LogoLogo
HomeAPI & SDKsProjectsForumStudio
  • Getting started
    • For beginners
    • For ML practitioners
    • For embedded engineers
  • Frequently asked questions (FAQ)
  • Tutorials
    • End-to-end tutorials
      • Computer vision
        • Image classification
        • Object detection
          • Object detection with bounding boxes
          • Detect objects with centroid (FOMO)
        • Visual anomaly detection
        • Visual regression
      • Audio
        • Sound recognition
        • Keyword spotting
      • Time-series
        • Motion recognition + anomaly detection
        • Regression + anomaly detection
        • HR/HRV
        • Environmental (Sensor fusion)
    • Data
      • Data ingestion
        • Collecting image data from the Studio
        • Collecting image data with your mobile phone
        • Collecting image data with the OpenMV Cam H7 Plus
        • Using the Edge Impulse Python SDK to upload and download data
        • Trigger connected board data sampling
        • Ingest multi-labeled data using the API
      • Synthetic data
        • Generate audio datasets using Eleven Labs
        • Generate image datasets using Dall-E
        • Generate keyword spotting datasets using Google TTS
        • Generate physics simulation datasets using PyBullet
        • Generate timeseries data with MATLAB
      • Labeling
        • Label audio data using your existing models
        • Label image data using GPT-4o
      • Edge Impulse Datasets
    • Feature extraction
      • Building custom processing blocks
      • Sensor fusion using embeddings
    • Machine learning
      • Classification with multiple 2D input features
      • Visualize neural networks decisions with Grad-CAM
      • Sensor fusion using embeddings
      • FOMO self-attention
    • Inferencing & post-processing
      • Count objects using FOMO
      • Continuous audio sampling
      • Multi-impulse (C++)
      • Multi-impulse (Python)
    • Lifecycle management
      • CI/CD with GitHub Actions
      • Data aquisition from S3 object store - Golioth on AI
      • OTA model updates
        • with Arduino IDE (for ESP32)
        • with Arduino IoT Cloud
        • with Blues Wireless
        • with Docker on Allxon
        • with Docker on Balena
        • with Docker on NVIDIA Jetson
        • with Espressif IDF
        • with Nordic Thingy53 and the Edge Impulse app
        • with Particle Workbench
        • with Zephyr on Golioth
    • API examples
      • Customize the EON Tuner
      • Ingest multi-labeled data using the API
      • Python API bindings example
      • Running jobs using the API
      • Trigger connected board data sampling
    • Python SDK examples
      • Using the Edge Impulse Python SDK to run EON Tuner
      • Using the Edge Impulse Python SDK to upload and download data
      • Using the Edge Impulse Python SDK with Hugging Face
      • Using the Edge Impulse Python SDK with SageMaker Studio
      • Using the Edge Impulse Python SDK with TensorFlow and Keras
      • Using the Edge Impulse Python SDK with Weights & Biases
    • Expert network projects
  • Edge Impulse Studio
    • Organization hub
      • Users
      • Data campaigns
      • Data
        • Cloud data storage
      • Data pipelines
      • Data transformation
        • Transformation blocks
      • Upload portals
      • Custom blocks
        • Custom AI labeling blocks
        • Custom deployment blocks
        • Custom learning blocks
        • Custom processing blocks
        • Custom synthetic data blocks
        • Custom transformation blocks
      • Health reference design
        • Synchronizing clinical data with a bucket
        • Validating clinical data
