Computer Vision Paper Implementations

This repository contains implementations of various papers in the field of computer vision for practice and learning purposes. The goal is to build and understand different neural network architectures by implementing them on various datasets.

Implementations

1. Basic Fully Connected Neural Network

• File: x1_FC_Digit_Classification_mnist.ipynb
• Description: This notebook contains the implementation of a basic fully connected neural network for digit classification using the MNIST dataset.

2. Deeper Fully Connected Neural Network

• File: x2_Deeper_FC_Digit_Cassification_mnist.ipynb
• Description: This notebook includes a deeper fully connected neural network for improved digit classification performance on the MNIST dataset.

3. Convolutional Neural Network (CNN)

• File: x3_CNN_Digit_Classification_mnist.ipynb
• Description: This notebook provides the implementation of a convolutional neural network (CNN) for digit classification on the MNIST dataset.

Getting Started

To get started with these implementations, follow the steps below:

1. Clone the repository:

   git clone https://github.com/abhismirai10/Computer_Vision_Paper_Implementation
   cd Computer_Vision_Paper_Implementation

2. Install the required dependencies:

   pip install -r requirements.txt

3. Open the notebooks: You can open the Jupyter notebooks using Jupyter Lab or Jupyter Notebook:

   jupyter lab
   # or
   jupyter notebook

4. Run the notebooks: Select and run the cells in each notebook to see the implementations in action.

Future Implementations

I plan to implement more computer vision papers regularly and update this repository with new notebooks. Stay tuned for more implementations!

Contributing

If you would like to contribute, feel free to fork the repository and submit pull requests. Any suggestions or improvements are welcome!

License

This project is licensed under the MIT License. See the LICENSE file for details.

---

Happy coding and learning!