# Edge Impulse Documentation - Tutorials

> Curated end-to-end, hardware, integration, tools, and topic tutorials.

This is the "Tutorials" section index of the Edge Impulse documentation, following https://llmstxt.org/. It lists the pages in this section only. For other sections see the root index at https://docs.edgeimpulse.com/llms.txt; for the complete expanded index see https://docs.edgeimpulse.com/llms-full.txt.

Links point to the markdown-rendered version of each page (`.md`), so agents retrieve clean content without navigation, ads, or scripts. Every link includes a short note describing the page.

## Intents

Intent-bearing retrieval prompts. Match a user request to the closest intent below, then retrieve the linked pages before answering.

### Get started with Edge Impulse from scratch

> I am new to Edge Impulse and want to understand the end-to-end workflow - collect data, design an impulse, train a model, and deploy it - so I can build my first edge AI project.

- [Build a first project with guided, beginner-friendly explanations.](https://docs.edgeimpulse.com/knowledge/guides/getting-started-for-beginners.md)
- [Configure the input, processing, and learning blocks that make up an impulse.](https://docs.edgeimpulse.com/studio/projects/impulse-design.md)
- [Pick a complete worked tutorial that matches the project you want to build.](https://docs.edgeimpulse.com/tutorials/end-to-end/overview.md)
- [Learn the core edge-AI concepts behind the workflow before building.](https://docs.edgeimpulse.com/knowledge/courses/edge-ai-fundamentals.md)

### Train an image classification model and deploy it to a device

> I want to collect labeled images, train a transfer-learning image classifier in Edge Impulse Studio, and deploy the model to a microcontroller or single-board computer.

- [Follow an end-to-end image classification project from data to deployment.](https://docs.edgeimpulse.com/tutorials/end-to-end/image-classification.md)
- [Collect and label image data directly in Studio.](https://docs.edgeimpulse.com/tutorials/topics/data/collect-image-data-studio.md)
- [Train an image classifier with transfer learning on limited data.](https://docs.edgeimpulse.com/studio/projects/learning-blocks/blocks/transfer-learning-images.md)
- [Export the trained impulse to run on your target device.](https://docs.edgeimpulse.com/studio/projects/deployment.md)

### Detect, locate, and count objects in a camera feed

> I want to build an object detection model that finds and counts multiple objects in real time on an embedded device, using FOMO or bounding boxes.

- [Follow an end-to-end object detection and counting project.](https://docs.edgeimpulse.com/tutorials/end-to-end/object-detection-centroids.md)
- [Use FOMO for fast, low-memory object detection on constrained devices.](https://docs.edgeimpulse.com/studio/projects/learning-blocks/blocks/object-detection/fomo.md)
- [Compare object detection block options and when to use each.](https://docs.edgeimpulse.com/studio/projects/learning-blocks/blocks/object-detection.md)
- [Count and track detected objects with post-processing.](https://docs.edgeimpulse.com/tutorials/topics/post-processing/count-objects-fomo.md)

### Build a keyword spotting or voice command model

> I want to recognize spoken keywords or voice commands that run entirely on-device, including how to gather or synthesize the audio data.

- [Follow an end-to-end keyword spotting project.](https://docs.edgeimpulse.com/tutorials/end-to-end/keyword-spotting.md)
- [Train a keyword model with audio transfer learning.](https://docs.edgeimpulse.com/studio/projects/learning-blocks/blocks/transfer-learning-keyword.md)
- [Synthesize keyword audio when you lack real recordings.](https://docs.edgeimpulse.com/tutorials/topics/data/generate-keyword-data-google-tts.md)
- [Reuse a ready-made keyword spotting dataset to get started.](https://docs.edgeimpulse.com/datasets/audio/keyword-spotting.md)

### Recognize motion or gestures from accelerometer data

> I want to classify movements or gestures from IMU / accelerometer time-series data and deploy the model to a wearable or microcontroller.

- [Follow an end-to-end motion / gesture recognition project.](https://docs.edgeimpulse.com/tutorials/end-to-end/motion-recognition.md)
- [Extract frequency features from motion signals with spectral analysis.](https://docs.edgeimpulse.com/studio/projects/processing-blocks/blocks/spectral-analysis.md)
- [Reuse a continuous motion dataset to prototype quickly.](https://docs.edgeimpulse.com/datasets/time-series/continuous-motion-recognition.md)

### Detect anomalies or defects (visual or sensor)

> I want to detect defects, faults, or unusual patterns by learning what 'normal' looks like, using visual anomaly detection or sensor-based anomaly detection.