        • Querying clinical data
        • Transforming clinical data
    • Project dashboard
      • Select AI hardware
    • Devices
    • Data acquisition
      • Uploader
      • Data explorer
      • Data sources
      • Synthetic data
      • Labeling queue
      • AI labeling
      • CSV Wizard (time-series)
      • Multi-label (time-series)
      • Tabular data (pre-processed & non-time-series)
      • Metadata
      • Auto-labeler | deprecated
    • Impulses
    • EON Tuner
      • Search space
    • Processing blocks
      • Audio MFCC
      • Audio MFE
      • Audio Syntiant
      • Flatten
      • HR/HRV features
      • Image
      • IMU Syntiant
      • Raw data
      • Spectral features
      • Spectrogram
      • Custom processing blocks
      • Feature explorer
    • Learning blocks
      • Anomaly detection (GMM)
      • Anomaly detection (K-means)
      • Classification
      • Classical ML
      • Object detection
        • MobileNetV2 SSD FPN
        • FOMO: Object detection for constrained devices
      • Object tracking
      • Regression
      • Transfer learning (images)
      • Transfer learning (keyword spotting)
      • Visual anomaly detection (FOMO-AD)
      • Custom learning blocks
      • Expert mode
      • NVIDIA TAO | deprecated
    • Retrain model
    • Live classification
    • Model testing
    • Performance calibration
    • Deployment
      • EON Compiler
      • Custom deployment blocks
    • Versioning
    • Bring your own model (BYOM)
    • File specifications
      • deployment-metadata.json
      • ei-metadata.json
      • ids.json
      • parameters.json
      • sample_id_details.json
      • train_input.json
  • Tools
    • API and SDK references
    • Edge Impulse CLI
      • Installation
      • Serial daemon
      • Uploader
      • Data forwarder
      • Impulse runner
      • Blocks
      • Himax flash tool
    • Edge Impulse for Linux
      • Linux Node.js SDK
      • Linux Go SDK
      • Linux C++ SDK
      • Linux Python SDK
      • Flex delegates
      • Rust Library
    • Rust Library
    • Edge Impulse Python SDK
  • Run inference
    • C++ library
      • As a generic C++ library
      • On Android
      • On your desktop computer
      • On your Alif Ensemble Series Device
      • On your Espressif ESP-EYE (ESP32) development board
      • On your Himax WE-I Plus
      • On your Raspberry Pi Pico (RP2040) development board
      • On your SiLabs Thunderboard Sense 2
      • On your Spresense by Sony development board
      • On your Syntiant TinyML Board
      • On your TI LaunchPad using GCC and the SimpleLink SDK
      • On your Zephyr-based Nordic Semiconductor development board
    • Arm Keil MDK CMSIS-PACK
    • Arduino library
      • Arduino IDE 1.18
    • Cube.MX CMSIS-PACK
    • Docker container
    • DRP-AI library
      • DRP-AI on your Renesas development board
      • DRP-AI TVM i8 on Renesas RZ/V2H
    • IAR library
    • Linux EIM executable
    • OpenMV
    • Particle library
    • Qualcomm IM SDK GStreamer
    • WebAssembly
      • Through WebAssembly (Node.js)
      • Through WebAssembly (browser)
    • Edge Impulse firmwares
    • Hardware specific tutorials
      • Image classification - Sony Spresense
      • Audio event detection with Particle boards
      • Motion recognition - Particle - Photon 2 & Boron
      • Motion recognition - RASynBoard
      • Motion recognition - Syntiant
      • Object detection - SiLabs xG24 Dev Kit
      • Sound recognition - TI LaunchXL
      • Keyword spotting - TI LaunchXL
      • Keyword spotting - Syntiant - RC Commands
      • Running NVIDIA TAO models on the Renesas RA8D1
      • Two cameras, two models - running multiple object detection models on the RZ/V2L
  • Edge AI Hardware
    • Overview
    • Production-ready
      • Advantech ICAM-540
      • Seeed SenseCAP A1101
      • Industry reference design - BrickML
    • MCU
      • Ambiq Apollo4 family of SoCs
      • Ambiq Apollo510
      • Arducam Pico4ML TinyML Dev Kit
      • Arduino Nano 33 BLE Sense
      • Arduino Nicla Sense ME
      • Arduino Nicla Vision
      • Arduino Portenta H7
      • Blues Wireless Swan
      • Espressif ESP-EYE
      • Himax WE-I Plus
      • Infineon CY8CKIT-062-BLE Pioneer Kit
      • Infineon CY8CKIT-062S2 Pioneer Kit
      • Nordic Semi nRF52840 DK
      • Nordic Semi nRF5340 DK
      • Nordic Semi nRF9160 DK
      • Nordic Semi nRF9161 DK
      • Nordic Semi nRF9151 DK
      • Nordic Semi nRF7002 DK
      • Nordic Semi Thingy:53
      • Nordic Semi Thingy:91
      • Open MV Cam H7 Plus
      • Particle Photon 2
      • Particle Boron
      • RAKwireless WisBlock
      • Raspberry Pi RP2040
      • Renesas CK-RA6M5 Cloud Kit
      • Renesas EK-RA8D1
      • Seeed Wio Terminal
      • Seeed XIAO nRF52840 Sense
      • Seeed XIAO ESP32 S3 Sense
      • SiLabs Thunderboard Sense 2
      • Sony's Spresense
      • ST B-L475E-IOT01A
      • TI CC1352P Launchpad
    • MCU + AI accelerators
      • Alif Ensemble
      • Arduino Nicla Voice
      • Avnet RASynBoard
      • Seeed Grove - Vision AI Module
      • Seeed Grove Vision AI Module V2 (WiseEye2)
      • Himax WiseEye2 Module and ISM Devboard
      • SiLabs xG24 Dev Kit
      • STMicroelectronics STM32N6570-DK
      • Synaptics Katana EVK
      • Syntiant Tiny ML Board
    • CPU
      • macOS
      • Linux x86_64
      • Raspberry Pi 4
      • Raspberry Pi 5
      • Texas Instruments SK-AM62
      • Microchip SAMA7G54
      • Renesas RZ/G2L
    • CPU + AI accelerators
      • AVNET RZBoard V2L
      • BrainChip AKD1000
      • i.MX 8M Plus EVK
      • Digi ConnectCore 93 Development Kit
      • MemryX MX3
      • MistyWest MistySOM RZ/V2L
      • Qualcomm Dragonwing RB3 Gen 2 Dev Kit
      • Renesas RZ/V2L
      • Renesas RZ/V2H
      • IMDT RZ/V2H
      • Texas Instruments SK-TDA4VM
      • Texas Instruments SK-AM62A-LP
      • Texas Instruments SK-AM68A
      • Thundercomm Rubik Pi 3
    • GPU
      • Advantech ICAM-540
      • NVIDIA Jetson
      • Seeed reComputer Jetson
    • Mobile phone
    • Porting guide
  • Integrations
    • Arduino Machine Learning Tools
    • AWS IoT Greengrass
    • Embedded IDEs - Open-CMSIS
    • NVIDIA Omniverse
    • Scailable
    • Weights & Biases
  • Tips & Tricks
    • Combining impulses
    • Increasing model performance
    • Optimizing compute time
    • Inference performance metrics
  • Concepts
    • Glossary
    • Course: Edge AI Fundamentals
      • Introduction to edge AI
      • What is edge computing?
      • What is machine learning (ML)?
      • What is edge AI?
      • How to choose an edge AI device
      • Edge AI lifecycle
      • What is edge MLOps?
      • What is Edge Impulse?
      • Case study: Izoelektro smart grid monitoring
      • Test and certification
    • Data engineering
      • Audio feature extraction
      • Motion feature extraction
    • Machine learning
      • Data augmentation
      • Evaluation metrics
      • Neural networks
        • Layers
        • Activation functions
        • Loss functions
        • Optimizers
          • Learned optimizer (VeLO)
        • Epochs
    • What is embedded ML, anyway?
    • What is edge machine learning (edge ML)?
Powered by GitBook
On this page
  • Prerequisites
  • Adding the CMSIS-PACK
  • Configuring printf
  • Running the impulse
  • Seeing the output
  • Upgrading the CMSIS-PACK

