A Very Short Introduction to Inception Score(IS)

What is the Inception Score?

  1. Diversity (Variety) — How diverse the generated images are —The entropy of the overall distribution should be high.
  2. Quality (Goodness)— How good the generated images are — Low entropy with high predictability is required.

Formula

  1. Conditional Probability Distribution — p(y/x).
    It should be highly predictable and with low entropy. Here y is the set of labels and x is the image.
  2. Marginal Probability Distribution — p(y)

How to calculate the Inception Score?

  1. Pass the generated images through the Inception model to get the conditional label distribution p(y|x)
  2. Calculate the marginal probability distribution p(y)
  3. Calculate the KL Divergence between p(y) and p(y|x)
  4. Calculate the sum over classes and take the average of outputs over images
  5. Finally, take the exponential of the averaged value.

Limitations of the Inception Score

  1. IS will be high if the network generates one image per class only, which is not a good representation of the classes.
  2. The Inception Network is trained on the Imagenet dataset consists of 1000 classes only. The Inception score will be low if you train your GAN on a class outside of these 1000 classes.
  3. It works on the square and relatively small size images —ex. 300x300

--

--

--

Co-founder - Mate Labs | Co-founder - Raven Protocol | Author - Generative Adversarial Networks Projects | Democratizing Artificial Intelligence

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Data Analysis and Preparation for Machine Learning Projects

Cross Validation and Hyperparameter Tuning

Learn Linear Regression In Machine Learning From Scratch

Linear Regression

The state of Machine Learning and AI industry: insights from Gooroo

Processing RVL -CDIP dataset using Spark OCR on Databricks

Introduction to the types of Machine Learning Algorithms

What is Named Entity Recognition?

Coding Convolutional Neural Networks (CNN) with TensorFlow

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Kailash Ahirwar

Kailash Ahirwar

Co-founder - Mate Labs | Co-founder - Raven Protocol | Author - Generative Adversarial Networks Projects | Democratizing Artificial Intelligence

More from Medium

Curriculum Learning in Deep

Communication-Efficient Distributed Deep Learning

Fashion Image Search Engine

Python Classes and Their Use in Keras