Here, we let and (outputs of local discriminator) represent the fidelity confidence of the cropped images and , respectively. We let and (outputs of global discriminator) represent the fidelity confidence of whole ...
Implementation of Wasserstein loss
Get Hands-On Generative Adversarial Networks with PyTorch 1.x now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.