Was this helpful?

Export as PDF
  1. Run inference

Cube.MX CMSIS-PACK

PreviousArduino IDE 1.18NextDocker container

Last updated 2 months ago

Was this helpful?

Impulses can be deployed as a CMSIS-PACK for STM32. This packages all your signal processing blocks, configuration and learning blocks up into a single package. You can include this package in any STM32 project with a single function call. The CMSIS-PACK uses to run any neural network, and CMSIS-DSP for all signal processing code - ensuring that models run as fast and efficiently as possible. In this tutorial, you'll export an impulse, import the impulse into STM32CubeMX, and then integrate it in your STM32 project to classify sensor data.

Using this CMSIS-PACK is currently only supported from C++ applications using STM32CubeIDE, on all Cortex-M MCUs.

Prerequisites

Make sure you followed the tutorial, and have a trained impulse. Also install the following software:

  • .

Make sure you have a C++ project configured that compiles for your target. You can convert an existing project to C++ by right-clicking on your project and selecting Convert to C++.

Enabling the CRC

The CRC needs to be enabled for your target. Open your .ioc file, then:

  1. Go to Pinout & Configuration.

  2. Select Computing > CRC.

  3. Enable the Activated checkbox.

Adding the CMSIS-PACK

Head over to your Edge Impulse project, and go to Deployment. From here you can create the full library which contains the impulse and all external required libraries. Select Cube.MX CMSIS-PACK and click Build to create the library.

To add the CMSIS-PACK library to your project, open your .ioc file, then:

  1. Go to Help > Manage embedded software packages.

  2. Select From Local ... and select the .pack file you just downloaded.

  3. Accept the license agreement, and the pack will be installed. The version number is automatically updated whenever you export the pack.

  1. Go back to your .ioc file, and go to Pinout & Configuration.

  2. Click Software packs > Select components.

  3. Select your project, expand the pack, and add a checkbox under 'Selection'.

  1. Click OK to close the window.

  2. Under Pinout & Configuration, select 'Additional software', and click on your project name. Place a checkbox next under 'Mode'.

  1. Click in the 'Project explorer' so the .ioc file loses focus.

  2. Click CTRL+S or CMD+S to save the workspace. This will regenerate the code. Afterward you should have a 'Middleware' folder in your project with your impulse and all required libraries.

  1. The code generator always generates a new main.c file, even for C++ projects. If you have both a main.c and a main.cpp file now, remove the main.c file.

Configuring printf

To log debug information the CMSIS-PACK uses the (weak defined) ei_printf function. You need to override this function in your main.cpp (if you only have a main.c rename it) to log to your UART port. E.g. this is how you set this up on the ST B-L475E-IOT01A. Under USER CODE BEGIN 0 add:

#include <stdarg.h>
#include "edge-impulse-sdk/classifier/ei_run_classifier.h"

void vprint(const char *fmt, va_list argp)
{
    char string[200];
    if(0 < vsprintf(string, fmt, argp)) // build string
    {
        HAL_UART_Transmit(&huart1, (uint8_t*)string, strlen(string), 0xffffff); // send message via UART
    }
}

void ei_printf(const char *format, ...) {
    va_list myargs;
    va_start(myargs, format);
    vprint(format, myargs);
    va_end(myargs);
}

Running the impulse

With the CMSIS-PACK included, and the UART set up, it's time to verify that the application works. Head back to the studio and click on Live classification. Then load a validation sample, and click on a row under 'Detailed result'.

To verify that the local application classifies the same, we need the raw features for this timestamp. To do so click on the 'Copy to clipboard' button next to 'Raw features'. This will copy the raw values from this validation file, before any signal processing or inferencing happened.

Open main.cpp (if you only have a main.c rename it) and add the following code under USER CODE BEGIN Includes (replace the features array with the data you just copied):

#include "edge-impulse-sdk/classifier/ei_run_classifier.h"

using namespace ei;

// paste the raw features here
static const float features[] = {
    -19.8800, -0.6900, 8.2300, -17.6600, -1.1300, 5.9700, ...
};

int get_feature_data(size_t offset, size_t length, float *out_ptr) {
    memcpy(out_ptr, features + offset, length * sizeof(float));
    return 0;
}

Then, under USER CODE BEGIN Init, add:

signal_t signal;
signal.total_length = sizeof(features) / sizeof(features[0]);
signal.get_data = &get_feature_data;

