Bridging deep learning and logical reasoning using a differentiable satisfiability solver
Project description
SATNet •
Bridging deep learning and logical reasoning using a differentiable satisfiability solver.
What is a SATnet
Installation
pip
pip install satnet
From source
git clone https://github.com/locuslab/SATNet
cd SATNet && python setup.py install
Package Dependencies
conda install -c pytorch tqdm
Docker Image
cd docker
sh ./build.sh
sh ./run.sh
Experiments:
Jupyter Notebook and Google Colab
Jupyter notebook and Google Colab
Run them manually
Getting the datasets
The Sudoku dataset and Parity dataset can be downloaded via
wget -cq powei.tw/sudoku.zip && unzip -qq sudoku.zip
wget -cq powei.tw/parity.zip && unzip -qq parity.zip
Sudoku Experiments
python exps/sudoku.py
python exps/sudoku.py --perm
python exps/sudoku.py --mnist --batchSz=50
Parity Experiments
pyhton exps/parity.py --seq=20
pyhton exps/parity.py --seq=40
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
satnet-0.1.0.tar.gz
(8.7 kB
view hashes)