Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature request: Add New Project - Image Classification using CNN (CIFAR-10 Dataset) under the Neural Networks Folder #822

Closed
sanyadureja opened this issue Nov 8, 2024 · 4 comments · Fixed by #823

Comments

@sanyadureja
Copy link
Contributor

Is your feature request related to a problem? Please describe.
Currently, the Neural Networks folder lacks a comprehensive example of image classification using Convolutional Neural Networks (CNNs) on standard datasets. Beginners often find it challenging to understand CNNs without practical, hands-on examples, especially on widely-used datasets like CIFAR-10.

Describe the solution you'd like
I would like to add a project under the Neural Networks folder that demonstrates image classification using CNNs, specifically utilizing the CIFAR-10 dataset. This will serve as an accessible introduction to CNN architecture for users, showcasing essential concepts such as convolutional layers, pooling, activation functions, and model evaluation.

Describe alternatives you've considered
An alternative would be to implement image classification on a simpler dataset (e.g., MNIST) or a more complex one (e.g., ImageNet). However, CIFAR-10 provides a balanced intermediate level, allowing users to understand CNNs without an overwhelming amount of data or complexity.

Approach to be followed (optional)

  • Load and preprocess the CIFAR-10 dataset.
  • Build a CNN model using layers such as Conv2D, MaxPooling2D, Flatten, and Dense.
  • Compile the model, specifying the optimizer, loss function, and evaluation metrics.
  • Train the model on the CIFAR-10 training data and validate it on test data.
  • Evaluate the model’s performance, and provide visualizations of sample predictions.
  • Document the code to guide users through the steps.

Additional context
This feature would enhance the Neural Networks folder by providing a hands-on, structured introduction to CNNs, helping users understand how to apply deep learning to image classification tasks. A sample architecture or learning curves could be included to visually aid understanding.

@sanyadureja sanyadureja added the enhancement New feature or request label Nov 8, 2024
Copy link

github-actions bot commented Nov 8, 2024

Thanks for creating the issue in ML-Nexus!🎉
Before you start working on your PR, please make sure to:

  • ⭐ Star the repository if you haven't already.
  • Pull the latest changes to avoid any merge conflicts.
  • Attach before & after screenshots in your PR for clarity.
  • Include the issue number in your PR description for better tracking.
    Don't forget to follow @UppuluriKalyani – Project Admin – for more updates!
    Tag @Neilblaze,@SaiNivedh26 for assigning the issue to you.
    Happy open-source contributing!☺️

@sanyadureja
Copy link
Contributor Author

@Neilblaze @SaiNivedh26 @UppuluriKalyani starting to work on this issue.

@sanyadureja
Copy link
Contributor Author

@UppuluriKalyani, @Neilblaze, and @SaiNivedh26 please review my PR #823 . I've solved the issue #822
Looking forward to getting the PR merged and assignment of level and labels.

Awaiting your response. Thank you!

Copy link

github-actions bot commented Nov 8, 2024

Hello @sanyadureja! Your issue #822 has been closed. Thank you for your contribution!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
2 participants