8000 GitHub - BENULL/Mem-STGCAE: This is the implementation of the paper "Memory Enhanced Spatial-Temporal Graph Convolutional Autoencoder for Human-related Video Anomaly Detection"
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

This is the implementation of the paper "Memory Enhanced Spatial-Temporal Graph Convolutional Autoencoder for Human-related Video Anomaly Detection"

Notifications You must be signed in to change notification settings

BENULL/Mem-STGCAE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Memory Enhanced Spatial-Temporal Graph Convolutional Autoencoder for Human-related Video Anomaly Detection

This is the implementation of the paper "Memory Enhanced Spatial-Temporal Graph Convolutional Autoencoder for Human-related Video Anomaly Detection"

Dependencies

  • Pytoch 1.7.0
  • Numpy
  • SciPy
  • Sklearn

Dataset

ShanghaiTech

please download the data from the following link

Link: trajectories

Directory Structure

.

├── models -- Including graph definitions and convolution operators

├── utils -- Data process and score utils

├── data -- Dataset directory

├── README.md

└── train_eval.py -- Main file for training / inference

Training

To train a model from scratch you should look up the model's configuration options.

Here is one example:

python train_eval.py --data_dir {dataset folder} --exp_dir {path to save experiment result}

About

This is the implementation of the paper "Memory Enhanced Spatial-Temporal Graph Convolutional Autoencoder for Human-related Video Anomaly Detection"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Lan 2D44 guages

0