charbel-a-hC / ups-mv-gans

This repository implements data augmentation for improving classification task using a GAN. Also ImageToImage translation will be implemented

Machine Vision GANS Project

To-Do

• add tensorboard monitoring
• argparser for CLI training automation
• Setup google colab instace
• Setup TF for RTX3070
• Edit Dockerfile cudnn/CUDA versions

Environment Setup

Clone and cd in the repository before running any of the commands:

git clone https://github.com/charbel-a-hC/ups-mv-gans.git
cd ups-mv-gans

You also need to install python3 locally if you wish to run the notebook on a local environment. This automatically install python3.6.9. For Ubuntu:

sudo apt-get install python3.8 \
    python3-pip \
    python3-venv \
    python3-dev \
    python3-distutils

And you need to update your pip:

/usr/bin/python3 -m pip install --upgrade pip

Docker

If you have docker installed:

docker build . -t ups-gans
docker run -it --rm -v --runtime=nvidia ${PWD}:/ups-mv-gans ups-gans

Local Environment (Ubuntu-18.04) - Poetry

Simply run the make command in the repository:

make env

A virtual environment will be created after running the above command. In the same shell, run:

poetry shell

This will activate the environment and you start running any script from this stage.

Local Environment - Conda

You can download Anaconda here. After the download, open an anaconda navigator prompt if you're on windows and run the following commands:

conda env create -f environment.yml
conda activate ml

Note: If you're on Linux, you can open a normal terminal and run the following command before creating the environment:

conda activate base

Google Colaboratory

You can open the notebook in Google Colab here: