Dhruv Sheth / cloud-classification-spresense Public

Target: Sony Spresense (Cortex-M4F 156MHz) Clone this project

Configure your deployment

You can deploy your impulse to any device. This makes the model run without an internet connection, minimizes latency, and runs with minimal power consumption. Read more.

Deployment target

C++ library

A portable C++ library with no external dependencies, which can be compiled with any modern C++ compiler.

No deployment options available for this project.

Inference engine

EON™ Compiler

Same accuracy, 17% less RAM, 27% less ROM.

TensorFlow Lite

Model optimizations and performance

Model optimizations can increase on-device performance but may reduce accuracy. Performance estimate for Sony Spresense (Cortex-M4F 156MHz).

Quantized (int8)


Latency
Ram
Flash
Accuracy

Image	Neural Network (Keras)	Total
-	753 ms.	753 ms.
-	60.2K	60.2K
-	109.3K	-
		93.47%

Unoptimized (float32)


Latency
Ram
Flash
Accuracy

Image	Neural Network (Keras)	Total
-	3,543 ms.	3,543 ms.
-	164.5K	164.5K
-	412.2K	-
		93.47%

Clone this project to deploy this impulse.

Latest build

No deployments yet

Run this model

Scan QR code or launch in browser to test your prototype

Launch in browser

Build output

Cancel

Click 'Build' to begin

Model testing output

Cancel

Built WebAssembly library

Learn how to integrate this library

Built C++ library

Learn how to integrate this library

Built C++ library (Linux)

Learn how to integrate this library

Built Android library (C++)

Learn how to integrate this library

Built STM32Cube.MX CMSIS-PACK

Learn how to integrate this library

Built Arduino library

Add this library through the Arduino IDE via:

Sketch > Include Library > Add .ZIP Library...

Examples can then be found under:

File > Examples > cloud-classification-spresense_inferencing

Built Zephyr module

Add this module to your application updating the CMakeLists.txt file adding:

list(APPEND ZEPHYR_EXTRA_MODULES ${CMAKE_CURRENT_SOURCE_DIR}/model)

Adapting the path to the folder where you have the model in your application.

To add the Edge Impulse SDK update the manifest file in use adding the entry for edge-impulse-sdk-zephyr as specified in the west.yml in the downloaded zip.

Learn how to integrate this model as module into your Zephyr application

Built Simplicity Studio Component

Built Open CMSIS package

Import the model and the Edge Impulse SDK packages to your project.

Play video to see how to import the package.

Built ST IoT Discovery Kit firmware

Drag the .bin file to the DIS_L4IOT drive to flash the binary.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built SiLabs Thunderboard Sense 2 firmware

Drag the .bin file to the TB004 drive to flash the binary.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built Renesas CK-RA6M5 firmware

Flash the board according to the instructions in the archive.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built Renesas EK-RA8D1 firmware

Flash the board according to the instructions in the archive.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built SiLabs xG24 firmware

Follow the instruction to flash the board.

Play video to see how to flash the binary.

Try live inference preview on your device, from your terminal or command prompt run: edge-impulse-run-impulse --debug

Built Infineon PSoC63 Pioneer Kit firmware

Install CyProgrammer and flash the HEX file from downloaded archive.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built Infineon PSoC62 Pioneer Kit firmware

Install CyProgrammer and flash the HEX file from downloaded archive.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built nRF52840 DK firmware

Drag the .bin file to the JLINK drive to flash the binary.

No JLINK drive? See instructions on updating the bootloader.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built nRF5340 DK firmware

Drag the .bin file to the JLINK drive to flash the binary.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built nRF9160 DK firmware

Drag the firmware.bin file to the JLINK drive to flash the binary.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built Thingy:53 firmware

Put the device in the bootloader mode and open nRF Connect for Desktop Programmer application and drag the zip file.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built Thingy:91 firmware

Follow the steps in INSTRUCTIONS.txt to flash the binary.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built nRF7002 DK firmware

Drag the .bin file to the JLINK drive to flash the binary.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built nRF9161 DK firmware

Drag the firmware.bin file to the JLINK drive to flash the binary.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built nRF9151 DK firmware

Drag the firmware.bin file to the JLINK drive to flash the binary.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built Arduino Nano 33 BLE Sense firmware

Click on the script for your operating system to flash the binary.

Play video to see how to flash the binary.

Try live inference preview on your device, from your terminal or command prompt run: edge-impulse-run-impulse --debug

Built Arduino Portenta H7 firmware

Click on the script for your operating system to flash the binary.

Play video to see how to flash the binary.

Try live inference preview on your device, from your terminal or command prompt run: edge-impulse-run-impulse --debug

Built Arduino Nicla Vision firmware

Click on the script for your operating system to flash the binary.

