Skip to content

compositional generalisation with reasoning on discrete bottlenecks

Notifications You must be signed in to change notification settings

mh-amani/neural_discrete_reasoning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

7c75302 · Feb 28, 2024

History

16 Commits
Nov 25, 2023
Feb 28, 2024
Nov 25, 2023
Nov 25, 2023
Nov 25, 2023
Nov 25, 2023
Dec 12, 2023
Nov 25, 2023
Nov 25, 2023
Dec 7, 2023
Nov 25, 2023
Nov 25, 2023
Nov 25, 2023
Nov 25, 2023
Dec 7, 2023
Nov 25, 2023
Nov 25, 2023
Nov 25, 2023

Repository files navigation

neural discrete reasoning

Description

What it does...

Installation

Pip

# clone project
git clone https://github.com/mh-amani/neural_discrete_reasoning
cd neural_discrete_reasoning

# [OPTIONAL] create conda environment
conda create -n ndr python=3.11
conda activate ndr

# install pytorch according to instructions
# https://pytorch.org/get-started/

# install requirements
pip install -r requirements.txt

Conda

# clone project
git clone https://github.com/mh-amani/neural_discrete_reasoning
cd neural_discrete_reasoning

# create conda environment and install dependencies
conda env create -f environment.yaml -n ndr

# activate conda environment
conda activate ndr

How to run

Train model with default configuration

# train on CPU
python src/train.py trainer=cpu

# train on GPU
python src/train.py trainer=gpu

Train model with chosen experiment configuration from configs/experiment/

python src/train.py experiment=experiment_name.yaml

You can override any parameter from command line like this

python src/train.py trainer.max_epochs=20 data.batch_size=64

About

compositional generalisation with reasoning on discrete bottlenecks

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages