How to use Weights & Biases: snippets, scripts, interactive notebooks, and videos.
Explore what's possible in the W&B app with the example projects below. Looking for code examples instead? Head to our GitHub repo.

Examples by application

A list of examples by applications to guide you how W&B is solving common problems.

Autonomous vehicles

Point Clouds
Bounding Boxes
3D from Video
Deep Drive
See LIDAR point cloud visualizations from the Lyft dataset. These are interactive and have bounding box annotations. Click the full screen button in the corner of an image, then zoom, rotate, and pan around the 3D scene.
This report describes how to log and interact with image masks for semantic segmentation.
Examples & walkthrough of how to annotate driving scenes for object detection
Infer depth perception from dashboard camera videos. This example contains lots of sample images from road scenes, and shows how to use the media panel for visualizing data in W&B.
This report compares models for detecting humans in scenes from roads, with lots of charts, images, and notes. The project page workspace is also available.


2D Molecules
3D Molecules
X Rays
This report explores training models to predict how soluble a molecule is in water based on its chemical formula. This example features scikit learn and sweeps.
This report explores molecular binding and shows interactive 3D protein visualizations.
This report explores chest x-ray data and strategies for handling real world long-tailed data.


Credit Scorecards
Track experiments, generate credit scorecard for loan defaults and run a hyperparameter sweep to find the best hyperparameters. Click here to view and interact with a live W&B Dashboard built with this notebook.

Examples by technique

Computer Vision

Images of species
PDF scans
This report explores per-class accuracy on an image dataset of plants and animals.
Parse TV ad receipts for political campaigns to extract amount paid, organization, dates of ad, and receipt id from 100s of different receipt formats.

Distributed Training

Data Parallel
This report visualizes experiments with Keras data parallel across up to 8 GPUs. Features include run sets and grouping, and notes.
Last modified 17d ago