Generative Adversarial Networks Projects

Initial latent vector approximation

Initial latent vector approximation is a method to approximate a latent vector to optimize the reconstruction of face images. To approximate a latent vector, we have an encoder network. We train the encoder network on the generated images and real images. Once trained, the encoder network will start generating latent vectors from the learned distribution. The training objective function for training the encoder network is the Euclidean distance loss.