Which machine learning models can I run?

You can apply any model from the FiftyOne Model Zoo, such as YOLOv8, Faster R-CNN, ResNet, MobileNet, CLIP, and Segment Anything (SAM).

How does the skill handle missing model dependencies?

If a model requires extra packages (like ultralytics or torch), the skill will identify the missing dependency and provide the exact install command to fix it.

What label formats can I import with this skill?

The skill supports common formats including COCO, YOLOv4/v5, VOC, KITTI, CVAT, and standard image/video classification directory trees.

Does this skill require the FiftyOne App?

Yes, the skill is designed to work with the FiftyOne MCP server and includes commands to launch and close the FiftyOne App for visual data exploration.

Can it handle 3D data and videos?

Absolutely. It supports various media types including images, videos (.mp4, .mkv, etc.), point clouds (.pcd), and 3D files (.fo3d).

FiftyOne Dataset Inference

Name: FiftyOne Dataset Inference
Author: AdonaiVera

byAdonaiVera

Ciencia de Datos y ML

Automates the creation of FiftyOne datasets from local media files and executes machine learning model inference pipelines.

Acerca de

The FiftyOne Dataset Inference skill streamlines the transition from raw local media to structured machine learning datasets. It allows users to automatically scan directories, import images, videos, and point clouds, and handle labels in formats like COCO, YOLO, and VOC. Beyond data management, it provides a guided workflow for running model inference from the FiftyOne Model Zoo—including popular architectures like YOLOv8 and ResNet—enabling rapid visualization and comparison of ground truth labels against model predictions within the FiftyOne App.

Características Principales

Support for COCO, YOLO, VOC, KITTI, and CVAT dataset imports
One-click inference for detection, classification, and segmentation models
Seamless integration with the FiftyOne Model Zoo and App visualization
End-to-end dataset management from creation to persistent storage
0 GitHub stars
Automated directory scanning for media and label format detection

Casos de Uso

Loading raw image directories to run object detection and generate initial predictions
Importing pre-labeled COCO or YOLO datasets to validate annotations and model performance
Converting folder-based classification trees into searchable, queryable FiftyOne datasets

Acerca de

Características Principales

Support for COCO, YOLO, VOC, KITTI, and CVAT dataset imports
One-click inference for detection, classification, and segmentation models
Seamless integration with the FiftyOne Model Zoo and App visualization
End-to-end dataset management from creation to persistent storage
0 GitHub stars
Automated directory scanning for media and label format detection

Casos de Uso

Loading raw image directories to run object detection and generate initial predictions
Importing pre-labeled COCO or YOLO datasets to validate annotations and model performance
Converting folder-based classification trees into searchable, queryable FiftyOne datasets