Style transfer bot

DLS final project

This project was created as a final task in Deep Learning Shool. Bot deployed on custom linux server on vultr.

Examle of work

Installation

Clone repository then enter it's directory

cd DLS_style_transfer_bot

Create .env file with your bot token

echo BOT_TOKEN=YOUR_BOT_TOKEN > .env

Note: without .env file it wont even start

Install the dependencies with pip and start the bot.

pip install -r /requirements.txt --extra-index-url https://download.pytorch.org/whl/cpu
python main.py

Docker

Bot is very easy to install and deploy in a Docker container.

By default, the Docker will use .env file, so make sure to create it. When ready, simply use the Dockerfile to build the image.

docker build -t <youruser>/style_bot:${version}

This will create the bot image and pull in the necessary dependencies. Be sure to swap out ${version} with the actual version of bot.

Once done, run the Docker image.

docker run -d --restart=always --name=style_bot <youruser>/style_bot:${version}

Verify the deployment by simply entering the bot.

Model was taken from this github repo.