Weights & Biases

Edge Impulse has partnered with Weights & Biases to help users build better models faster with experiment tracking, dataset versioning, and model management.

Weights & Biases makes it easy to track your experiments, manage & version your data, and collaborate with your team so you can focus on building the best models. Use W&B's lightweight, interoperable tools to quickly track experiments, version and iterate on datasets, evaluate model performance, reproduce models, visualize results and spot regressions, and share findings with colleagues. Set up W&B in 5 minutes, then quickly iterate on your machine learning pipeline with the confidence that your datasets and models are tracked and versioned in a reliable system of record.

This tutorial describes how to integrate your Edge Impulse model with Weights & Biases and get started with tracking metrics within Weights & Biases.

Getting started with Weights & Biases

Check out Weights & Biases's documentation for information on getting started as a first-time user with the platform.

Preliminary steps

• Install Edge Impulse CLI

• Create a Weights & Biases account

• Create an Edge Impulse account

Now continue with the tutorial provided by Weights & Biases.

Next steps: building a machine learning model

With everything set up you can now build your first machine learning model with these tutorials:

• Responding to your voice

• Recognize sounds from audio

• Adding sight to your sensors

• Detect objects with bounding boxes

• Detect objects with centroids (FOMO)

Looking to connect different sensors? The Data forwarder lets you easily send data from any sensor into Edge Impulse.

Using Weights & Biases

Follow the Weights & Biases tutorial on running and training Sweeps. This tutorial also includes information on the W&B Edge Impulse custom block integration, training sweeps, validation metrics, and training metrics of your dataset.