Profile cover photo
Profile photo
Mimi Sun
I code for fun and profit.
I code for fun and profit.

Mimi's posts

Post has shared content
Can you tell a husky and a malamute apart? The new Inception model can.
On the heels of yesterday's release of TF-Slim ( ) comes the release of Inception-ResNet-v2, a convolutional neural network (CNN) that achieves a new state of the art in terms of accuracy on the ILSVRC image classification benchmark.

Learn more in the blog post below, and in the paper Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (

Post has shared content
Amazing portraits

Post has shared content
<3 this enchanted doodle.
Today's #GoogleDoodle celebrates our beautiful planet with illustrations inspired by its five biomes. Happy Earth Day!
Animated Photo

Post has shared content
Wonderful implementation by #Sony's #FutureLab making a humble book #interactive, in this case for Alice In Wonderland. Really brings it to life. Projection mapping is really hot these days! Future of reading?

Post has shared content
Not sure why Mozilla and Firefox would be carrying a Microsoft flag. Love the arm extensions :D
Yep, that's exactly what it looks like. A feline standard-bearer for Microsoft riding a T-Rex holding weird grabber thingies. Obviously.

(Thanks for the fun gift, +Bilal Mahmood​!)

Post has shared content
All the photos here are super cute: 
I want a cheetah friend too...

Post has shared content
Many interesting projects here:
We want to see what you’re building! Submit any tech project you’re working on to the IEEE DIY Project for a chance to win a gift card worth up to $500.

This week, IEEE Fellow John Cohn shares his thoughts on the Bluetooth Switch submitted by Kaustav Nandy. For your chance to be featured in our next video, submit your project now!

Post has shared content
Open Source Release of TensorFlow

I'm very excited to announce the open source release of the TensorFlow machine learning library that I and many others at Google have been building.

This blog post gives an overview:

The web site has a number of tutorials and documentation about the system:

The source is on GitHub:

You might also be interested in the whitepaper we've prepared that describes TensorFlow in more detail:

We'd love to hear what people think.

Post has shared content
Today we've announced the Google Brain Residency Program, a one year program for people with computer science background who are interested in Deep Learning to join us at Google, study machine learning and conduct research with our team.
Details, timeline and application process:

Post has attachment
Wait while more posts are being loaded