YOLO + CLIP Image Classification Project

Overview

This project combines the object detection capabilities of YOLO (You Only Look Once) with the advanced semantic analysis provided by CLIP (Contrastive Language-Image Pre-training) to enhance object detection and classification in images. This integration aims to leverage YOLO's robust detection capabilities to identify objects, which are then classified using CLIP based on their similarity to a set of predefined text descriptions.

Setup

To run this project, you need to install the required Python libraries. You can install these libraries using the provided requirements.txt file: Also, make sure that the absolute path to read-sign-detection folder is changed in road_sign.yaml file finalProject\compVisionGroupProject\road_sign.yaml:

path: C:\.....................\road-sign-detection

pip install -r requirements.txt