Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. License
5. Contact
6. Acknowledgements

About The Project

Project for FINAL EXAM for "Machine Learning in Practice(CSE340-00)" Kyunghee University. Main purpose is to detect age of given person at range between 2 and 120, only using models with size less than 2M parameters.

This repo includes 5 different models : Modified ResNet18, Modified SpinalNet, Modified DenseNet, DLDLv2, RandomBin

Built With

• [Pytorch]

Getting Started

To get a local copy up and running follow these simple steps.

Prerequisites

• Pytorch
• Since datasets are used only for the final, it cannot be uploaded. But you may find FGNET, UTKFace, Adience, IMDB-WIKI datasets interesting.

Installation

1. Clone the repo

   git clone https://github.com/dhkim2810/AgeDetect

2. Install prerequisites

• Pytorch

Usage

You can run models using files in script folder. For basic use,,,

 python main.py --use_gpu --trial 1 --arch resnet18

License

Distributed under the MIT License. See LICENSE for more information.

Contact

Donghoon Kim - [email protected]

Project Link: https://github.com/dhkim2810/AgeDetect