1 Repo
Awesome GitHub RepositoriesMinibatch Standard Deviations
Adds a statistical feature map to the discriminator to detect and penalize mode collapse in generated batches.
Distinct from Minibatch Iterators: Distinct from Minibatch Iterators: adds a statistical feature map to the discriminator, not just grouping data into subsets.
Explore 1 awesome GitHub repository matching data & databases · Minibatch Standard Deviations. Refine with filters or upvote what's useful.
Awesome Minibatch Standard Deviations GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- tkarras/progressive_growing_of_gans
tkarras/progressive_growing_of_gans
6,159Auf GitHub ansehenThis repository provides a complete framework for training generative adversarial networks (GANs) that produce high-resolution photorealistic images, up to 1024 by 1024 pixels. The core technique is progressive layer growth, where both the generator and discriminator networks start training at low resolution and gradually add new layers to model finer details, enabling stable synthesis of large images. The framework includes a high-resolution image generator, an image quality metric evaluator, a latent space interpolation tool for creating smooth transition videos, and a multi-resolution datas
Implements minibatch standard deviation to help the discriminator detect mode collapse during training.
Python
