CycleGAN Documentation

In this week’s assignment, I tried with CycleGAN, monet2photo model. The model trained around 3.5 days. But the download process from Intel Cloud is very frustrating. I have downloaded around 15 times, and for almost 2 days. Every time, the connection is broken, or because of the network, it stalled. 

Finally, I downloaded it. And by following the instruction, I convert the model and freeze the model graph. Then I used this model for different pictures as an experiment. So I first tried several of Monet’s paintings. Some of them work pretty well, but some of them have bad results. Then I also tried with some other impressionism artists’ paintings. Finally, I tried with paintings from other artists who are not impressionism.

Continue reading “CycleGAN Documentation”

iML Final Concept Documentation

Name: Yinmiao Li

Concept: Transfer human full body photo to stick figure style pictures.

  1. Reason to choose the topic:
    I have done a lot of sound-related projects in many courses, including this, so I want to try something else other than a sound project.
    I like the German comics Vater und Sohn (Father and Son) all the time. So I would want to do something like this comic style.
    From this book, I think about transfer human to this simplified drawing picture, and then stick figure.

    Also, many projects classify abstract ‘cartoonified’ photos into real objects’ photos. I was trying to do this in a reverse way. 
  2. Related Project: “Cartoonify”, “Scribbling Speech”, “Draw it”
  3. Methods Used: Try with style transfer and CycleGAN with google’s dataset Quick Draw. If the results are bad, changed to image classification and feature extraction. Also, PoseNet for the body movement.
  4. Expectation: Webcam capture or load full body photos, and transfer to stick figure style. If time allowed, connect with a small printer made by Arduino or Raspberry pie, and print the stick figure out. Adding some text comments by machine according to the actions of the stick figure will also be fine, but this part depend on time.

Style Transfer Assignment

Topic: Create a Galaxy

Inspiration: Inspired by One of Memo Akten’s work as below:
With the input video of an eye, it’s output is a Stardust. He mentioned that this is not done by style transfer.
What’s more, I’ve tried to make galaxy like images in Processing before, and it is very troublesome, especially to mimic the foggy and cloudy like texture. I used noise() in Processing for mimicking, but the result is not very good. Here’s an example:
Continue reading “Style Transfer Assignment”