This morning I found myself summarizing my favorite bits from a talk that I enjoyed at Google Cloud Next in San Francisco, What’s New with TensorFlow? Then I thought about it for a moment and couldn’t see a reason not to share my super-short summary with you (except maybe that you might not watch the video — you totally should check it out, is awesome) so here goes… the speaker I made a video version of this article that’s even shorter, in case you’re in a hurry and/or you prefer information to be injected into your brain via your ears. #1 It’s a powerful machine learning framework TensorFlow is a framework that might be your new best friend if you have a lot of data and/or you’re after the state-of-the-art in AI: . Neural networks. Big ones. It’s not a data science Swiss Army Knife, it’s the … which means you can probably stop reading if all you want to do is put a regression line through 20-by-2 spreadsheet. machine learning deep learning industrial lathe But if big is what you’re after, get excited. TensorFlow has been used to go , prevent blindness by helping doctors , and help save forests by alerting authorities to signs of . It’s what and are built on top of and it’s yours to play with. TensorFlow is open source, you can and immediately. hunting for new planets screen for diabetic retinopathy illegal deforestation activity AlphaGo Google Cloud Vision download it for free get started Discovered with the help of TensorFlow, the planet Kepler-90i makes the Kepler-90 system the only other system we know of that has eight planets in orbit around a single star. No system has been found with more than eight planets, so I guess that means we’re tied with Kepler-90 for first place (for now). Learn more . here #2 The bizarre approach is optional I’m head over heels for . TensorFlow Eager If you tried TensorFlow in the old days and ran away screaming because it forced you to code like an academic/alien instead of like a developer, come baaaack! TensorFlow eager execution lets you interact with it like a pure Python programmer: all the immediacy of writing and debugging line-by-line instead of holding your breath while you build those huge graphs. I’m a recovering academic myself (and quite possibly an alien), but I’ve been in love with TF eager execution since it came out. So eager to please! #3 You can build neural networks line-by-line Keras + TensorFlow = easier neural network construction! is all about user-friendliness and easy prototyping, something old TensorFlow sorely craved more of. If you like object oriented thinking and you like building neural networks one layer at a time, you’ll love . In just the few lines of code below, we’ve created a sequential neural network with the standard bells and whistles like dropout (remind me to wax lyrical about my metaphors for dropout sometime, they involve staplers and the flu). Keras tf.keras Oh, you like puzzles, do you? Patience. Don’t think too much about staplers. #4 It’s not only Python Okay, you’ve been complaining about TensorFlow’s Python monomania for a while now. Good news! TensorFlow is not just for Pythonistas anymore. It now runs in many languages, from R to Swift to JavaScript. #5 You can do everything in the browser Speaking of JavaScript, you can train and execute models in the browser with . Go nerd out on the , I’ll still be here when you get back. TensorFlow.js cool demos Real-time in the browser with TensorFlow.js. Turn on your camera for a demo . Or don’t get out of your chair. ¯\_(ツ)_/¯ Up to you. Human Pose Estimation here #6 There’s a Lite version for tiny devices Got a clunker desktop from a museum? Toaster? (Same thing?) brings model execution to a variety of devices, including mobile and IoT, giving you more than a 3x boost in inference speedup over original TensorFlow. Yes, now you can get machine learning on your Raspberry Pi or your phone. In the , Laurence does a brave thing by live-demoing image classification on an Android emulator in front of thousands... and it works. TensorFlow Lite talk 1.6 seconds to compute? Check! Banana with over 97% probability? Check! Toilet tissue? Well, I’ve been to a few countries where I suppose a sheet of paper like the one Laurence is holding up counts. #7 Specialized hardware just got better If you’re tired of waiting for your CPU to finish churning through your data to train your neural network, you can now get your hands on hardware specially designed for the job with . The T is for tensor. Just like TensorFlow… coincidence? I think not! A few weeks ago, Google announced version 3 TPUs in alpha. Cloud TPUs #8 The new data pipelines are much improved What’s that you’re doing with over there? In case you wanted to do it in TensorFlow but then rage-quit, the now makes your input processing in TensorFlow more expressive and efficient. gives you data pipelines synchronized with training. numpy namespace tf.data tf.data fast, flexible, and easy-to-use #9 You don’t need to start from scratch You know what’s not a fun way to get started with machine learning? A blank new page in your editor and no example code for miles. With TensorFlow Hub, you can engage in a more efficient version of the time-honored tradition of helping yourself to someone else’s code and calling it your own (otherwise known as professional software engineering). is a repository for reusable pre-trained machine learning model components, packaged for one-line reuse. Help yourself! TensorFlow Hub While we’re on the subject of community and not struggling alone, you might like to know that TensorFlow just got an official and . YouTube channel blog Update! As of March 2019, there’s a 10th thing you should know… #10 TensorFlow just got user friendly! Now that we’re done with last year’s news, it’s time for the thing you need to know above all others: is finally here! It’s a radical makeover that’s all about making TF super easy to use. The consequences are going to have major ripple effects on every industry, just you wait. Read my update about it . one TensorFlow 2.0 here That concludes my summary, so the full talk to entertain you for the next 42 minutes. here’s
