https://github.com/ashusao/st-samplenet
Spatially Constrained Transformer with Efficient Global Relation Modelling for Spatio-Temporal Prediction
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (5.1%) to scientific vocabulary
Repository
Spatially Constrained Transformer with Efficient Global Relation Modelling for Spatio-Temporal Prediction
Basic Info
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
ST-SampleNet
Spatially Constrained Transformer with Efficient Global Relation Modelling for Spatio-Temporal Prediction
Description
This repository is the implementation of the paper "Spatially Constrained Transformer with Efficient Global Relation Modelling for Spatio-Temporal Prediction" by Ashutosh Sao and Simon Gottschalk.
Installation
To install all dependencies
bash
conda create -n stsamplenet
conda activate stsamplenet
bash install.sh
Folder Structure
Input data: tmp/data/
Saved model: tmp/model/
Training & Evaluation
Run teacher model containing all regions first.
Run:
bash
python3 main.py
To train region pruned model set the region_keep_rate and train_teacher flag in config.ini
and train the model again using the command above to see the effect of pruning.
Owner
- Name: Ashutosh Sao
- Login: ashusao
- Kind: user
- Location: Hannover, Germany
- Repositories: 1
- Profile: https://github.com/ashusao
A Machine Learning Enthusiast, pursuing PhD. in the same at L3S Research Cebter, Hannover.
GitHub Events
Total
- Watch event: 1
- Push event: 1
Last Year
- Watch event: 1
- Push event: 1