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)
See the
CLI documentation for more information and setup instructions.
Alternatively, you can download your model for
below.
Run your model as a Docker container
To run your model as a container with an HTTP interface, use:
Container:
public.ecr.aws/z9b3d4t5/inference-container:2c47193d290bd2fbbc5343de8d9a87b599f60332
Arguments:
--api-key ei_2994dcb172c1bb8ca37867ce0c9e6116a527816c4f6b21b967dd6e1cad217218 --run-http-server 1337 --impulse-id 2
For example, in a one-liner locally:
docker run --rm -it \
-p 1337:1337 \
public.ecr.aws/z9b3d4t5/inference-container:2c47193d290bd2fbbc5343de8d9a87b599f60332 \
--api-key ei_2994dcb172c1bb8ca37867ce0c9e6116a527816c4f6b21b967dd6e1cad217218 \
--run-http-server 1337 \
--impulse-id 2
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:
Container:
public.ecr.aws/z9b3d4t5/inference-container-jetson:44b632fb48202776b1560e000f20b9bf41c658e0
Arguments:
--api-key ei_2994dcb172c1bb8ca37867ce0c9e6116a527816c4f6b21b967dd6e1cad217218 --run-http-server 1337 --impulse-id 2
For example, in a one-liner locally:
docker run --rm -it --runtime=nvidia --gpus all \
-p 1337:1337 \
public.ecr.aws/z9b3d4t5/inference-container-jetson:44b632fb48202776b1560e000f20b9bf41c658e0 \
--api-key ei_2994dcb172c1bb8ca37867ce0c9e6116a527816c4f6b21b967dd6e1cad217218 \
--run-http-server 1337 \
--impulse-id 2
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:
Container:
public.ecr.aws/z9b3d4t5/inference-container-jetson-orin:1106e56ec1415e2fe1916242397652675e91b4f7
Arguments:
--api-key ei_2994dcb172c1bb8ca37867ce0c9e6116a527816c4f6b21b967dd6e1cad217218 --run-http-server 1337 --impulse-id 2
For example, in a one-liner locally:
docker run --rm -it --runtime=nvidia --gpus all \
-p 1337:1337 \
public.ecr.aws/z9b3d4t5/inference-container-jetson-orin:1106e56ec1415e2fe1916242397652675e91b4f7 \
--api-key ei_2994dcb172c1bb8ca37867ce0c9e6116a527816c4f6b21b967dd6e1cad217218 \
--run-http-server 1337 \
--impulse-id 2
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:
Container:
public.ecr.aws/z9b3d4t5/inference-container-jetson-orin-6-0:e37642601b1879da13cadda843bacb5aad376697
Arguments:
--api-key ei_2994dcb172c1bb8ca37867ce0c9e6116a527816c4f6b21b967dd6e1cad217218 --run-http-server 1337 --impulse-id 2
For example, in a one-liner locally:
docker run --rm -it --runtime=nvidia --gpus all \
-p 1337:1337 \
public.ecr.aws/z9b3d4t5/inference-container-jetson-orin-6-0:e37642601b1879da13cadda843bacb5aad376697 \
--api-key ei_2994dcb172c1bb8ca37867ce0c9e6116a527816c4f6b21b967dd6e1cad217218 \
--run-http-server 1337 \
--impulse-id 2
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 Qualcomm Adreno 702 GPUs, use:
Container:
public.ecr.aws/z9b3d4t5/inference-container-qc-adreno-702:4d7979284677b6bdb557abe8948fa1395dc89a63
Arguments:
--api-key ei_2994dcb172c1bb8ca37867ce0c9e6116a527816c4f6b21b967dd6e1cad217218 --run-http-server 1337 --impulse-id 2
For example, in a one-liner locally:
docker run --rm -it --device /dev/dri \
-p 1337:1337 \
public.ecr.aws/z9b3d4t5/inference-container-qc-adreno-702:4d7979284677b6bdb557abe8948fa1395dc89a63 \
--api-key ei_2994dcb172c1bb8ca37867ce0c9e6116a527816c4f6b21b967dd6e1cad217218 \
--run-http-server 1337 \
--impulse-id 2
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.
