Fréchet inception distance
The Fréchet inception distance (FID) is a metric used to assess the quality of images created by a generative model, like a generative adversarial network (GAN). Unlike the earlier (IS), which evaluates only the distribution of generated images, the FID compares the distribution of generated images with the distribution of real images that were used to train the generator. The FID metric is the current standard metric for assessing the quality of GANs as of 2020. It has been used to measure the quality of many recent GANs including the high-resolution StyleGAN1 and StyleGAN2 networks.
Wikipage disambiguates
Wikipage redirect
Link from a Wikipage to another Wikipage
primaryTopic
Fréchet inception distance
The Fréchet inception distance (FID) is a metric used to assess the quality of images created by a generative model, like a generative adversarial network (GAN). Unlike the earlier (IS), which evaluates only the distribution of generated images, the FID compares the distribution of generated images with the distribution of real images that were used to train the generator. The FID metric is the current standard metric for assessing the quality of GANs as of 2020. It has been used to measure the quality of many recent GANs including the high-resolution StyleGAN1 and StyleGAN2 networks.
has abstract
The Fréchet inception distance ...... leGAN1 and StyleGAN2 networks.
@en
Wikipage page ID
64,450,754
page length (characters) of wiki page
Wikipage revision ID
1,015,064,321
Link from a Wikipage to another Wikipage
wikiPageUsesTemplate
subject
comment
The Fréchet inception distance ...... leGAN1 and StyleGAN2 networks.
@en
label
Fréchet inception distance
@en