Hi, devs!
I have been studying and working on Machine Learning for last 3 years.
I usually check out last ML/Deep Learning papers and try to develop Google Colab Notebooks to reproduce and play with their projects because many of them are awesome and fun!
Below, I will do a list o some of last Notebooks I created. All of them allow you to interact with the pretrained models they offer:
1) 3D Ken Burns
- TL;DR Use my Notebook to upload a picture an create a 3D effect over it!
This is a reference implementation of 3D Ken Burns Effect from a Single Image using PyTorch. Given a single input image, it animates this still image with a virtual camera scan and zoom subject to motion parallax. Should you be making use of our work, please cite our paper.
- Colab Notebook:
- Repo
2) Learning to Paint
- TL;DR Use my Notebook to upload a picture and create a video with the painting process and the final result
Arxiv | YouTube
We show how to teach machines to paint like human painters, who can use a small number of strokes to create fantastic paintings. By employing a neural renderer in model-based Deep Reinforcement Learning (DRL), our agents learn to determinethe position and color of each stroke and make long-term plans to decompose texture-rich images into strokes.
- Colab Notebook:
- Repo
3) TwinGAN
- TL;DR Use my Notebook to upload a selfie and get a picture with your Anime and/or cat avatar.
Unsupervised Image Translation for Human Portraits.
We provide two pre-trained models: human to anime and human to cats.
- Colab Notebook:
- Repo
4) GPT-2 from Colab with Javascript interface
- TL;DR Use the famous GPT-2 (even the most powerful model of 1.5B params) to generate or complete your text.
Colab Notebook:
Top comments (3)
Manuel, hi. Thanks for this post, I am happy to see someone playing around with machine learning. Can't believe I missed it. I have been playing with StyleGAN occasionally but mostly GPT-2 a lot. Training it on my own systems and on Colab. Your Colab notebook for GPT-2 came in handy, my old Notebook stopped working because of some tensorflow.contrib not being available. I had created a notebook that would write all its output to my API endpoint. I use an Anaconda3 environment to deploy and talk to Python with Node and usually that works but there are a few things concerning GPT-2 that I haven't fully figured out or have no optimal way of doing yet. I am pretty much trying to reproduce the functionality of textsynth.org/ on my server and that webpage happens to be identical to the output of your Notebook so you must know a thing or two about it. :P
You seem passionate, (it is not just business or work) so if you have the time and interest for it I would really like to have a short dialog with you and consult you with a few questions. I can not PM you here on dev.to yet because you don't follow me yet but any platform is fine. Thanks.
Wow, the ai is awesome already, I cannot wait to see where it will go.
I will provide more Notebooks with new projects if people like it :)