This repository provides a MATLAB / Caffe re-implementation of the Faster R-CNN object detection framework (originally from Ren et al. 2015). The Faster R-CNN architecture combines a Region Proposal Network (RPN) with a Fast R-CNN style detection network to share convolutional feature maps and thus speed up detection. The repo includes code to train, test, and deploy Faster R-CNN models under the MATLAB / Caffe environment, example configuration files, and model checkpoints. Multiple configuration files for different datasets and architectures. Evaluation scripts for mAP and detection metrics.
Features
- Shared convolutional backbone for proposals + detection
- Region Proposal Network (RPN) for generating object proposals
- End-to-end training of proposal + detector
- Multiple configuration files for different datasets and architectures
- Support for fine-tuning existing models
- Evaluation scripts for mAP and detection metrics
Project Samples
Categories
Computer Vision LibrariesLicense
MIT LicenseFollow Faster R-CNN
You Might Also Like
MongoDB Atlas runs apps anywhere
MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Faster R-CNN!