natanielruiz / network-image-translation

Image translation on a webpage using a server-client architecture on a GENI slice.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

network-image-translation

Image translation on a webpage using a server-client architecture on a GENI slice.

To reproduce:

  1. Create a slice on GENI using the 'rspec' file and ssh into the server.
  2. sudo apt install git-all
  3. Clone repo.
  4. sudo mv sites-available/* /etc/apache2/sites-available/.
  5. sudo mv www/* /var/www/.
  6. Download checkpoints to folder "/var/www/checkpoints" from here: https://drive.google.com/drive/folders/0B9jhaT37ydSyRk9UX0wwX3BpMzQ
  7. sudo apt-get update
  8. sudo apt-get install apache2
  9. sudo service apache2 restart
  10. sudo apt-get install python3.6
  11. sudo apt install python3-pip
  12. pip3 install virtualenv
  13. cd /var/www
  14. python3 -m venv myVM3.6
  15. source myVM3.6/bin/activate
  16. sudo chmod _R 777 myVM3.6
  17. pip3 install tensorflow, scipi, moviepy, imageio, ffmpeg, cgi-tools
  18. sudo chmod -R 777 style-image
  19. sudo chmod -R 777 out_images

The server is online and ready to go.

You can also use the setup.sh script.

To use:

  1. Navigate to http://192.12.245.162/hello.py on your web browser.
  2. Click on 'Choose File'
  3. Select a .png or .jpg image from your computer.
  4. Click on 'Upload'

Demo Video

The system will randomly select one of our style images. It will then present your original input, the style image used as well as the resulting stylized image which contains your original content with the style of the style image.

Enjoy!

About

Image translation on a webpage using a server-client architecture on a GENI slice.


Languages

Language:Python 82.5%Language:HTML 14.0%Language:Roff 2.2%Language:Shell 1.3%