This content provides an overview of GANs (Generative Adversarial Networks) and the challenges in evaluating the quality of the generated synthetic images. GANs consist of two main networks, a generator and a discriminator, which are trained together to maintain an equilibrium. Since there is no objective loss function for training GANs, the evaluation of GAN models relies on manually inspecting the quality of the generated images. The full blog can be accessed on Medium.

source update: How On Earth Can We Evaluate the Generated Images By GANs? – Towards AI