolutely, sign-up for the Enterprise Trial https://studio.edgeimpulse.com/trial-signup now and get access to all Enterprise features for 14 days.

What constitutes Output?

Output refers to the project deployment package, and artifacts generated on the Edge Impulse platform (including any files, texts, events or other data sets), listed on the user dashboard of a project when a model is created. Output is created by your data combined with the Edge Impulse tools to create a unique model ready for testing or deployment.

Do I own my data?

User original non-public data uploaded to the Edge Impulse website always belongs to the User. Once it is used on the Edge Impulse platform, the original data is still the users IP, but the new Output created using the Edge Impulse tools and on the Edge Impulse platform is owned and licensed back to the user under the ToS on the Community and Professional Plans. The Output created on the Enterprise plan is owned by the user as noted in the Enterprise ToS.

When can I use my Output and Deployment Package, created on the Edge Impulse Platform, for commercial use?

Community Plan: No Commercial Use

Professional Plan: Commercial Use of Output is included when used in entities of fewer that 15 full-time-equivalent headcount (full-time employees and full- and part-time contractors) that continue to maintain their monthly/annual Professional plan subscription. Termination of a Professional plan immediately terminates rights to use Output.

Professional Plan: Commercial Use is not permitted for companies with 15 or more FTEs.

Enterprise Plan: Includes full commercial use and ownership of Output.

Can competitors use Edge Impulse?

Community and Professional Plans:
No, and Edge Impulse reserves the right to suspend, cancel and/or terminate a competitor’s rights to use the account.

Enterprise Plan:
Yes, as long as the competitor does not access any Services or Documentation to build a competitor product or service or copy any ideas, features, functions or graphics of Services.

More Pricing Questions

Community

Professional

Enterprise

User Patent rights

Yes, with grant-back of patent rights to Edge Impulse for defensive purposes

Yes, with grant-back of patent rights to Edge Impulse for defensive purposes

Patent non-assert (patent holder/licensee promises not to assert its IP rights)

Covered parties include Edge Impulse, Edge Impulse customers, end users, vendors, and business partners

Commercial Use

Community Plan restricted to education, demo and research only. No Commercial rights. View Terms of Service for details.

Commercial rights limited to entities of 15 or less full-time employees and contractors. Larger companies are able to explore and research, with no Commercial rights. View Terms of Service for details.

Full commercial rights. View Enterprise terms of Service for details.

IP ownership - Software, Documentation, and website

Edge Impulse owns with license-back to user during subscription term

Edge Impulse owns with license-back to user during subscription term

Edge Impulse owns with license-back to user during subscription term

Community

Applicable Terms of Service

User Patent rights

Yes, with grant-back of patent rights to Edge Impulse for defensive purposes

Patent non-assert

Covered parties include Edge Impulse, Edge Impulse customers, end users, vendors, and business partners

Commercial Use

Community Plan restricted to education, demo and research only. No Commercial rights. View Terms of Service for details.

IP ownership - Site and Services including system software, patents, content

Edge Impulse owns with license-back to user during subscription term

Professional

User Patent rights

Yes, with grant-back of patent rights to Edge Impulse for defensive purposes

Patent non-assert

Commercial Use

Commercial rights limited to entities of 15 or less full-time employees and contractors. Larger companies are able to explore and research, with no Commercial rights. View Terms of Service for details.

IP ownership - Site and Services including system software, patents, content

Edge Impulse owns with license-back to user during subscription term

Enterprise

Applicable Terms of Service

User Patent rights

Patent non-assert

Commercial Use

Full commercial rights. View Enterprise terms of Service for details.

IP ownership - Site and Services including system software, patents, content

Edge Impulse owns with license-back to user during subscription term

Need more help?

Pricing, billing, & licensing

Have a pricing question or need help managing your account? Check out our plans & pricing page.

View plans & pricing
Product demo

Looking to evaluate Edge Impulse for your use case or need help with a custom solution?

Schedule a demo