metadata

title: Butterfly Classification Using CNN
emoji: 🚀
colorFrom: gray
colorTo: blue
sdk: gradio
sdk_version: 4.15.0
app_file: app.py
pinned: false
license: mit

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Butterfly Classification using CNN

Author: Kamelia Zaman Moon
Project link: https://huggingface.co/spaces/KameliaZaman/Butterfly-Classification-using-CNN
Language(s): Python
License: MIT
Contact: [email protected]

Introduction
Model Architecture
How-to Guide
License
Contributors

1. Introduction

This project focuses on classifying butterfly images using a Convolutional Neural Network (CNN). The dataset includes images of butterflies and moths, with the goal of training a model to accurately predict the species of a given butterfly image.

2. Model Architecture

The CNN model used for this project is based on the ResNet50V2 architecture. The model is trained on a dataset consisting of training, validation, and test sets. The key components of the model architecture include convolutional layers, dropout for regularization, global average pooling, and fully connected layers. The model is compiled using the Adam optimizer and sparse categorical crossentropy loss.

──  model_checkpoint_manual_effnet.h5 - generated model.

──  Butterfly classification with CNN.ipynb - preprocesses input, trains, saves and evaluates the model.

──  app.py - this module starts the app interface.

──  README.md - readme file of this project.

──  requirements.txt - list of required packages.

3. How-to Guide

3.1. Data Preparation

The dataset is loaded from a CSV file containing information about the butterflies and moths.
Image paths are constructed based on the dataset information.
The dataset is split into training, validation, and test sets.

3.2. Exploratory Data Analysis (EDA)

Visualizations are created to explore the distribution of labels in the dataset.

3.3. Image Data Generation

Image data generators are used to augment the training data.
Training and validation data generators are created.

3.4. Model Training

The ResNet50V2-based model is constructed and compiled.
The model is trained on the augmented training data, and its performance is monitored using validation data.
Callbacks for reducing learning rate and early stopping are employed during training.

3.5. Model Evaluation

The trained model is evaluated on the test set to measure its accuracy.

3.6. Deployment

Gradio is utilized for deploying the trained model.
Users can input an image, and the model will predict the butterfly species.

# clone project   
git clone https://huggingface.co/spaces/KameliaZaman/Butterfly-Classification-using-CNN/tree/main

# go inside the project directory 
cd Butterfly-Classification-using-CNN

# install the required packages
pip install -r requirements.txt

# run the gradio app
python app.py

4. License

This project is licensed under the MIT License.

5. Contributors

Kamelia Zaman Moon - [email protected]

Spaces:

KameliaZaman
/

Butterfly-Classification-using-CNN

Sleeping