Skip to content

A reimplementation of "Spatial-Temporal Graph Convolutional Networks for Action Recognition" (Yan et al., 2018) in PyTorch, developed for the Deep Learning course at KTH

nagyrajmund/st-gcn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

92 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Project status: course is over, tidying up the repo currently

Description

Authors*: Livia Qian, Amrita Panesar, Rajmund Nagy

This is the project repository of "Spatiotemporal Graph Convolutional Networks for Action Recognition" for the DD2424 Deep learning in data science course at KTH. The basis of the project is this publication.

*In reverse alphabetic order.


Directory structure

/datasets           Datasets as raw .csv files. NOTE: These files should only exist locally, don't upload them to github!
/src/data           Code for loading and processing the datasets
    /network        Implementation of the network and the graph convolution layer
    /notebooks      Notebooks for debugging and exploratory analysis
    /scripts        Scripts for generating figures, experiments etc
    /utils          Miscellaneous utility functions

About

A reimplementation of "Spatial-Temporal Graph Convolutional Networks for Action Recognition" (Yan et al., 2018) in PyTorch, developed for the Deep Learning course at KTH

Topics

Resources

Stars

Watchers

Forks