A playbook for systematically maximizing the performance of deep learning models.

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

A fast MoE impl for PyTorch

PyTorch code and models for the DINOv2 self-supervised learning method.

Deep and online learning with spiking neural networks in Python

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

The open-source tool for building high-quality datasets and computer vision models

Effortless data labeling with AI support from Segment Anything and other awesome models.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

An open source implementation of CLIP.

One Research Framework To Rule Them All

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Visual Concept Connectome

Refine high-quality datasets and visual AI models

📚 Jupyter notebook tutorials for OpenVINO™

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

Official Toolkit for The RoboDrive Challenge

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

Automatically find issues in image datasets and practice data-centric computer vision.

A Region-and-Trajectory Traffic Flow Estimation