- [Follow an end-to-end visual anomaly / defect detection project.](https://docs.edgeimpulse.com/tutorials/end-to-end/visual-anomaly-detection.md)
- [Detect visual defects with FOMO-AD when defect samples are scarce.](https://docs.edgeimpulse.com/studio/projects/learning-blocks/blocks/visual-anomaly-detection-fomo-ad.md)
- [Flag abnormal sensor readings with K-means anomaly detection.](https://docs.edgeimpulse.com/studio/projects/learning-blocks/blocks/anomaly-detection-k-means.md)

### Upload or collect data programmatically via the API and SDK

> I want to push samples into a project or pull data out programmatically using the Ingestion API or the Python SDK, including structured labels.

- [Reference the Ingestion API for uploading samples and device data.](https://docs.edgeimpulse.com/apis/ingestion.md)
- [Upload samples with structured multi-label metadata.](https://docs.edgeimpulse.com/tutorials/tools/apis/ingestion/ingest-structured-label-data.md)
- [Use the Python SDK to move data in and out of projects.](https://docs.edgeimpulse.com/tools/libraries/sdks/studio/python.md)
- [Upload and download project data from Python step by step.](https://docs.edgeimpulse.com/tutorials/tools/sdks/studio/python/upload-download-data.md)

### Automate training and deployment (MLOps / CI/CD)

> I want to automate model builds, testing, and deployment with the Studio API and CI pipelines like GitHub Actions for continuous edge MLOps.

- [Drive builds, tests, and deployments from the Studio API.](https://docs.edgeimpulse.com/apis/studio.md)
- [Wire training and deployment into a GitHub Actions pipeline.](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/deploy-github-actions.md)
- [Version, deploy, monitor, and update edge ML systems.](https://docs.edgeimpulse.com/knowledge/concepts/lifecycle/lifecycle-management.md)

### Ship over-the-air (OTA) model updates to deployed devices

> I want to update the model on already-deployed devices over the air, and understand the OTA update lifecycle and firmware integration.

- [Understand the over-the-air model update lifecycle.](https://docs.edgeimpulse.com/knowledge/concepts/lifecycle/ota-model-updates.md)
- [Implement OTA model updates in a C++ firmware application.](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-cpp.md)
- [Implement OTA model updates on Arduino devices.](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-arduino.md)

### Import and deploy my own pretrained model (BYOM)

> I already have a trained model and want to bring it into Edge Impulse, including custom or freeform input/output formats, and deploy it.

- [Bring your own model into a project and profile it for a target.](https://docs.edgeimpulse.com/studio/projects/dashboard/byom.md)
- [Deploy a model with custom or freeform input/output formats.](https://docs.edgeimpulse.com/tutorials/topics/machine-learning/deploy-freeform-model.md)

### Generate synthetic data when I lack real samples

> I don't have enough real-world data and want to generate synthetic images, audio, or time-series data to train my model.

- [Generate synthetic training data from inside Studio.](https://docs.edgeimpulse.com/studio/projects/data-acquisition/synthetic-data.md)
- [Understand when and how synthetic data helps model training.](https://docs.edgeimpulse.com/knowledge/concepts/data-engineering/synthetic-data.md)
- [Create synthetic image data with a generative model.](https://docs.edgeimpulse.com/tutorials/topics/data/generate-image-data-dall-e.md)

### Give an AI coding agent knowledge of Edge Impulse

> I want my AI coding agent to understand the Edge Impulse Studio and Ingestion APIs and my target hardware using Agent Skills.

