FiftyOne Tutorials#
Each tutorial below is a curated demonstration of how FiftyOne can help refine your datasets and turn your good models into great models.

Leverage the power of DINOv3 embeddings for visual search, similarity analysis, and foreground segmentation in FiftyOne. Learn to compute embeddings, visualize them, and build classifiers using this state-of-the-art vision model.

Translate your pandas knowledge to FiftyOne. This tutorial gives a side-by-side comparison of performing common operations in pandas and FiftyOne.

Aggregate statistics aren't sufficient for object detection. This tutorial shows how to use FiftyOne to perform powerful evaluation workflows on your detector.

Evaluation made easy. This tutorial walks through an end-to-end example of fine-tuning a classifier and understanding its failure modes using FiftyOne.

Visualize your data in new ways. This tutorial shows how to use FiftyOne's powerful embeddings visualization capabilities to improve your image datasets.

So you've loaded and explored your data in FiftyOne... but now what? See how to send it off to CVAT for annotation in just one line of code.

Unlock the power of the Labelbox platform. See how you can get your FiftyOne datasets annotated with just one line of code.

Put your FiftyOne datasets to work and learn how to train and evaluate Detectron2 models directly on your data.

Expand your data lake and evaluate your object detection models with Google's Open Images dataset and evaluation protocol, all natively within FiftyOne.

Your models need diverse data. This tutorial shows how FiftyOne can remove near-duplicate images and recommend unique samples for model training.

Better models start with better data. This tutorial shows how FiftyOne can automatically find label mistakes in your classification datasets.

How good are your ground truth objects? Use the FiftyOne Brain's mistakenness feature to find annotation errors in your object detections.

Easily pre-annotate your FiftyOne datasets using approximate nearest neighbors search on embeddings with Qdrant.

Visualize and evaluate YOLOv8 model predictions before fine-tuning for your custom use case.

Lidar is expensive. This tutorial shows how FiftyOne can help you construct high quality 3D point cloud datasets using Point-E point cloud models.

Metrics for monocular depth estimation can be deceiving. Run MDE models on your data and visualize their predictions with FiftyOne.

Compare and contrast dimensionality reduction techniques for visualizing your data in FiftyOne.

Run and evaluate zero-shot image classification models with OpenCLIP, Hugging Face Transformers, and FiftyOne.

Learn how to apply and test out different augmentations on your datasets using FiftyOne and Albumentations.

Use embeddings to cluster images in your dataset and visualize the results in FiftyOne.

Detect small objects in your images with Slicing-Aided Hyper-Inference (SAHI) and FiftyOne.

Detect anomalies in your images with Anomalib and FiftyOne.
Note
Check out the fiftyone-examples repository for more examples of using FiftyOne!