will-wow

My company tried doing a VR standup in here last year. It was impressive that it worked at all - some people were on desktop, some on mobile, some in headsets. But while it was kind of a fun bonding event to see everyone walking around and chatting, it also took 3x as long as a zoom standup since people kept losing audio, dropping out, etc. We went back to zoom the next day.

Hah well good to know ;-)

Maybe it’s for the best, I suppose that if I looked like I was online when I wasn't, then someone might be annoyed that I wasn’t responding to them!

When the scheduled message goes through, does that change your slack status to "active"? I wonder if people would think it was weird to see me looking like I was sending messages while offline.

Oh cool! Was it also a mask detector, and if so did you find a pre-trained model for it?

Yeah! AutoML lets you export a TensorFlow.js version of the model to Google cloud storage, and there's a frontend library, tfjs-automl (https://github.com/tensorflow/tfjs/tree/master/tfjs-automl), that downloads the model and sets it up for detections.

Then I'm connecting to the device's webcam with navigator.mediaDevices.getUserMedia, and twice a second send a reference to the video stream object to the detector, which runs inferences locally and returns the coordinates of any detected objects.

There's some glue code to do the whole dance to connect to the camera and model, but after that it works pretty seamlessly, on my desktop and mobile browsers

I used Google's AutoML Vision service (https://cloud.google.com/vision) to train the model off of pictures of masked and unmasked faces from coworkers and creative commons images from Flickr, and am running the model in-brower in a React app. It was pretty cool to see how easy it was to set up an object detection model without having to figure out how to set it up with Keras or something.