Steve Seguin

Results 569 comments of Steve Seguin

If anyone wants to prototype a small snippet of code that demonstrates it, I can pop it into place, Saves me from having to do research and tinkering. otherwise, I...

I've trained to around 40,000 and then to over 100,000 at 256x256; the final result is sorta okay, but it has an odd checkerboard pattern in most results and is...

If i recall, 1000 images of the same person got decent results. I can’t say what the ideal is though, as I was using around 80,000 images in my tests....

I got good results with a custom data set that was properly aligned, decent resolution/sharpness, and about 3 days on a Titan RTX. Mixing faces of different people reduced the...

As per why I never merged it: PHP is an active server component, where as everything else in the repo is passive HTML/Javascript code. I don't think it would be...

What's your interest in the Streamdeck with VDO.Ninja specifically? There's some better options currently, if looking to just do some basic hotkeying. You can check out the Bitfocus Companion app...

Was this ever addressed? As per the OP, I can pass the audio device ID to the getUserMedia constraint, but it seems to ignore it. Tested so far on Windows...

I took a glance at the code, and I have the buffer on the output set to "unlimited". This is probably the issue, and you'll probably want to cap the...

when using the --framebuffer option, which is near identical to fdsink, the latency is quite low: https://youtu.be/LGaruUjb8dg?t=2395 There is a higher latency when I have the queue's buffer large, but...

I've added `--latency 200` as an option; the gstreamer default is 200 (milliseconds), so you can try lowering to 70 to see if that helps you out. There might be...