Pinned Repositories
gamephysikWS19
Transformer-Explainability
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
adapter-based-news-recommender
In this project we trained personalized transformer models for news recommendation using adapters [similar to (IA)^3]. With layerwise relevancy propagation, we try to explain the recommendation to the user. Using a web interface and displaying word clouds, the user can be assigned to a “filter bubble”. This allows users to reflect on their behavior
facenet-pytorch
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
godot-amazon-android-module
Simple basic module to use AmazonGameCircle and Amazon IAP in Godot
heightmap-data-sampler
Some scripts dealing with different map-projection to sample regularized quadratic patches from given real-world heightmap data. The regularized patches can be used to train neural networks (for example GANs))
low-resource-ts-improvement-experiments
A bunch of experiments to improve text simplification (TS) tasks using encoder-decoder transformers
simple-game-engine
Exercises for the purpose of creating your own simple game engine based on low level direct x commands.
ASG_ProjectJJJ
Joshua
josh-oo's Repositories
josh-oo/godot-amazon-android-module
Simple basic module to use AmazonGameCircle and Amazon IAP in Godot
josh-oo/adapter-based-news-recommender
In this project we trained personalized transformer models for news recommendation using adapters [similar to (IA)^3]. With layerwise relevancy propagation, we try to explain the recommendation to the user. Using a web interface and displaying word clouds, the user can be assigned to a “filter bubble”. This allows users to reflect on their behavior
josh-oo/facenet-pytorch
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
josh-oo/heightmap-data-sampler
Some scripts dealing with different map-projection to sample regularized quadratic patches from given real-world heightmap data. The regularized patches can be used to train neural networks (for example GANs))
josh-oo/low-resource-ts-improvement-experiments
A bunch of experiments to improve text simplification (TS) tasks using encoder-decoder transformers
josh-oo/simple-game-engine
Exercises for the purpose of creating your own simple game engine based on low level direct x commands.