mangtronix / cartoonize

Google Colab web app to convert images and videos into cartoon!

Home Page:https://colab.research.google.com/github/mangtronix/cartoonize/blob/master/Cartoonize_Colab.ipynb

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Cartoonizer on Colab

CartoonGAN web app modified by Mangtronix to run on Google Colab.

To run the web app on Google Colab, simply open this link:

https://colab.research.google.com/github/mangtronix/cartoonize/blob/master/Cartoonize_Colab.ipynb

Enable GPU using Runtime->Change runtime type

Start the code using Runtime->Run all

The URL to the web app will be printed in the final cell. Click on the URL to access the web app. For example (your URL will be different):

Running on http://b20379fdb887.ngrok.io

ORIGINAL README

Cartoonizer

Convert images and videos into a cartoon!

The webapp is deployed here - https://cartoonize-lkqov62dia-de.a.run.app

Prerequisites for Google Cloud and Algorithmia

These are important steps if you want to leverage Google buckets, signed URLs and Algorithmia's platform.

Cloud Run authentication

To use any functionalities pertaining to Google Cloud, you'll need a global authentication file (JSON). You can obtain this JSON by following the steps given here - Getting started with authentication

After you get the JSON file, rename it to token.json (so that it's compatible with the codebase).

Set the environment variable in your terminal -

export GOOGLE_APPLICATION_CREDENTIALS="/path/to/token.json"

Notes:

  • You can set it permanently by adding this line to ~/.bashrc.
  • Dockerfile already includes the setting of this particular environment variable. :)

Algorithmia

We used the Serveless AI Layer product of Algorithmia for inference on videos. To learn more on how to deploy your model in Algorithmia, check here - https://algorithmia.com/developers

Installation

Application tested on:

  • python 3.7
  • tensorflow 2.1.0
  • tf_slim 1.1.0
  • Cuda version 10.1
  • OS: Linux (Ubuntu 18.04)

Using Docker

The easiest way to get the webapp running is by using the Dockerfile:

  1. cd into the root directory and build the image
docker build -t cartoonize .

Note: Set the appropriate values in config.yaml before building the image.

  1. Run the container by exposing the appropriate ports
docker run -p 8080:8080 cartoonize

Using virtualenv

  1. Make a virtual environment using virutalenv and activate it
virtualenv -p python3 cartoonize
source cartoonize/bin/activate
  1. Install python dependencies
pip install -r requirements.txt
  1. Run the webapp. Be sure to set the appropriate values in config.yaml file before running the application.
python app.py

Sample Image and Video

Emma Watson Cartoonized

Emma Watson Cartoonized

Youtube Video of Avenger's Bar Scene Cartoonized

Cartoonized version of Avenger's bar scene

License

  1. Copyright © Cartoonizer (Demo webapp)

  2. Copyright (C) Xinrui Wang, Jinze Yu. (White box cartoonization)

About

Google Colab web app to convert images and videos into cartoon!

https://colab.research.google.com/github/mangtronix/cartoonize/blob/master/Cartoonize_Colab.ipynb

License:Other


Languages

Language:HTML 40.6%Language:Python 30.7%Language:Jupyter Notebook 27.4%Language:Dockerfile 1.3%