8000 GitHub - mengsig/GeoAI: Predicting erosion patterns via. ML
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

mengsig/GeoAI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation


How to install:

To install the repository, ensure that you enable your virtual environment. I can recommend py-venv. This can easily be installed on Unix-like OS (Mac, Linux). For Mac, use Brew, and for Linux use the suitable package manager - i.e. pacman for Arch-linux, apt-get for Ubuntu, etc.

Then create your virtual environment using:

python -m venv geoAI

Then activate your virtual environment using:

source geoAI/bin/activate

Thereafter, simply run:

pip install -r requirements.txt

to install all of the necessary dependencies.


How to run the CNNs:

To run any of the CNN models, please call the following command:

python src/<the_cnn_you_want_to_run.py>

where <the_cnn_you_want_to_run>={cnn.py, cnn_data_augment.py, cnn_binary.py}.

It should generate a directory called results/, wherein runs will be saved according to your local time.

An example output of src/cnn_data_augment.py:

Which yields an MSE loss $L = 0.846$.

About

Predicting erosion patterns via. ML

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages

0