https://github.com/alyssahusna44/poai-image-classification

An implementation of an AI model that classifies animal subspecies. The project involved data preparation, model training using ResNet50, DenseNet121, and MobileNetV3, and evaluation using metrics: accuracy and mAP. 🗂️
https://github.com/alyssahusna44/poai-image-classification

artificial-intelligence image-classification machine-learning model-training-and-evaluation neural-networks numpy pandas python tensorflow

Last synced: 3 months ago
JSON representation

An implementation of an AI model that classifies animal subspecies. The project involved data preparation, model training using ResNet50, DenseNet121, and MobileNetV3, and evaluation using metrics: accuracy and mAP. 🗂️

• Host: GitHub
• URL: https://github.com/alyssahusna44/poai-image-classification
• Owner: alyssahusna44
• License: mit
• Created: 2025-01-24T13:48:58.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-03-16T13:02:26.000Z (over 1 year ago)
• Last Synced: 2025-03-31T11:17:28.968Z (over 1 year ago)
• Topics: artificial-intelligence, image-classification, machine-learning, model-training-and-evaluation, neural-networks, numpy, pandas, python, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 1.47 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Animal Subspecies Classification

This project focuses on the classification of animal subspecies using machine learning models. The models trained in this repository are designed to classify images of animals into various subspecies categories.

## Table of Contents

- [Overview](#overview)

- [Models](#models)

- [Setup Instructions](#setup-instructions)

- [Usage](#usage)

- [License](#license)

## Overview

The goal of this project is to create accurate classifiers for different animal subspecies based on image data. We utilize deep learning techniques and pre-trained models like ResNet50, MobileNetV3, and DenseNet121 for efficient training.

## Models

The following models are available in this project:

- **ResNet50**: A deep residual network model for image classification.

- **MobileNetV3**: A lightweight model optimized for mobile and edge devices.

- **DenseNet121**: A densely connected convolutional network for efficient feature reuse.

### Accessing the Models

The models are hosted on Google Drive. You can download them from the following folder:

[**Animal Subspecies Classification Models**](https://drive.google.com/drive/folders/1amG7RqxqujTs5DDMLn1nexEp-KSVoR4U?usp=sharing)

Download the desired model file and follow the usage instructions to integrate it into your own classification pipeline.

## Setup Instructions

1. **Clone the Repository**

2. **Set Up Python Environment**

3. **Install Dependencies**

   

## Usage

1. **Download the Model:**

   Download the model of your choice from the Google Drive folder linked above.

2. **Run the Classification Script:**

   Once the model is downloaded, use the following script to classify an image:

## Contributors

- **Alyssa Husna binti Jamarizan**

- **Izz Hakimi bin Khairul Adzha**

- **Alya Azwin binti Zamri**

- **Nur Sazahah binti Salauddin**

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.