- [Package Edge Impulse knowledge as an Agent Skill.](https://docs.edgeimpulse.com/tutorials/topics/ai-agents/create-edge-impulse-skill.md)
- [Build a companion skill scoped to your own project or hardware.](https://docs.edgeimpulse.com/tutorials/topics/ai-agents/create-a-companion-skill.md)
- [Reuse tested prompts for common Edge Impulse agent tasks.](https://docs.edgeimpulse.com/tutorials/topics/ai-agents/prompt-library.md)

## Tutorials

- [Tutorials](https://docs.edgeimpulse.com/tutorials.md)
- [End-to-end tutorials](https://docs.edgeimpulse.com/tutorials/end-to-end/overview.md)
- [Image classification](https://docs.edgeimpulse.com/tutorials/end-to-end/image-classification.md): Train a transfer-learning model to recognize objects and deploy it to a microcontroller.
- [Object detection with bounding boxes](https://docs.edgeimpulse.com/tutorials/end-to-end/object-detection-bounding-boxes.md): Detect and localize multiple objects in a scene with bounding boxes using transfer learning on an edge device.
- [Object detection with centroids](https://docs.edgeimpulse.com/tutorials/end-to-end/object-detection-centroids.md): Detect, count, and track objects in real time on a microcontroller using FOMO - 30× faster than MobileNet SSD and under 200K RAM.
- [Visual anomaly detection](https://docs.edgeimpulse.com/tutorials/end-to-end/visual-anomaly-detection.md): Learn what 'normal' looks like and automatically detect defects or unusual patterns in images - no labeled anomaly data required.
- [Visual regression](https://docs.edgeimpulse.com/tutorials/end-to-end/visual-regression.md): Build a model that predicts a continuous value - like a fill level or angle - directly from images, and deploy it to an embedded device.
- [Keyword spotting](https://docs.edgeimpulse.com/tutorials/end-to-end/keyword-spotting.md): Build a voice keyword detection system that runs entirely on an embedded device.
- [Sound recognition](https://docs.edgeimpulse.com/tutorials/end-to-end/sound-recognition.md): Build a model that recognizes specific sounds - like running water - from audio, and deploy it to an embedded device.
- [Motion recognition with anomaly detection](https://docs.edgeimpulse.com/tutorials/end-to-end/motion-recognition.md): Recognize gestures from accelerometer data with a neural network classifier and anomaly detection, deployed to a microcontroller.
- [Environmental sensor fusion](https://docs.edgeimpulse.com/tutorials/end-to-end/environmental-sensor-fusion.md): Fuse accelerometer and temperature sensor data to build a multi-sensor classifier, and deploy it to an Arduino Nano 33 BLE Sense.
- [HR/HRV estimation](https://docs.edgeimpulse.com/tutorials/end-to-end/hr-hrv-estimation.md): Extract heart rate and heart rate variability (HRV) features from PPG data to power health-monitoring applications at the edge.
- [Temperature anomaly detection on Opta PLC](https://docs.edgeimpulse.com/tutorials/end-to-end/temp-anomaly-detection-opta-plc.md): Detect temperature anomalies on an Arduino Opta PLC using Edge Impulse, with optional Arduino Cloud integration for remote monitoring.
- [OBD Automotive data](https://docs.edgeimpulse.com/tutorials/end-to-end/obd-automotive-data.md): Process OBD-II and CAN bus time-series data to classify vehicle faults, and run inference on a Linux SBC.
- [Avnet RASynBoard - motion recognition](https://docs.edgeimpulse.com/tutorials/hardware/avnet-rasyn-motion-recognition.md): Recognize gestures with a neural network on the Avnet RASynBoard (Renesas RA6 + Syntiant NDP 120) using Edge Impulse.
- [Particle Photon 2 - audio event detection](https://docs.edgeimpulse.com/tutorials/hardware/particle-photon2-audio-even-detection.md): Detect audio events like a doorbell ring on the Particle Photon 2 using a microphone and Edge Impulse.
- [Particle Photon 2 and Boron - motion recognition](https://docs.edgeimpulse.com/tutorials/hardware/particle-photon2-motion-recognition.md): Recognize gestures from IMU data on the Particle Photon 2 or Boron using Edge Impulse.
- [Renesas RA8D1 - NVIDIA TAO models](https://docs.edgeimpulse.com/tutorials/hardware/renesas-ra8d1-nvidia-tao.md): Run NVIDIA TAO pre-trained object detection and classification models on the Renesas RA8D1 Cortex-M85 MCU.
