Skip to content

Latest commit

 

History

History
25 lines (19 loc) · 904 Bytes

readme.md

File metadata and controls

25 lines (19 loc) · 904 Bytes

Galaxy morphology classification with CNNs

Accompanying repository to the deep learning project that I completed for PH0101

Presentation

See the written report, where I walk you through the entire workflow for this project, including exploratory data analysis, image preprocessing and finally building a convolutional neural network (CNN) with TensorFlow and the Keras API.

Installation

Download the source code

$ git clone https://github.com/paulphys/galaxyclass

The source code already includes instructions for downloading the dataset, but in case you want to get it separately

$ curl -LO https://physics.sh/galaxyclass-data.zip

Usage

Start the notebook

$ jupyter-notebook galaxyclass.ipynb