Skip to content

A generic image classification program that uses Google's Machine Learning library Tensorflow and a pre-trained Deep Learning Convolutional Neural Network model like MobileNet or Inception.

Notifications You must be signed in to change notification settings

abhishekarya1/cluster-image-classifier-tensorflow

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Tensorflow Image Classifier: Globular vs Open Star Cluster

This is the repository developed for demonstrating Transfer Learning with Convolutional Neural Networks like MobileNet and Inception.

Astronomers can use this classifier to automatically label whether an image taken by telescope is of a Globular Star Cluster or an Open Star Cluster.

diff

Requirements

Usage

  1. Change directory structure for classification directories.

  2. Retrain the model using retrain.py and modifying the hyperparameters.

  3. Run the label_image.py to label the image. python label_image.py <path_to_image>

Training

training

Tensorboard Training Summaries

s1 s2

Results

Model can successfully differentiate between image of a globular cluster and an open cluster.

Accuracy

accuracy

Test on Globular Star Cluster Image

result1

Test on Open Star Cluster Image

result2

About

A generic image classification program that uses Google's Machine Learning library Tensorflow and a pre-trained Deep Learning Convolutional Neural Network model like MobileNet or Inception.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages