- Pytorch - Machine learning library for Python-related dependencies
- Anaconda - Anaconda includes all the other Python-related dependencies
- ArgParse - Command line parsing in Python
Below are installation instructions under Anaconda. IMPORTANT: We use python 3.7.3
- Setup a fresh Anaconda environment and install packages:
# create and switch to new anaconda env
$ conda create -n RUN python=3.7.3
$ source activate RUN
# install required packages
$ pip install -r requirements.txt
- Here are the instructions to use the code base:
- To train the model with options, use the command line:
$ python train_model.py --options %(For the details of options)
$ python train_model.py [-h] [short_name_arg] %(For explanation on the commands)
- An example of running:
$ python train_model.py -m1 'map_1' -m2 'map_2' -me 30 -do 0.9
- Choose a model to evaluate on test map, with the command line:
$ python test_model.py --options %(For the details of options)
$ python test_model.py [-h] [short_name_arg] %(For explanation on the commands)
This software and data are released under the terms of the Apache License, Version 2.0.