LukasHedegaard/continual-transformers LukasHedegaard/continual-transformers

  • Stars
    star
    26
  • Rank 930,752 (Top 19 %)
  • Language
    Jupyter Notebook
  • License
    Apache License 2.0
  • Created about 3 years ago
  • Updated about 1 year ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
LukasHedegaard/continual-transformers
github

LukasHedegaard

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

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

More Repositories

1

pytorch-benchmark

Easily benchmark PyTorch model FLOPs, latency, throughput, allocated gpu memory and energy consumption
Python
83
star
2

continual-inference

A Python library for Continual Inference Networks in PyTorch
Python
46
star
3

co3d

Official source code for "Continual 3D Convolutional Neural Networks for Real-time Processing of Videos" [ECCV2022]
Python
43
star
4

ride

Training wheels, side rails, and helicopter parent for your Deep Learning projects in PyTorch
Python
24
star
5

continual-skeletons

Official codebase for "Online Skeleton-based Action Recognition with Continual Spatio-Temporal Graph Convolutional Networks"
Python
21
star
6

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]
Jupyter Notebook
16
star
7

structured-pruning-adapters

Structured Pruning Adapters in PyTorch
Jupyter Notebook
15
star
8

datasetops

Fluent dataset operations, compatible with your favorite libraries
Python
10
star
9

continual-transformers-tf

TensorFlow implementation of Continual Transformer building blocks
Python
2
star
10

youtube-dataset-downloader

Download utility for datasets from YouTube
Python
2
star
11

opendr-activity-recognition-demo

OpenDR human activity recognition demo
Python
1
star
12

supers

Call a function in all superclasses using `supers(self).foo(42)`
Python
1
star
13

office31

Splits for Office31 domain adaptation tasks
Python
1
star
14

sudoku-solver-rust

Rust
1
star
15

LukasHedegaard.github.io

Personal website
HTML
1
star
16

keras-visual

Visualisation framework for Tensorflow Keras models
Jupyter Notebook
1
star
17

co-rider

Tiny configuration library tailored for the Ride ecosystem
Python
1
star
18

mnist-usps

MNIST-USPS datasets splits for few-shot domain adaptation
Python
1
star