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.
Search deployment options
Default Deployment
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.
Deploy to any Linux-based development board
Edge Impulse for Linux lets you run your models on any Linux-based development board,
with SDKs for Node.js, Python, Go and C++ to integrate your models quickly into
your application.
Install the Edge Impulse Linux CLI
Run edge-impulse-linux-runner (run with --clean to switch projects)
This automatically builds and downloads the latest model (incl. hardware optimizations), and runs an HTTP endpoint at http://localhost:1337 with instructions.
Read the docs for information,
like bundling in your model inside the container and selecting extra hardware optimizations.
Run your model as a Docker container
To run your model as a container with an HTTP interface on NVIDIA Jetson's GPUs (JetPack 4.6.x), use:
docker run --rm -it --runtime=nvidia --gpus all \
-p 1337:1337 \
public.ecr.aws/g7a8t7v6/inference-container-jetson:05926a492f8a440915266ea774513f4d7f7d69ad \
--api-key ei_419e15e00a5c1c41db291509cbe943e26c1b1c2b8bea7ee54d574285a403011e \
--run-http-server 1337
This automatically builds and downloads the latest model (incl. hardware optimizations), and runs an HTTP endpoint at http://localhost:1337 with instructions.
Read the docs for information,
like bundling in your model inside the container and selecting extra hardware optimizations.
Run your model as a Docker container
To run your model as a container with an HTTP interface on NVIDIA Jetson Orin's GPUs (JetPack 5.1.x), use:
docker run --rm -it --runtime=nvidia --gpus all \
-p 1337:1337 \
public.ecr.aws/g7a8t7v6/inference-container-jetson-orin:1324212e2a5b32e59e31f3b959c45757960640d5 \
--api-key ei_419e15e00a5c1c41db291509cbe943e26c1b1c2b8bea7ee54d574285a403011e \
--run-http-server 1337
This automatically builds and downloads the latest model (incl. hardware optimizations), and runs an HTTP endpoint at http://localhost:1337 with instructions.
Read the docs for information,
like bundling in your model inside the container and selecting extra hardware optimizations.
Run your model as a Docker container
To run your model as a container with an HTTP interface on NVIDIA Jetson Orin's GPUs (JetPack 6.0), use:
docker run --rm -it --runtime=nvidia --gpus all \
-p 1337:1337 \
public.ecr.aws/g7a8t7v6/inference-container-jetson-orin-6-0:bb88b238be0bfbefadf3a517000ba2b2c80e185a \
--api-key ei_419e15e00a5c1c41db291509cbe943e26c1b1c2b8bea7ee54d574285a403011e \
--run-http-server 1337
This automatically builds and downloads the latest model (incl. hardware optimizations), and runs an HTTP endpoint at http://localhost:1337 with instructions.
Read the docs for information,
like bundling in your model inside the container and selecting extra hardware optimizations.
Model Optimizations
Model optimizations can increase on-device performance but may reduce accuracy.
EON™ Compiler
Same accuracy, 16% less RAM, 32% less ROM.
TensorFlow Lite
Quantized (int8)
Latency
Ram
Flash
Accuracy
Audio (MFE)
Neural Network (Keras)
Total
43 ms.
6 ms.
49 ms.
10.6K
6.4K
10.6K
-
39.8K
-
85.96%
Unoptimized (float32)
Latency
Ram
Flash
Accuracy
Audio (MFE)
Neural Network (Keras)
Total
43 ms.
5 ms.
48 ms.
10.6K
6.6K
10.6K
-
52.6K
-
85.38%
Estimate for TI LAUNCHXL-CC1352P (Cortex-M4F 48MHz).
Clone this project to deploy this impulse.
Latest build
Fallback Build
Run this model
Scan QR code or launch in browser to test your prototype
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.
Then, from your terminal or command prompt run: edge-impulse-run-impulse
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.
Then, from your terminal or command prompt run: edge-impulse-run-impulse
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.
Then, from your terminal or command prompt run: edge-impulse-run-impulse
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 RP2040 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 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.
Then, from your terminal or command prompt run: edge-impulse-run-impulse
Built Grove AI Vision module firmware
Switch your module into bootloader mode and drop the firmware.uf2 file onto the Grove AI disk.
Then, from your terminal or command prompt run: edge-impulse-run-impulse
Built Seeed SenseCAP A1100 firmware
Switch your module into bootloader mode and drop the firmware.uf2 file onto the VISIONAI disk.
Then, from your terminal or command prompt run: edge-impulse-run-impulse
Built Spresense 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 Spresense + Commonsense 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 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
We're always looking for ways to improve Edge Impulse. If you have any feedback, please let us know!
This field is required
This field is required
Sign up to clone this project
You'll need a free Edge Impulse
account to clone this project.
Create an account to add your own data,
modify models, and join the largest community of
embedded machine learning developers!
Configure your target device and application budget
Target device
Define your target device requirements to inform model optimizations and performance calculations.
No device yet? Use the default settings which you can change at any time.
| MHz
Max
Application budget
Specify the available RAM and ROM for the model's operation, along with the maximum allowed latency
for your specific application. Not sure yet? Start with the defaults and modify them later on.
| KB
Max
| KB
Max
| ms
Max
Choose your pricing
YEARLY
$400
/month
billed annually
SAVE 15%
MONTHLY
$475
/month
billed monthly
Additional usage
Professional Plan includes 1,000 compute minutes per month. Additional usage will be charged at $0.10 per minute, billed monthly.
