An open API service indexing awesome lists of open source software.

https://github.com/codeofrahul/image_classification_using_mobilenetv2_and_yolov8

This repository demonstrates image classification using two powerful deep learning models: MobileNetV2 and YOLOv8.
https://github.com/codeofrahul/image_classification_using_mobilenetv2_and_yolov8

Last synced: 7 months ago
JSON representation

This repository demonstrates image classification using two powerful deep learning models: MobileNetV2 and YOLOv8.

Awesome Lists containing this project

README

          

# Image_Classification_using_MobileNetV2_and_YOLOv8
This repository demonstrates image classification using two powerful deep learning models: MobileNetV2 and YOLOv8.

## Highlights

- **Leverages pre-trained models:** Utilizes MobileNetV2 and YOLOv8 for efficient and accurate classification.
- **Easy to use:** Provides simple functions for classifying images.
- **Multiple model options:** Offers flexibility by allowing users to choose between MobileNetV2 and YOLOv8.
- **Detailed explanations:** Includes markdown cells and comments with explanations of the models and their usage.

## Overview

This project aims to showcase the capabilities of MobileNetV2 and YOLOv8 in image classification tasks. It provides a practical example of how to load, preprocess images, and perform classification using these models.

## How it Works

1. **MobileNetV2:** Loads a pre-trained MobileNetV2 model and uses it to classify images into 1000 object categories.
2. **YOLOv8:** Utilizes a pre-trained YOLOv8 classification model to identify objects within images.

## Getting Started

1. **Clone the repository:** `git clone https://github.com/CodeofRahul/Image_Classification_using_MobileNetV2_and_YOLOv8.git`
2. **Install dependencies:** `pip install tensorflow pillow ultralytics`
3. **Run the code:** Execute the provided Python code to classify your own images.

## Contributing

Contributions are welcome! Feel free to open issues or pull requests for bug fixes, enhancements, or new features.