https://github.com/vishnun0027/cnn-image-classification

This project is focused on developing a CNN deep learning model to classify images
https://github.com/vishnun0027/cnn-image-classification

cnn-model image-classification python tensorflow

Last synced: 2 months ago
JSON representation

This project is focused on developing a CNN deep learning model to classify images

• Host: GitHub
• URL: https://github.com/vishnun0027/cnn-image-classification
• Owner: vishnun0027
• Created: 2024-08-17T17:05:55.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-08-18T06:42:40.000Z (4 months ago)
• Last Synced: 2024-09-25T07:32:00.298Z (3 months ago)
• Topics: cnn-model, image-classification, python, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 47.4 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# CNN-image-classification

Indian Bird Species Classification using CNN

This project is focused on developing a deep learning model to classify images of Indian bird species into 25 distinct classes. The dataset comprises 30,000 training images and 7,500 validation images, representing different bird species commonly found in India.

## Dataset

The dataset contains a total of 37,000 images split into train and validation sets in an 80:20 ratio, with 30,000 images in the training set and 7,500 images in the validation set. Each species has 1,500 images in the dataset. This dataset can be used for image classification tasks and to develop machine learning models to recognize different species of birds found in India.

Download the Dataset

You can download the dataset from the following link:

[Indian Birds Species Image Classification Dataset](https://www.kaggle.com/datasets/ichhadhari/indian-birds)

## Project Structure

* Dataset: The dataset is organized into training and validation sets, each containing images categorized into 25 classes.

* Model: A Convolutional Neural Network (CNN) was implemented using TensorFlow and Keras. The model architecture consists of multiple convolutional layers with max pooling, followed by fully connected layers. Dropout and L2 regularization were used to prevent overfitting.

* Data Augmentation: Data augmentation techniques such as random flipping, rotation, and zooming were applied to enhance model generalization.

* Optimization: The model was compiled with the Adam optimizer and trained with early stopping and checkpointing to save the best-performing model.

* Evaluation: The model's performance was evaluated based on accuracy and loss on the validation set.

## Key Features

* Custom CNN Model: A custom CNN architecture tailored for the task of bird species classification.

* Data Augmentation: Integrated data augmentation to improve model robustness.

* Training Optimization: Early stopping and model checkpointing to ensure optimal training and prevent overfitting.

* TensorBoard: Visualization of training progress using TensorBoard.