Lukas Hedegaard

pytorch-benchmark. Easily benchmark PyTorch model FLOPs, latency, throughput, allocated gpu memory and energy consumption

continual-inference. A Python library for Continual Inference Networks in PyTorch

co3d. Official source code for "Continual 3D Convolutional Neural Networks for Real-time Processing of Videos" [ECCV2022]

continual-skeletons. Official codebase for "Online Skeleton-based Action Recognition with Continual Spatio-Temporal Graph Convolutional Networks"

continual-transformers. Official Pytorch Implementation for "Continual Transformers: Redundancy-Free Attention for Online Inference" [ICLR 2023]

ride. Training wheels, side rails, and helicopter parent for your Deep Learning projects in PyTorch

structured-pruning-adapters. Structured Pruning Adapters in PyTorch

dage. Official TensorFlow implementation for "Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol" [TIP 2021] and "Supervised Domain Adaptation using Graph Embedding" [ICPR 2020]

datasetops. Fluent dataset operations, compatible with your favorite libraries

CoOadTR. Ablation study for "OadTR: Online Action Detection with Transformers".

office31. Splits for Office31 domain adaptation tasks

youtube-dataset-downloader. Download utility for datasets from YouTube

ptflops. Flops counter for convolutional networks in pytorch framework

continual-transformers-tf. TensorFlow implementation of Continual Transformer building blocks

keras-visual. Visualisation framework for Tensorflow Keras models

opendr-activity-recognition-demo. OpenDR human activity recognition demo

ActivityNet. This repository is intended to host tools and demos for ActivityNet

co-rider. Tiny configuration library tailored for the Ride ecosystem

sudoku-solver-rust. Rust

channel-spa-experiments. Experiments for channel-based Structured Pruning Adapters

mnist-usps. MNIST-USPS datasets splits for few-shot domain adaptation

supers. Call a function in all superclasses using `supers(self).foo(42)`