detectron2
Object Detector
A platform for object detection and segmentation tasks using machine learning algorithms
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
31k stars
389 watching
8k forks
Language: Python
last commit: 12 months ago
Linked from 6 awesome lists
Related projects:
| Repository | Description | Stars |
|---|---|---|
| | A PyTorch wrapper around Facebook AI Research's Detectron models for object detection and instance segmentation | 557 |
| | A software framework for video segmentation in images and videos using AI models | 13,054 |
| | A PyTorch implementation of a self-supervised learning method for learning robust visual features without supervision. | 9,425 |
| | This project provides code and tools for running inference with a visual segmentation model that can generate object masks from input prompts. | 48,092 |
| | A modular framework for building vision and language multimodal research projects using PyTorch. | 5,510 |
| | Automated tree crown delineation from aerial imagery using deep learning | 170 |
| | A visual object detection system that combines region proposals with neural network features to improve detection performance. | 2,381 |
| | An image processing bot for Facebook Messenger that uses Google Cloud Vision API to analyze images and provide insights. | 12 |
| | A deep learning library for image segmentation and object detection using PyTorch. | 1,054 |
| | A comprehensive repository of object detection papers and datasets using deep learning techniques | 11,335 |
| | An implementation of Faster R-CNN detection framework in PyTorch | 1,816 |
| | Generating photorealistic avatars from audio | 2,715 |
| | Provides state-of-the-art video understanding codebase with efficient training methods and pre-trained models for various tasks | 6,680 |
| | Real-time object detection using deep learning and a large dataset of classes | 1,184 |
| | An unsupervised object detection and segmentation framework that can learn from image data alone, without requiring human annotations. | 954 |