Lists (1)
Starred repositories
[NeurIPS 2025] Pixel-Perfect Depth
Ranger deep learning optimizer rewrite to use newest components
Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase
[ICML 2025] Implementation of Spatial Reasoning with Denoising Models
A feature-rich command-line audio/video downloader
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model
Renderer for 3D Tiles in Javascript using three.js
Official inference framework for 1-bit LLMs
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
Advanced RANSAC (DEGENSAC) with bells and whistles for H and F estimation
[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.
Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.
An orchestration platform for the development, production, and observation of data assets.
Render any git repo into a single static HTML page for humans or LLMs
Reference PyTorch implementation and models for DINOv3
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Dataset of Linus Torvalds' rants classified by negativity using sentiment analysis
SauravMaheshkar / samv2
Forked from facebookresearch/sam2CPU compatible fork of the official SAMv2 implementation aimed at more accessible and documented tutorials
Hierarchical Reasoning Model Official Release
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data