1 个仓库
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
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- tkarras/progressive_growing_of_gans
tkarras/progressive_growing_of_gans
6,159在 GitHub 上查看This 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
