A dissertation submitted in partial fulfilment of the requirements for the degree of M.Sc. in Artificial Intelligence.
May 2021
Table of Contents
- Download and install Anaconda distribution for Python 3.8
- (Optional*) Download and install CUDA Toolkit 10.2
- (Optional*) Download and install cuDNN compatible with version CUDA 10.2
* Required for real-time processing
* Requires Nvidia CUDA compatible GPU
- Clone repository
git clone https://github.com/samuelsciberras/msc-ai
- Create conda environment
conda env create --file yv4-dsort-speedest.yml
- Download YOLOv4 trained models here and place them in directory /System/checkpoints/
- Activate conda environment
conda activate yv4-dsort-speedest
- Run
cd System/ python main.py
Samuel Sciberras - [email protected]