Open Terminus-IMRC opened 7 years ago
Along with this, please update README.md
, RaspberryPiLibrary/libjpcnn.so
and so on.
Hey, why was this not merged still? just got stuck?
He now works for Google and seems very busy. In addition, there are much faster sgemm implementations which run on Raspberry Pi QPU such as py-videocore, so little motivation to manage this repo IMHO :-)
QPU = GPU? I was looking for a dnn for audio that would run on a raspberrypi GPU. If you have a direction to point me to (real-time speed)
Yes, QPU (quad processing unit) is a GPU implemented on Raspberry Pi.
We, Idein Inc., offer a fast deep learning (inference) library/software. If you're interested, feel free to contact us: https://idein.jp/
Our YouTube channel: https://www.youtube.com/channel/UCp0a6npOi89ksgks3ej7FPw
@Terminus-IMRC thans for the offer, but I am currently looking for a solution that is open source. I am trying to build something people can replicate instantly around the world, a library that requires contact would slow that.
I see. In addition to py-videocore, QMKL is a good open-source example if you want to make something faster by using QPU.
Hi. This pull request is for supporting Raspberry Pi 2 and 3. Here are the changes:
/dev/vcio
./dev/mem
on Raspberry Pi 2 and 3. ThisBUS_TO_PHYS
macro was first seen in https://github.com/raspberrypi/userland/commit/3b81b91c18ff19f97033e146a9f3262ca631f0e9 .Please merge these changes to your repo. Thanks.