Smarter Phones In Your Hacks With TensorFlow Lite

November 23, 2017 by Steven Dufresne 11 Comments

One way to run a compute-intensive neural network on a hack has been to put a decent laptop onboard. But wouldn’t it be great if you could go smaller and cheaper by using a phone instead? If your neural network was written using Google’s TensorFlow framework then you’ve had the option of using TensorFlow Mobile, but it doesn’t use any of the phone’s accelerated hardware, and so it might not have been fast enough.

Google has just released a new solution, the developer preview of TensofFlow Lite for iOS and Android and announced plans to support Raspberry Pi 3. On Android, the bottom layer is the Android Neural Networks API which makes use of the phone’s DSP, GPU and/or any other specialized hardware to speed up computations. Failing that, it falls back on the CPU.

Currently, fewer operators are supported than with TensforFlor Mobile, but more will be added. (Most of what you do in TensorFlow is done through operators, or ops. See our introduction to TensorFlow article if you need a refresher on how TensorFlow works.) The Lite version is intended to be the successor to Mobile. As with Mobile, you’d only do inference on the device. That means you’d train the neural network elsewhere, perhaps on a GPU-rich desktop or on a GPU farm over the network, and then make use of the trained network on your device.

What are we envisioning here? How about replacing the MacBook Pro on the self-driving RC cars we’ve talked about with a much smaller, lighter and less power-hungry Android phone? The phone even has a camera and an IMU built-in, though you’d need a way to talk to the rest of the hardware in lieu of GPIO.

You can try out TensorFlow Lite fairly easily by going to their GitHub and downloading a pre-built binary. We suspect that’s what was done to produce the first of the demonstration videos below.

Continue reading “Smarter Phones In Your Hacks With TensorFlow Lite” →

Learn About Blockchains By Building One

November 23, 2017 by Jenny List 27 Comments

What do we curious Hackaday scribes do when we want to learn about something? First port of call: search the web.

When that something is blockchain technology and we’re looking for an explanation that expands our cursory overview into a more fundamental understanding of the basic principles, there is a problem. It seems that to most people blockchains equate to one thing: cryptocurrencies, and since cryptocurrencies mean MONEY, they then descend into a cultish frenzy surrounded by a little cloud of flying dollar signs. Finding [Daniel van Flymen]’s explanation of the fundamentals of a blockchain in terms of the creation of a simple example chain using Python was thus a breath of fresh air, and provided the required education. Even if he does start the piece by assuming that the reader is yet another cryptocurrency wonk.

We start by creating a simple class to hold all the Python functions, then we are shown a single block. In his example it’s a JSON object, and it contains the payload in the form of a transaction record along with the required proof-of-work and hash. We’re then taken through a very simple proof-of-work algorithm, before being shown how the whole can be implemented as very simple endpoints.

You are not going to launch a cryptocurrency using this code, and indeed that wasn’t our purpose in seeking it out. But if you are curious about the mechanics of a blockchain and are equally tired of evangelists of The Blockchain who claim it will cure all ills but can’t explain it in layman’s terms, then this relatively simple example is for you.

The wrong way to build a blockchain image: Jenny List. #FarmLife.