Human portrait drawing powered by AI (U^2-Net)

https://github.com/NathanUA/U-2-Net

Using the recently released U²-Net trained model, it is possible to create human portrait drawing from human photo!

In this article, I will explain how to use U²-Net on Google Colaboratory. If you don’t have any knowledge of machine learning, don’t worry. I have prepared a notebook for you to experience wonderful experience of AI. To use it, you just need to follow a few steps!

  1. Visit https://colab.research.google.com/notebooks/welcome.ipynb.

2. Open notebook (File > Open notebook)

  • Select “GitHub” tab
  • Input first editbox(Enter a GitHub URL or…) to “adakoda”
  • Select “Repository” to “adakoda/U-2-Net”
  • Select notebook to “notebook/U_2_Net_demo.ipynb” and select (click line) it

3. Run all (Runtime > Run all)

  • Select “RUN ANYWAY”

The complete code for the notebook can be found in the following repository.

Enjoy!

--

--

--

I love programming.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

The Goal of AI (a thought experiment)

Machine Learning for Power Traders

The powers and perils of AI in transforming human society and public health

Parashift announces US market expansion

The psychology of travel decisions. What does the “Top Destination” mean for me?

Data Poisoning is a Threat to National Security

AI, Data Protection and Blockchain

What I Learned From Attending REWORK Deep Learning Summit 2021

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
adakoda

adakoda

I love programming.

More from Medium

Summary: Class-incremental Learning via Deep Model Consolidation

Neural Image Style Transfer

Observing behavior of tokens in Visual Transformers

Speech to Text Processing using Deep Learning Models