Tycho van der Ouderaa's repositories
MovingMNIST
Moving MNIST as PyTorch Dataset
RevGAN
RevGAN implementation in PyTorch. We extend the Pix2pix and CycleGAN framework by exploring approximately invertible architectures in 2D and 3D. These architectures are approximately invertible by design and thus partially satisfy cycle-consistency before training even begins. Furthermore, since invertible architectures have constant memory complexity in depth, these models can be built arbitrarily deep without requiring additional memory. In the paper we demonstrate superior quantitative output on the Cityscapes and Maps datasets at near constant memory budget.
Char-RNN-Understanding
Understanding Character-level RNN Language Models with Diagnostic Classifiers in PyTorch.
InvertibleLanguageModel
Stacked RNN Language Model with invertible recurrent blocks
nodejs_multiplayergame
Multiplayer game in javascript using websockets and node.js
flownet2-pytorch
Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Geo-Vec-Model
Implementation of the Geo-Vec model for embedding documents
glow-pytorch
pytorch implementation of openai paper "Glow: Generative Flow with Invertible 1×1 Convolutions"
lwjgl_platformer
Java platformer game using the lwjgl library
mml-autumn-2022
Materials for Autumn 2022 Mathematics for Machine Learning course.
mypy
Optional static typing for Python
website2021
Mark's website. Edit this to add your name to the research group.