Computer Vision

High-performance object detection library.

World's most widely used computer vision library.

State-of-the-art real-time object detection.

Industry-leading data annotation platform for computer vision. Interactive video and image annotation tool used by tens of thousands of teams for machine learning at any scale.

Promptable image and video segmentation model with released checkpoints and training code.

QGIS plugin for point-and-click SAM segmentation of buildings, trees and any object in satellite and drone imagery, with a free CPU-only local mode.

Differentiable computer vision library.

Reusable computer-vision utilities for detection, tracking, and segmentation pipelines in Python.

PyTorch audio processing library. Comprehensive toolkit for audio I/O, transformations, and deep learning with support for speech recognition, TTS, and audio classification. BSD-2-Clause licensed.

Cross-platform multimodal pipelines.

Deepfake video detection with eight EfficientNet-B4 models trained on FaceForensics++, with Grad-CAM heatmaps and attention measured across eight facial regions. Code MIT licensed, model weights CC BY-NC 4.0.