- [Renesas RZ/V2L - object detection (x2)](https://docs.edgeimpulse.com/tutorials/hardware/renesas-rzv2l-object-detection-x2.md): Run multiple object detection models simultaneously across two cameras on the Renesas RZ/V2L with DRPAI acceleration.
- [Sony Spresense - image classification](https://docs.edgeimpulse.com/tutorials/hardware/sony-spresense-image-classification.md): Classify objects through a camera using transfer learning on the Sony Spresense, and deploy the model to the device.
- [SiLabs xG24 Dev Kit - object detection](https://docs.edgeimpulse.com/tutorials/hardware/silabs-xg24-devkit-object-detection.md): Count people in real time using FOMO object detection on the SiLabs xG24 Dev Kit with AI/ML hardware accelerator.
- [Syntiant NDPs - keyword spotting](https://docs.edgeimpulse.com/tutorials/hardware/syntiant-ndp-keyword-spotting.md): Build a keyword spotting model and deploy it to Syntiant TinyML, Arduino Nicla Voice, or Avnet RASynBoard using Edge Impulse.
- [Syntiant NDPs - motion recognition](https://docs.edgeimpulse.com/tutorials/hardware/syntiant-ndp-motion-recognition.md): Recognize circular gestures from IMU data on the Syntiant TinyML Board or Arduino Nicla Voice using Edge Impulse.
- [TI LaunchXL - keyword spotting](https://docs.edgeimpulse.com/tutorials/hardware/ti-launchxl-keyword-spotting.md): Detect voice keywords on the TI LaunchXL using a deep neural network classifier trained in Edge Impulse.
- [TI LaunchXL - sound recognition](https://docs.edgeimpulse.com/tutorials/hardware/ti-launchxl-sound-recognition.md): Recognize specific sounds like running water on the TI LaunchXL using an audio classification model from Edge Impulse.
- [Motion recognition using an agent](https://docs.edgeimpulse.com/tutorials/end-to-end/motion-recognition-using-agent.md): Use an AI coding agent to take an Edge Impulse project from raw data collection through model training and deployment to a device.
- [Install Agent Skills](https://docs.edgeimpulse.com/tutorials/topics/ai-agents/create-edge-impulse-skill.md): Install Agent Skills from the Edge Impulse agent-tools repository to give AI coding agents persistent knowledge of the Edge Impulse platform, APIs, and deployment workflows.
- [Create a companion skill](https://docs.edgeimpulse.com/tutorials/topics/ai-agents/create-a-companion-skill.md): Use a companion skill that knows your target hardware and SDK so an AI agent can write application code that runs the exported model on your device.
- [Prompt library](https://docs.edgeimpulse.com/tutorials/topics/ai-agents/prompt-library.md): Ready-to-use AI agent prompts for every stage of an Edge Impulse project.
- [Collect image data using a mobile phone](https://docs.edgeimpulse.com/tutorials/topics/data/collect-image-data-phone.md): Collect and import labeled image data into Edge Impulse using your mobile phone as a wireless camera.
- [Collect image data using Studio](https://docs.edgeimpulse.com/tutorials/topics/data/collect-image-data-studio.md): Collect labeled image data directly into Edge Impulse Studio using a connected development board with an integrated camera.
- [Collect image data using OpenMV Cam H7 Plus](https://docs.edgeimpulse.com/tutorials/topics/data/collect-image-data-openmv-h7-plus.md): Collect and import labeled image data into Edge Impulse using the OpenMV Cam H7 Plus camera module.
- [Generate image data using Dall-E](https://docs.edgeimpulse.com/tutorials/topics/data/generate-image-data-dall-e.md): Use OpenAI's DALL-E to generate synthetic image datasets for Edge Impulse when real-world data is unavailable or difficult to collect.
- [Generate image data using RealVisXL](https://docs.edgeimpulse.com/tutorials/topics/data/generate-image-data-realvisxl.md): Generate photorealistic synthetic image datasets for Edge Impulse using the RealVisXL model hosted on Hugging Face.
- [Generate keyword data using Google TTS](https://docs.edgeimpulse.com/tutorials/topics/data/generate-keyword-data-google-tts.md): Generate synthetic keyword spotting audio datasets for Edge Impulse using Google Text-to-Speech to programmatically create labeled voice samples.
- [Generate time-series data using MATLAB](https://docs.edgeimpulse.com/tutorials/topics/data/generate-time-series-data-matlab.md): Generate synthetic time-series motion data in MATLAB using the Signal Processing Toolbox, and upload it to Edge Impulse for training.
