UppuluriKalyani/ML-Nexus

Celestial Object Classification using CNN

Opened this issue · 2 comments

Karm-Dave commented

Celestial Object Classification Using CNN

Description

Implement a Convolutional Neural Network (CNN) to classify celestial objects such as stars, galaxies etc and other astronomical bodies. The model will analyze astronomical images and assign them to their respective classes based on learned patterns.

Goals

  • Build a CNN model capable of classifying celestial objects based on input images.
  • Use existing astronomical datasets (e.g., telescope images) for training and evaluation.
  • Achieve high accuracy for distinguishing between different types of celestial objects (e.g., stars, black holes, galaxies).

Datasets

  • Images with labeled classes (e.g., dwarf stars, giant stars, galaxies).

Features

  • Data Preprocessing:

    • Image resizing (e.g., 64x64x3 matrix) and normalization.
    • Data augmentation techniques (rotation, zoom, etc.).

  • Model Design:

    • CNN architecture with multiple convolutional and pooling layers.
    • Use ReLU activation and softmax for multi-class classification.
    • Include dropout layers to prevent overfitting.

  • Training & Evaluation:

    • Train the model using an appropriate optimizer (e.g., Adam).
    • Split dataset into training and test sets, or use cross-validation.
    • Evaluate the model using metrics like accuracy, precision, recall, and F1 score.

I would like to take this issue under Hacktoberfest and GSSOC 2024 Extd

github-actions commented

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!☺️
github-actions commented

Thanks for raising this issue! However, we believe a similar issue already exists. Kindly go through all the open issues and ask to be assigned to that issue.