Generative adversarial networks (GANs) are an architecture for training
two models simultaneously – the generator (artist) learns to create images
that look real and the discriminator (art critic) learns to apart real
images from fakes. The conditional generative adversarial network (CGAN)
is a type of GAN that involves the conditional on a class label or
data from other modalities of images.
This experiment with a CGAN generates images for each digit. The website shows a series of images from 50 epochs. The model was trained with THE MNIST DATABASE using Python and Keras/TensorFlow in Jupyter Notebook.
© 2021 by Claudia Wasem