Generative_Adversarial_Network_illustration.svg


Summary

Description
English: The noise vector is fed to the generator which produces a fake image which is then fed to a discriminator. The discriminator is also fed a real image from a data set (the two discriminators shown are the same neural model). The discriminator is optimised to output 0 when fed the fake image and 1 when fed the real image. In turn, the generator is optimised so that the fake image makes the discriminator output 1.
Malti: In-noise vector jiġi mgħoddi lill-generator li jipproduċi stampa fittizja li mbagħad tiġi mgħoddija lid-discriminator. Id-discriminator jiġi wkoll mgħoddi stampa ta' vera minn data set (iż-żewġ discriminators murija huma l-istess mudell newrali). Id-discriminator jiġi ottimizzat biex jgħati 0 meta jiġi mgħoddi stampa fittizja u 1 meta jiġi mgħoddi stampa ta' vera. Minn naħa l-oħra, il-ġenerator jiġi ottimizzat biex l-istampa fittizja tagħmel lid-discriminator jgħati 1.
Date
Source Own work
Author Mtanti

Licensing

I, the copyright holder of this work, hereby publish it under the following license:
w:en:Creative Commons
attribution share alike
You are free:
  • to share – to copy, distribute and transmit the work
  • to remix – to adapt the work
Under the following conditions:
  • attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • share alike – If you remix, transform, or build upon the material, you must distribute your contributions under the same or compatible license as the original.

Captions

An illustration of how a GAN works.

Items portrayed in this file

depicts

29 June 2023