The Inception Score (IS) is an algorithm used to assess the quality of images created by a generative image model such as a generative adversarial network (GAN). [1] The score is calculated based on the output of a separate, pretrained Inceptionv3 image classification model applied to a sample of (typically around 30,000) images generated by the generative model. The Inception Score is maximized when the following conditions are true:
It has been somewhat superseded by the related Fréchet inception distance. [3] While the Inception Score only evaluates the distribution of generated images, the FID compares the distribution of generated images with the distribution of a set of real images ("ground truth").
Let there be two spaces, the space of images and the space of labels . The space of labels is finite.
Let be a probability distribution over that we wish to judge.
Let a discriminator be a function of type
The Inception Score of relative to is
Pseudocode:
INPUT discriminator .
INPUT generator .
Sample images from generator.
Compute , the probability distribution over labels conditional on image .
Sum up the results to obtain , an empirical estimate of .
Sample more images from generator, and for each, compute .
Average the results, and take its exponential.
RETURN the result.
A higher inception score is interpreted as "better", as it means that is a "sharp and distinct" collection of pictures.
, where is the total number of possible labels.
iff for almost all
The highest inception score is achieved if and only if the two conditions are both true:
The Inception Score (IS) is an algorithm used to assess the quality of images created by a generative image model such as a generative adversarial network (GAN). [1] The score is calculated based on the output of a separate, pretrained Inceptionv3 image classification model applied to a sample of (typically around 30,000) images generated by the generative model. The Inception Score is maximized when the following conditions are true:
It has been somewhat superseded by the related Fréchet inception distance. [3] While the Inception Score only evaluates the distribution of generated images, the FID compares the distribution of generated images with the distribution of a set of real images ("ground truth").
Let there be two spaces, the space of images and the space of labels . The space of labels is finite.
Let be a probability distribution over that we wish to judge.
Let a discriminator be a function of type
The Inception Score of relative to is
Pseudocode:
INPUT discriminator .
INPUT generator .
Sample images from generator.
Compute , the probability distribution over labels conditional on image .
Sum up the results to obtain , an empirical estimate of .
Sample more images from generator, and for each, compute .
Average the results, and take its exponential.
RETURN the result.
A higher inception score is interpreted as "better", as it means that is a "sharp and distinct" collection of pictures.
, where is the total number of possible labels.
iff for almost all
The highest inception score is achieved if and only if the two conditions are both true: