An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models
An easy, flexible, and accurate plate recognition project for Chinese licenses in unconstrained situations.
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks
The purpose of this project is to demonstrate the advantages of combining multiple CNNs to a common cascade structure. In contrast to training a single CNN only, the resulting classifier can be faster and more accurate at once. It can be used e.g. for the purpose of face detection.
An implementation of Cascade R-CNN: Delving into High Quality Object Detection.
