Teaching a program to paint like an artist

Teaching a program to paint like an artist
Spock Singh as a painting

There are some things that completely blow your mind. Applying artist specific styles to images is one of them. Completely sci-fiction - although the Prisma filter has made this accessible.

In the last blog, I set up the core software requirements for the Udacity deeplearning course. This blog uses the setup to transfer the styles of 3 famous paintings and apply it to images.

It takes ages for an artist to come to a signature style. It takes longer for another to mimic the style and I cannot fathom if a mimic can apply the style to different images. Deep learning does it with panache. Impressive! I am a convert.

I used the project called fast-style-transfer and ran the following command on an image to produce an output.

# creating a sandbox environment for python
conda create -n style-transfer python=3.5
source activate style-transfer
conda install -c conda-forge tensorflow=0.11.0
conda install scipy pillow

# doing style transfer
python evaluate.py --checkpoint ./rain-princess.ckpt --in-path  --out-path ./output_image.jpg

Pictures to be stylised

Untitled
Untitled

The original artwork:

The Wave by Kanagawa

Untitled

Scream by Edward Munch

Untitled

Rain Princess by Leonid Affremov

Untitled

The modified images

Untitled
Untitled
Untitled
Untitled
Untitled