Training of SSD(Single Shot Detector) for Facial Detection using Nvidia Jetson Nano
This is an incremental application of an existing method to a specific domain (facial detection on embedded hardware) with no stated broader impact.
The project tackled facial detection by training an SSD model on a dataset of 139 labeled images and deploying it on an Nvidia Jetson Nano, achieving functional deployment but without reporting specific performance metrics.
In this project, we have used the computer vision algorithm SSD (Single Shot detector) computer vision algorithm and trained this algorithm from the dataset which consists of 139 Pictures. Images were labeled using Intel CVAT (Computer Vision Annotation Tool) We trained this model for facial detection. We have deployed our trained model and software in the Nvidia Jetson Nano Developer kit. Model code is written in Pytorch's deep learning framework. The programming language used is Python.