Play video to see how to flash the binary.

Try live inference preview on your device, from your terminal or command prompt run: edge-impulse-run-impulse --debug

Built BrickML firmware

Flash the board according to the instructions in the archive.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built BrickML SoM firmware

Flash the board according to the instructions in the archive.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built ESP-EYE (ESP32) firmware

Click on the script for your operating system to flash the binary.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built Raspberry Pi RP2040 firmware

Connect the Raspberry Pi Pico to your computer using a micro-USB cable, making sure that you hold down the BOOTSEL button as you do so, to force it into USB Mass Storage Mode. Drag the firmware file (*.uf2) from archive to newly appeared USB Mass Storage device.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built Raspberry Pi Pico 2 (RP2350) firmware

Connect the Raspberry Pi Pico 2 to your computer using a micro-USB cable, making sure that you hold down the BOOTSEL button as you do so, to force it into USB Mass Storage Mode. Drag the firmware file (*.uf2) from archive to newly appeared USB Mass Storage device.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built Raspberry Pi Pico 2 WiFi (RP2350) firmware

Connect the Raspberry Pi Pico 2W to your computer using a micro-USB cable, making sure that you hold down the BOOTSEL button as you do so, to force it into USB Mass Storage Mode. Drag the firmware file (*.uf2) from archive to newly appeared USB Mass Storage device.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built Himax WE-I firmware

Click on the script for your operating system to flash the binary.

Play video to see how to flash the binary.

Try live inference preview on your device, from your terminal or command prompt run: edge-impulse-run-impulse --debug

Built Grove AI Vision module firmware

Switch your module into bootloader mode and drop the firmware.uf2 file onto the Grove AI disk.

Try live inference preview on your device, from your terminal or command prompt run: edge-impulse-run-impulse --debug

Built Seeed SenseCAP A1100 firmware

Switch your module into bootloader mode and drop the firmware.uf2 file onto the VISIONAI disk.

Try live inference preview on your device, from your terminal or command prompt run: edge-impulse-run-impulse --debug

Built Spresense firmware

Click on the script for your operating system to flash the binary.

Play video to see how to flash the binary.

Try live inference preview on your device, from your terminal or command prompt run: edge-impulse-run-impulse --debug

Built Spresense + Commonsense firmware

Click on the script for your operating system to flash the binary.

Play video to see how to flash the binary.

Try live inference preview on your device, from your terminal or command prompt run: edge-impulse-run-impulse --debug

Built TI LAUNCHXL-CC1352P firmware

Click on the script for your operating system to flash the binary.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built Synaptics KA10000 firmware

Click on the script for your operating system to flash the binary.

Play video to see how to flash the binary.

Then, from your terminal or command prompt run: edge-impulse-run-impulse

Built OpenMV library

Learn how to integrate this library

Built TensorRT library

Learn how to integrate this library

Built Tensai Flow library

Learn how to integrate this library

Built DRP-AI library

Learn how to integrate this library

Built DRP-AI TVM library

Learn how to integrate this library

Built DRP-AI TVM i8 library

Learn how to integrate this library

Built TIDL-RT (TDA4VM) library

Learn how to integrate this library

Built Memryx Deploy Program

Learn how to integrate this library

Built TIDL-RT (AM62A) library

Learn how to integrate this library

Built Linux (AARCH64 AM62A) model

Learn how to use this model

Built TIDL-RT (AM68A) library

Learn how to integrate this library

Built Linux (AARCH64 AM68A) model

Learn how to use this model

Built NVIDIA Jetson (JetPack 4.6.x) model

Learn how to use this model

Built NVIDIA Jetson Orin (JetPack 5.1.x) model

Learn how to use this model

Built NVIDIA Jetson Orin (JetPack 6.0) model

Learn how to use this model

Built Advantech ICAM-540 model

Learn how to use this model

Built custom block

Learn how to build custom deployment blocks

Built custom block

Learn how to use this target

Built macOS (x86) model

To use this model you'll need macOS to trust this model:

Open a terminal window and navigate to the folder where you downloaded this model.
Mark the model as executable: chmod +x path-to-model.eim
Remove the quarantine flag: xattr -d com.apple.quarantine ./path-to-model.eim
You can now use this model with the Node.js, Python, Go or C++ SDKs 🎉

Learn how to use this model

Built macOS (arm64) model

To use this model you'll need macOS to trust this model:

Open a terminal window and navigate to the folder where you downloaded this model.
Mark the model as executable: chmod +x path-to-model.eim
Remove the quarantine flag: xattr -d com.apple.quarantine ./path-to-model.eim
You can now use this model with the Node.js, Python, Go or C++ SDKs 🎉

Learn how to use this model