Powered by Mediapipe, TensorFlow, and Jeeliz.

Emily Xie:

Urban legend says that Mona Lisa’s eyes will follow you as you move around the room. This is known as the “Mona Lisa effect.” For fun, I recently programmed an interactive digital portrait that brings this phenomenon to life through your browser and webcam.

Craig Wiley, from Google Cloud, joins us to discuss various pieces of the TensorFlow ecosystem along with TensorFlow Enterprise. He sheds light on how enterprises are utilizing AI and supporting AI-driven applications in the Cloud. He also clarifies Google’s relationship to TensorFlow and explains how TensorFlow development is impacting Google Cloud Platform.

This code attempts to learn over time the makeup of the background of a video such that I can attempt to remove any humans from the scene. This is all happening in real time, in the browser, using TensorFlow.js

Impressive results for an experiment. Try the live demo on Codepen and/or Glitch.

Style-based GAN architecture produces impressive image generation results, but it’s not without its limitations. NVidia’s research team has been hard at work fixing some of the problems with StyleGAN (artifacts).

In addition to improving image quality, this path length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it possible to reliably detect if an image is generated by a particular network.

Check out the video of StyleGAN2 in action or, if you’re feeling brazen, dive right into their paper.

We’ve mentioned ML/AI in the browser and in JS a bunch on this show, but we haven’t done a deep dive on the subject… until now! Victor Dibia helps us understand why people are interested in porting models to the browser and how people are using the functionality. We discuss TensorFlow.js and some applications built using TensorFlow.js

Folks have been talking about TensorFlow 2 for some time now (See Practical AI #42 for one excellent example), but now it’s finally here. The bulleted list:

• Easy model building with Keras and eager execution.
• Robust model deployment in production on any platform.
• Powerful experimentation for research.
• API simplification by reducing duplication and removing deprecated endpoints.

This is a huge release. Check out the highlights list in the changelog to see for yourself.

This week Daniel and Chris discuss the announcements made recently at TensorFlow Dev Summit 2019. They kick it off with the alpha release of TensorFlow 2.0, which features eager execution and an improved user experience through Keras, which has been integrated into TensorFlow itself. They round out the list with TensorFlow Datasets, TensorFlow Addons, TensorFlow Extended (TFX), and the upcoming inaugural O’Reilly TensorFlow World conference.

CV Compiler is an online resume analysis tool designed exclusively for software engineers.

The review technology scans for keywords from the world of programming and how they are used in the resume, relative to the best practices in the industry.

CV Compiler was built using Python with libraries NLTK and spaCy for tokenization, lemmatization, and POS-tagging.

The internal analysis engine for large datasets (resumes, job descriptions) was built upon a Seq2Seq model in TensorFlow.

Finish him!

Chris and Daniel are back together in another news/updates show. They discuss PyTorch v1.0, some disturbing uses of AI for tracking social credit, and learning resources to get you started with machine learning.

The strong advantage of TensorFlow is it flexibility in designing highly modular models which can also be a disadvantage for beginners since a lot of the pieces must be considered together when creating the model.

If you’re interested in TensorFlow, but haven’t dove in yet for one reason or another, this might be a good place to start.

Abhishek Singh isn’t deaf or mute, but that didn’t stop him from asking the question:

If voice is the future of computing interfaces, what about those who cannot hear or speak?

This thought led to a super cool project wherein a computer interprets sign language and speaks the results to a nearby Alexa device. Live demo here and code here.

Amanda Ramcharan, Latifa Mrisho, and Peter McCloskey joined Daniel and Chris to talk about how Penn State University are collaborating to help African farmers increase their yields via a TensorFlow powered mobile app.

A reimplementation of TensorFlow for Ruby. This is a ground up implementation with no dependency on TensorFlow. Effort has been made to make the programming style as near to TensorFlow as possible, comes with a pure Ruby evaluator by default with support for an opencl evaluator for large models and datasets.

a pure Python implementation of a neural-network based Go AI, using TensorFlow

This is not trying to be the top Go AI program. They want to build a readable, understandable implementation that can benefit the community.