Fall_Detection_using_Transformer - Deployment

Edge Impulse Experts / Fall_Detection_using_Transformer Public

Target: Arduino Portenta H7 (Cortex-M7 480MHz) 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.

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/g7a8t7v6/inference-container-jetson:32b6381a5e18511d5a39806344dc90400d12d486

Arguments:

--api-key ei_3d5f812072c79069e2d3669e356eaee28373b15b1310554187c3975dcb19a7a3 --run-http-server 1337

Ports to expose:

1337

For example, in a one-liner locally:

docker run --rm -it --runtime=nvidia --gpus all \
    -p 1337:1337 \
    public.ecr.aws/g7a8t7v6/inference-container-jetson:32b6381a5e18511d5a39806344dc90400d12d486 \
        --api-key ei_3d5f812072c79069e2d3669e356eaee28373b15b1310554187c3975dcb19a7a3 \
        --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:

Container:

public.ecr.aws/g7a8t7v6/inference-container-jetson-orin:056d0e5e0a8c7e04fbaa8a9cccd92e79dfaa7839

Arguments:

--api-key ei_3d5f812072c79069e2d3669e356eaee28373b15b1310554187c3975dcb19a7a3 --run-http-server 1337

Ports to expose:

1337

For example, in a one-liner locally:

docker run --rm -it --runtime=nvidia --gpus all \
    -p 1337:1337 \
    public.ecr.aws/g7a8t7v6/inference-container-jetson-orin:056d0e5e0a8c7e04fbaa8a9cccd92e79dfaa7839 \
        --api-key ei_3d5f812072c79069e2d3669e356eaee28373b15b1310554187c3975dcb19a7a3 \
        --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:

Container:

public.ecr.aws/g7a8t7v6/inference-container-jetson-orin-6-0:74e21361f651747ba5fe177bee84267d1c2bd3fc

Arguments:

--api-key ei_3d5f812072c79069e2d3669e356eaee28373b15b1310554187c3975dcb19a7a3 --run-http-server 1337

Ports to expose:

1337

For example, in a one-liner locally:

docker run --rm -it --runtime=nvidia --gpus all \
    -p 1337:1337 \
    public.ecr.aws/g7a8t7v6/inference-container-jetson-orin-6-0:74e21361f651747ba5fe177bee84267d1c2bd3fc \
        --api-key ei_3d5f812072c79069e2d3669e356eaee28373b15b1310554187c3975dcb19a7a3 \
        --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.

Quantized (int8)


Latency
Ram
Flash
Accuracy

Raw data	Classifier	Total
-	132 ms.	132 ms.
2.3K	-	2.3K
-	30.6K	-
		-

Unoptimized (float32)


Latency
Ram
Flash
Accuracy

Raw data	Classifier	Total
-	466 ms.	466 ms.
2.3K	-	2.3K
-	-	-
		97.32%

To compare model accuracy, clone this project and run model testing.

Estimate for Arduino Portenta H7 (Cortex-M7 480MHz).

Clone this project to deploy this impulse.

Run this model

Scan QR code or launch in browser to test your prototype

Launch in browser

Configure your deployment

Deploy to any Linux-based development board

Run your model as a Docker container

Run your model as a Docker container

Run your model as a Docker container

Run your model as a Docker container

Model Optimizations

Quantized (int8)

Unoptimized (float32)

Latest build

Run this model

Build output

Model testing output

Configure your deployment

Default Deployment

C++ library

Deploy to any Linux-based development board

Run your model as a Docker container

Run your model as a Docker container

Run your model as a Docker container

Run your model as a Docker container

Model Optimizations

EON™ Compiler

EON™ Compiler

TensorFlow Lite

Quantized (int8)

Unoptimized (float32)

Latest build

Run this model

Build output

Model testing output