Released Neural Network Libraries v1.12.0!

Friday, October 09, 2020

Release

Posted by shin

We have Released Neural Network Libraries v1.12.0! StyleGan2 and TecoGAN examples are now available!

Spotlight

StyleGan2 Inference / Colab Demo Open In Colab

StyleGan2 is a state-of-the-art model for image generation, with improved quality from the original StyleGan. The model introduces a new normalization scheme for generator, along with path length regularizer, both of which contribute to getting rid of artifacts present in the previous model. Currently, only inference code is available, but we plan to follow up quickly with training code.

We have also made Colab demo for StyleGan2. By changing a random seed fed to the network, you can see the generated faces change drastically. Not only simple face generation, you can try face generation with style mixing technique proposed in the paper as well (you can see that result below). Please give it a try and have fun!


​​

TecoGAN

Input Output
       
       

TecoGAN (TEmporally COherent GAN) is a model for video super-resolution that exploits temporal self-supervision. By leveraging temporal adversarial learning with a novel ping-pong loss, the model is able to generate results free of temporal artifacts while preserving spatial details.

Utilities

Format Conversion

Examples

Documentation

Bugfix