https://github.com/cyanosite/intel-image-classification

Image classification using Deep Convolutional Neural Networks
https://github.com/cyanosite/intel-image-classification

Last synced: 9 days ago
JSON representation

Image classification using Deep Convolutional Neural Networks

• Host: GitHub
• URL: https://github.com/cyanosite/intel-image-classification
• Owner: Cyanosite
• License: mit
• Created: 2023-10-15T16:19:17.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-02-28T21:36:08.000Z (9 months ago)
• Last Synced: 2024-10-11T18:56:56.493Z (about 1 month ago)
• Language: Jupyter Notebook
• Size: 3.31 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Intel Image Classification

## Overview

This project aims to classify images into different classes using a deep learning model. The dataset consists of images related to various classes from the Intel Image classification dataset.

## Dataset

The dataset contains images from the following classes:

1. Forest

2. Street

3. Mountain

4. Sea

5. Building

6. Glacier

![Dataset](img/categories.png)

## Model Accuracy

The trained model achieved an accuracy of 87.4% on the validation dataset.

![Accuracy](img/model_accuracy.png)

## Prediction Example

Here is an example of how the model predicts the class of an image:

![Prediction Example](img/prediction.png)

## Installation

1. Clone the repository.

2. Install the required dependencies by running the following command:

    ```

    pip install -r requirements.txt

    ```

## Usage

To use this project, follow these steps:

1. Launch Jupyter Notebook by running the following command:

    ```

    jupyter notebook

    ```

2. Open the `solution.ipynb` notebook in Jupyter Notebook.

3. Follow the instructions in the notebook to classify images using the trained model.

Note: Make sure you have the necessary hardware and software requirements to run Jupyter Notebook.

## Contributing

Contributions are welcome! If you find any issues or have suggestions for improvement, please open an issue or submit a pull request.

## License

This project is licensed under the [MIT License](LICENSE).