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)
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:9efe6696a7f1927ec359902bf5458960c10bc6ea
Arguments:
--api-key ei_a0afbbe53aa534aee0fd4275e4f8fdda8bb80cef2cd9cf08276c50c5a03d34e3 --run-http-server 1337
For example, in a one-liner locally:
docker run --rm -it \
-p 1337:1337 \
public.ecr.aws/z9b3d4t5/inference-container:9efe6696a7f1927ec359902bf5458960c10bc6ea \
--api-key ei_a0afbbe53aa534aee0fd4275e4f8fdda8bb80cef2cd9cf08276c50c5a03d34e3 \
--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's GPUs, use:
Container:
public.ecr.aws/z9b3d4t5/inference-container-jetson:a0e0085793dd7a95c332c8554424d32b9919a563
Arguments:
--api-key ei_a0afbbe53aa534aee0fd4275e4f8fdda8bb80cef2cd9cf08276c50c5a03d34e3 --run-http-server 1337
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:a0e0085793dd7a95c332c8554424d32b9919a563 \
--api-key ei_a0afbbe53aa534aee0fd4275e4f8fdda8bb80cef2cd9cf08276c50c5a03d34e3 \
--run-http-server 1337
This automatically builds and downloads the latest model with TensorRT support, 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, use:
Container:
public.ecr.aws/z9b3d4t5/inference-container-jetson-orin:d7eec0d01b91b7c88bd5ef84b1e13e8dc1fe9253
Arguments:
--api-key ei_a0afbbe53aa534aee0fd4275e4f8fdda8bb80cef2cd9cf08276c50c5a03d34e3 --run-http-server 1337
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:d7eec0d01b91b7c88bd5ef84b1e13e8dc1fe9253 \
--api-key ei_a0afbbe53aa534aee0fd4275e4f8fdda8bb80cef2cd9cf08276c50c5a03d34e3 \
--run-http-server 1337
This automatically builds and downloads the latest model with TensorRT support, 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.