And, under USER CODE BEGIN WHILE, add:

while (1)
{
      ei_impulse_result_t result = { 0 };
      EI_IMPULSE_ERROR res = run_classifier(&signal, &result, true);
      ei_printf("run_classifier returned: %d\n", res);

      ei_printf("Predictions (DSP: %d ms., Classification: %d ms., Anomaly: %d ms.): \n",
          result.timing.dsp, result.timing.classification, result.timing.anomaly);

      // print the predictions
      ei_printf("[");
      for (size_t ix = 0; ix < EI_CLASSIFIER_LABEL_COUNT; ix++) {
    	  ei_printf_float(result.classification[ix].value);
  #if EI_CLASSIFIER_HAS_ANOMALY == 1
          ei_printf(", ");
  #else
          if (ix != EI_CLASSIFIER_LABEL_COUNT - 1) {
              ei_printf(", ");
          }
  #endif
      }
  #if EI_CLASSIFIER_HAS_ANOMALY == 1
      ei_printf_float(result.anomaly);
  #endif
      ei_printf("]\n\n\n");

    HAL_Delay(5000);
}

Then build and flash the application to your development board, via Project > Build All and Run > Debug.

Issues flashing through STM32CubeIDE?

If you have issues flashing through the IDE, right click on your project name, select Properties > Resources, and note the location of your project under 'Location'. In this folder you'll find a Debug and/or a Release folder with the built binaries (end with .bin). Many ST boards mount as a mass-storage device (e.g. the ST IoT Discovery Kit and virtually all NUCLEO boards), and you can also flash by dragging the binary file to this mass storage device.

Seeing the output

$ edge-impulse-run-impulse --raw

This will run the signal processing pipeline, and then classify the output:

Running neural network...
Predictions (time: 1 ms.):
idle:   0.015319
snake:  0.000444
updown: 0.006182
wave:   0.978056
Anomaly score (time: 1 ms.): 0.133557
run_classifier_returned: 0
[0.01532, 0.00044, 0.00618, 0.97806, 0.134]

Which matches the values we just saw in the studio. You now have your impulse running on your STM32 development board!

Upgrading the CMSIS-PACK

To upgrade your CMSIS-PACK do this:

  1. Download the new version of the CMSIS-PACK from Edge Impulse.

  2. Open your .ioc file, go to Pinout & Configuration > Additional software and select the CMSIS-PACK.

  3. De-select the checkbox under 'Mode'.

  1. Click in the 'Project explorer' so the .ioc file loses focus, and press CTRL+S or CMD+S. This will generate some new code.

  2. Remove the 'Middlewares/Third_party' folder.

  3. Go back to the .ioc file, select Help > Manage embedded software packages and add the new CMSIS-PACK.

  4. On the .ioc page, click Software Packs > Select Components.

  5. Find your CMSIS-PACK, and expand the line. If the 'Selection' checkbox is selected, uncheck this first.

  6. Change the Version dropdown to the new CMSIS-PACK version.

  7. Expand the item again, and enable the 'Selection' toggle. Press OK to exit the modal.

  1. Find the new CMSIS-PACK version under 'Additional software' in the item list, click on it (there are now probably multiple CMSIS-PACKs listed here for some reason), and set a new checkbox under 'Mode'.

  1. Click in the 'Project explorer' so the .ioc file loses focus, and press CTRL+S or CMD+S. This will generate some new code.

  2. Remove main.c as it will be generated again.

  3. You now have a new CMSIS-PACK version!

To see the output of the impulse, connect to the development board over a serial port on baud rate 115,200 and reset the board (e.g. by pressing the black button on the . You can do this with your favourite serial monitor or with the Edge Impulse CLI:

ST B-L475E-IOT01A
EON
Continuous motion recognition
STM32CubeIDE
Enabling the CRC on your target
Your impulse as a CMSIS-PACK available from STM32CubeIDE
Selecting the CMSIS-PACK.
Enabling the CMSIS-PACK
The CMSIS-PACK added to a project
Selecting the row with timestamp '320' under 'Detailed result'.
Copying the raw features.
Disable the old CMSIS-PACK
De-select, change version, then select again
Enable the new CMSIS-PACK