GOSHtastic - Game shows, Options, Software, & Hardware!

I've had a Sparkfun ESP32 Thing laying around on my desk since back in May when I met the fellow from Iron Transfer at a pinball convention, and we got to talking about IoT and his devices to remotely administrate pinball machines.  However, I spent tons of time this year planning for exhibitions, and didn't really get to do anything with it -- until now. Before You Begin There are a few choices you need to make up-front about which IDE you wish to use for development, plus which development framework.  I have chosen Microsoft's Visual Studio Code since it is cross-platform, feature-rich without hogging resources, free to download, and based on an open-source product similar to how Google Chrome is derived from Chromium.  It comes with extensions for language support and IntelliSense, which are must-haves when authoring code.  You are free to use an IDE of your choice; it won't really hamper your ability to enjoy the rest of this article. The other decision ...

In Francois Chollet’s book Deep Learning with Python , he stresses the importance of utilizing a separate validation set of data while training a machine learning model in order to test periodically (say after every epoch) that the accuracy on something else besides strictly the training data (e.g. this validation set) is in fact improving. Machine learning models are subject to learn relationships that have nothing to do with the problem at hand.   For instance, a model tasked with trying to determine which way a military tank is facing might end up making assumptions based on whether it is day or night.   This is often a result of trying to eke out the model’s maximum performance, say by optimizing for the smallest value of a loss function.   However, what ends up happening is that the model overfits on the training data, which means it loses its generalization — its ability to predict the correct outcome of new samples or examples that we as humans would inten...

Why? Since my last post, I've been highly focused on Tensorflow projects at home and at work.  In the process of running Tensorflow behind an API, I've needed to make code changes to the "secret sauce" (business logic) that stands before Tensorflow and actually provides it with its data.  This could be in the pipeline of multiple Tensorflow models chained together, image manipulation, working with data that gets outputted from the model, or whatever other reasons.  Unfortunately, it is often slow and wastes a bunch of time to constantly restart the whole server (including reinitializing Tensorflow for 20 or 30 seconds), especially when you simply made a typo or used the wrong variable name or something like that. Besides the Tensorflow work, I've been involved in many blog-worthy pursuits since my last post but simply haven't had time to write about them.  (In fact, I meant to write this last week, but forgot.)  Anyway, at the end of June, right before my...

Among all the hype around the latest and greatest technologies, there is so much publicity devoted toward how they are being used in grand schemes to cure cancer, reduce energy waste, conserve water, solve poverty, and so forth.  While all these things are wonderful to humanity, there has to be someone left in the background who helps all the do-gooders unwind when it's time to take a break! The TL/DR Version: Get To the Point! Use clever arguments when loading up your Docker container so you don't have to shut it down and restart it when you want to mount external directories from the host filesystem or expose the port for the Tensorboard server.  There is also nvidia-docker available if you want to use your CUDA cores. sudo nvidia-docker run -it -p 6006:6006 -v ~/Pictures/video-game-training/:/video-game-training gcr.io/tensorflow/tensorflow:latest-devel-gpu bash Use the  --output_user_root  option in your Bazel builds so you can save it to that external ...

(Addendum: Follow along my thought process below with this extra pedagogical material:  https://www.slideshare.net/StephenWylie3/process-of-arcade-rom-hacking  ) An interesting work project, right? I was invited to take my Giant NES Controller to a recruiting event for work taking place at a local brewery.  But you can't just have an NES controller without anything to play, right?  Thus, I pitched a couple ideas on custom games to go along with the giant controller since I didn't want participants playing anything standard either.  The thing they agreed to was to feature the Tapper arcade game, by Bally/Midway in 1983, but modified to show the brewery's logo instead of being Budweiser-branded like it was originally. My handiwork, about 80% done, and with a tiny glitch.  Can you spot the remaining issues? Now you might be thinking Tapper wasn't ever ported to NES, and that's correct.  However, with the help of the MAME arcade emulator and a ...