Image Classification for Galaxy10

# Image Classification for Galaxy10 ## Problem Statement Given a dataset of diverse galaxy images captured through various telescopes and instruments, the objective is to implement Image Classification Neural Network models for Galaxy10 classification. You can use Convolutional Neural Networks (CNNs) or any other prebuilt models available in libraries like TensorFlow or PyTorch. The goal is to automatically classify these galaxies into one of the following categories: Disturbed Galaxies, Merging Galaxies, Round Smooth Galaxies, In-between Round Smooth Galaxies, Cigar Shaped Smooth Galaxies, Barred Spiral Galaxies, Unbarred Tight Spiral Galaxies, Unbarred Loose Spiral Galaxies, Edge-on Galaxies without Bulge, and Edge-on Galaxies with Bulge. The evaluation will be based on the accuracy of the classification. ## Task Implement Image Classification Neural Network models, such as Convolutional Neural Networks (CNNs), to accurately categorize astronomical images into ten distinct types of galaxies. Utilize available prebuilt models in libraries like TensorFlow or PyTorch (Preferably), and fine-tune them for this specific classification task. Try to achieve the highest accuracy possible and also play with different models. [Dataset](https://drive.google.com/drive/folders/1S1-m-RlaP96MVQvhUZR0_FSIrgMX-1KL?usp=sharing)