- [Generate time-series data using PyBullet](https://docs.edgeimpulse.com/tutorials/topics/data/generate-time-series-data-pybullet.md): Generate synthetic accelerometer time-series datasets using PyBullet physics simulation and upload them to Edge Impulse for model training.
- [Label audio data using your existing model](https://docs.edgeimpulse.com/tutorials/topics/data/label-audio-data-existing-model.md): Use an existing Edge Impulse model to run inference on raw audio data and automatically upload the labeled results back to your project.
- [Label image data using GPT-4o](https://docs.edgeimpulse.com/tutorials/topics/data/label-image-data-gpt-4o.md): Automatically label unlabeled image datasets in Edge Impulse using GPT-4o vision to classify images based on a custom text prompt.
- [Build a custom processing block](https://docs.edgeimpulse.com/tutorials/topics/feature-extraction/build-custom-processing-blocks.md): Extend Edge Impulse with your own signal processing logic by building and deploying a custom processing block to Studio.
- [Use embeddings for sensor fusion](https://docs.edgeimpulse.com/tutorials/topics/feature-extraction/use-embeddings-sensor-fusion.md): Combine high-dimensional audio or image embeddings with time-series sensor data for advanced sensor fusion using custom DSP blocks.
- [Classify multiple 2D input features](https://docs.edgeimpulse.com/tutorials/topics/machine-learning/classify-multiple-2d-features.md): Train a neural network with multiple 2D feature branches for sensor fusion classification using a single Edge Impulse model.
- [Deploy pretrained models with freeform outputs](https://docs.edgeimpulse.com/tutorials/topics/machine-learning/deploy-freeform-model.md): Import and deploy a pretrained model with custom input/output formats into Edge Impulse using freeform model deployment.
- [Use the regression learning block](https://docs.edgeimpulse.com/tutorials/topics/machine-learning/use-regression-learning-block.md): Design a regression model in Edge Impulse to predict continuous values from time-series sensor data, applied to a cold-chain monitoring use case.
- [Visualize neural networks decisions with Grad-CAM](https://docs.edgeimpulse.com/tutorials/topics/machine-learning/visualize-neural-netowrks-gradcam.md): Use Grad-CAM to visualize which parts of an image your neural network focuses on when making classification decisions.
- [Run multiple impulses (C++)](https://docs.edgeimpulse.com/tutorials/topics/inference/run-multiple-impulses-cpp.md): Run two independent Edge Impulse impulses simultaneously on a microcontroller using the C++ SDK.
- [Run on Qualcomm Device Cloud](https://docs.edgeimpulse.com/tutorials/topics/inference/run-qualcomm-device-cloud.md): Run Edge Impulse inference on real Qualcomm hardware remotely using Qualcomm Device Cloud, without needing to purchase physical devices.
- [Sample audio continuously](https://docs.edgeimpulse.com/tutorials/topics/inference/sample-audio-continuously.md): Continuously capture and classify audio on an embedded device using the Edge Impulse SDK's continuous inferencing mode to avoid missing audio events.
- [Count objects using FOMO](https://docs.edgeimpulse.com/tutorials/topics/post-processing/count-objects-fomo.md): Post-process FOMO detections to accurately count objects by tracking centroids across video frames.
- [Two-stage OCR on Linux devices](https://docs.edgeimpulse.com/tutorials/topics/model-cascades/ocr.md): Build a two-stage OCR pipeline on Linux edge devices using model cascading - detect text regions, then recognize characters.
- [Acquire and process data using Golioth on AI](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/acquire-process-golioth.md): Securely collect and process labeled sensor data from cellular-connected devices using Golioth on AI and Edge Impulse custom transformation blocks.
- [Deploy using GitHub Actions](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/deploy-github-actions.md): Automate Edge Impulse model builds and deployments using GitHub Actions and the Edge Impulse REST API for continuous integration and delivery.
- [Allxon](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-allxon.md): Deploy over-the-air Edge Impulse model updates to NVIDIA Jetson edge devices using Allxon's remote device management platform.
