We will explore running object detection on-device with HoloLens, using Unity game engine as our development platform. AR Academy is a great introduction to all aspects of HoloLens development. It has 300-level tutorials that demonstrate how to connect the device to Azure Cognitive Services to perform machine learning tasks. There are no samples of performing … Continue reading HoloLens Object Detection →

I’m writing a series of posts on supercharging object detection inference performance in video streams using Tensorflow and cool tech from NVIDIA: step-by-step, starting from 6 fps all the way up to 230. But before I start, this small post is about a cool little gem, which I think is often overlooked. Anyone in the … Continue reading On the Margins: Non-maximum Suppression with Tensorflow →

Midnight strikes, I lose the wager, woken by a screeching pager, Scarlet hue means issue’s major, major OOMing on the node. SSH into the victim, tail and grep per playbook’s dictum, ‘Til revealed is cache eviction as what crumbled ‘neath the load. Run a dump of heap and threading, start the steps for shedding load. Who hath merged this wretched code? Bleary eyes see dashboards healing, weary mind’s still looping, reeling, Ired at some dev who’s stealing hours from my restful mode. Fueled by spiteful indig[...]

Seeing the popularity of elmish architecture and attempts at implementations of backends based on it (or any unsupervised cooperative actor loops) I thought I’d share my thoughts. Desirable characteristics Most naive implementations of synchronous (HTTP/RPC) APIs are perfectly content to return some equivalent of 500 code at a drop of a hat. My DB timed […]

So I was bored, didn’t know what to do, started solving problems on codewars (shut up!). There was this little problem there, where they are asking you to compute , for potentially large n’s with precision. It’s easy to see that this needs to be refactored (no need to actually compute factorials), and the solution […]