- [Arduino IDE (for ESP32)](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-arduino.md): Deploy over-the-air (OTA) Edge Impulse model updates to ESP32 devices using the Arduino IDE and the Edge Impulse REST API for automated update checks.
- [Arduino IoT Cloud](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-arduino-iot-cloud.md): Deploy over-the-air (OTA) Edge Impulse impulse updates to Arduino devices using the Arduino IoT Cloud.
- [Balena](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-balena.md): Deploy over-the-air (OTA) Edge Impulse model updates to Linux edge devices using Balena's container-based fleet management platform.
- [Blues Wireless](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-blues-wireless.md): Deploy over-the-air (OTA) Edge Impulse firmware updates to Blues Wireless Notecard-connected devices using Notehub DFU.
- [C++](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-cpp.md): Implement over-the-air (OTA) Edge Impulse model updates in C++ by storing the model in a file or partition separate from the application binary.
- [Espressif IDF](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-espressif-idf.md): Deploy over-the-air (OTA) Edge Impulse model updates to ESP32 devices using the Espressif IDF OTA framework and Edge Impulse REST API.
- [Nordic Thingy53](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-thingy53.md): Deploy over-the-air (OTA) Edge Impulse model updates to the Nordic Thingy:53 using the Nordic Thingy app and the firmware DFU pipeline.
- [NVIDIA Jetson](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-jetson-nano.md): Deploy over-the-air (OTA) Edge Impulse model updates to NVIDIA Jetson Nano using Docker containers and the Edge Impulse Linux runner.
- [Particle Workbench](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-particle-workbench.md): Deploy over-the-air (OTA) Edge Impulse impulse updates to Particle Photon 2 devices using Particle Workbench and the Edge Impulse API.
- [Particle Webhook](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-particle-webhook.md): Configure a Particle webhook to forward sensor data to the Edge Impulse ingestion API as part of an OTA model update and active learning pipeline.
- [Zephyr on Golioth](https://docs.edgeimpulse.com/tutorials/topics/lifecycle-management/ota-zephyr-golioth.md): Deploy over-the-air (OTA) Edge Impulse model updates to Zephyr RTOS devices using Golioth's cloud OTA service and the Edge Impulse REST API.
- [Android series overview](https://docs.edgeimpulse.com/tutorials/topics/android/android-series.md): Deploy Edge Impulse models on Android using the NDK and Edge Impulse C++ SDK
- [Static buffer inference on Android](https://docs.edgeimpulse.com/tutorials/topics/android/static-buffer-inference.md): Run Edge Impulse inference with pre-loaded test data on Android
- [Keyword spotting on Android](https://docs.edgeimpulse.com/tutorials/topics/android/keyword-spotting.md): Build a real-time audio keyword recognition app on Android using your phone's microphone
- [QNN hardware acceleration on Android](https://docs.edgeimpulse.com/tutorials/topics/android/qnn-acceleration.md): Enable Qualcomm AI Engine Direct SDK acceleration for Edge Impulse models on Snapdragon devices
- [Android data collector](https://docs.edgeimpulse.com/tutorials/topics/android/android-data-collector.md): Collect phone sensor data, images, and BLE-relayed inference results from a Zephyr device, and upload directly to your Edge Impulse project
- [Zephyr series overview](https://docs.edgeimpulse.com/tutorials/topics/zephyr/zephyr-module-series.md): A series of tutorials on using Edge Impulse Zephyr Module for deploying machine learning models using the Edge Impulse Zephyr Module
- [Porting Zephyr Projects Between Boards](https://docs.edgeimpulse.com/tutorials/topics/zephyr/porting-between-boards.md): Learn how to port Edge Impulse Zephyr applications between different hardware platforms
- [IMU inference on Zephyr](https://docs.edgeimpulse.com/tutorials/topics/zephyr/zephyr-module-imu.md): Run Edge Impulse machine learning models for real-time motion classification on Zephyr RTOS using IMU sensors
- [Microphone Keyword Spotting on Zephyr](https://docs.edgeimpulse.com/tutorials/topics/zephyr/zephyr-module-microphone-kws.md): Run Edge Impulse audio keyword spotting models on Zephyr RTOS using PDM microphones
- [BLE GATT sensor bridge for Edge Impulse](https://docs.edgeimpulse.com/tutorials/topics/zephyr/zephyr-ble-gatt-client.md): Stream IMU data and inference results over BLE using Zephyr - supports Nesso N1 (ESP32-C6), Arduino Nano 33 BLE Sense, and Nordic Thingy:53
- [Robotics with Edge Impulse and ROS 2](https://docs.edgeimpulse.com/tutorials/topics/robotics-series/robotics-series.md): Build robotics workflows that combine ROS 2, Edge Impulse vision models, simulation, and physical robot deployment.
- [Run Edge Impulse Object Detection with ROS 2](https://docs.edgeimpulse.com/tutorials/topics/robotics-series/edgeimpulse-ros2-integration.md): Use edgeimpulse_ros to run a Linux .eim model on a ROS 2 image topic and publish vision_msgs detection messages.
- [Run Edge Impulse Vision on a JetBot with Rubik Pi](https://docs.edgeimpulse.com/tutorials/topics/robotics-series/wheeled-robot-ros2-integration.md): Combine JetBot ROS 2 motor control on Qualcomm Rubik Pi with Edge Impulse Linux object detection.
- [Run Edge Impulse Pick and Place with UNO Q Braccio](https://docs.edgeimpulse.com/tutorials/topics/robotics-series/robotic-arm-ros2-integration.md): Use Edge Impulse object detection, ROS 2, and an Arduino UNO Q to sort colored blocks with a TinkerKit Braccio arm.
- [Build a Mobile Inspection System with Edge Impulse and ROS 2](https://docs.edgeimpulse.com/tutorials/topics/robotics-series/wheeled-inspection-system.md): Design a wheeled rover inspection workflow with ROS 2, Edge Impulse detection, anomaly scoring, gimbal control, logging, and safety layers.
- [Ingest structured label data](https://docs.edgeimpulse.com/tutorials/tools/apis/ingestion/ingest-structured-label-data.md)
- [Collect data from a device](https://docs.edgeimpulse.com/tutorials/tools/apis/studio/collect-data-device.md)
- [Customize the EON Tuner](https://docs.edgeimpulse.com/tutorials/tools/apis/studio/customize-the-eon-tuner.md)
- [Deploy a model](https://docs.edgeimpulse.com/tutorials/tools/apis/studio/deploy-model.md)
- [Use the Python API bindings](https://docs.edgeimpulse.com/tutorials/tools/api-bindings/studio/python/use-python-api-bindings.md)
- [Use the Edge Impulse Python SDK to upload and download data](https://docs.edgeimpulse.com/tutorials/tools/sdks/studio/python/upload-download-data.md)
- [Use the Edge Impulse Python SDK to run the EON Tuner](https://docs.edgeimpulse.com/tutorials/tools/sdks/studio/python/run-eon-tuner.md)
- [Use the Edge Impulse Python SDK with Hugging Face](https://docs.edgeimpulse.com/tutorials/tools/sdks/studio/python/use-hugging-face.md)
- [Use the Edge Impulse Python SDK with SageMaker Studio](https://docs.edgeimpulse.com/tutorials/tools/sdks/studio/python/use-sagemaker-studio.md)
- [Use the Edge Impulse Python SDK with TensorFlow and Keras](https://docs.edgeimpulse.com/tutorials/tools/sdks/studio/python/use-tf-keras.md)
- [Use the Edge Impulse Python SDK with Weights & Biases](https://docs.edgeimpulse.com/tutorials/tools/sdks/studio/python/use-wandb.md)
- [Arduino Machine Learning Tools](https://docs.edgeimpulse.com/tutorials/integrations/arduino-ml-tools.md)
- [AWS IoT Greengrass](https://docs.edgeimpulse.com/tutorials/integrations/aws-greengrass.md)
- [Deploy PyTorch models with ExecuTorch](https://docs.edgeimpulse.com/tutorials/integrations/executorch.md): Train PyTorch models in Edge Impulse and export ExecuTorch programs using custom learning and deployment blocks
- [AngleForge: consistent image angles with Qwen Image Edit](https://docs.edgeimpulse.com/tutorials/integrations/huggingface-angleforge-synthetic-data.md)
- [NVIDIA Omniverse](https://docs.edgeimpulse.com/tutorials/integrations/nvidia-omniverse.md)
- [Scailable](https://docs.edgeimpulse.com/tutorials/integrations/scailable.md)
- [syntheticAIdata Vision Datasets](https://docs.edgeimpulse.com/tutorials/integrations/syntheticaIdata-vision-datasets.md)
- [Weights & Biases](https://docs.edgeimpulse.com/tutorials/integrations/weights-and-biases.md)
- [ROS 2 (edgeimpulse_ros)](https://docs.edgeimpulse.com/tutorials/integrations/ros2.md)

## Optional

- [Documentation index (all sections)](https://docs.edgeimpulse.com/llms.txt): Root llms.txt router linking every documentation section.