search

jetpacapp / DeepBeliefSDK

The SDK for Jetpac's iOS Deep Belief image recognition framework
Other
2.86k stars 437 forks source link

Support for Raspberry Pi 2 and 3 #74

Open Terminus-IMRC opened 7 years ago

Terminus-IMRC commented 7 years ago

Hi. This pull request is for supporting Raspberry Pi 2 and 3. Here are the changes:

Please merge these changes to your repo. Thanks.

Terminus-IMRC commented 7 years ago

Along with this, please update README.md, RaspberryPiLibrary/libjpcnn.so and so on.

guysoft commented 5 years ago

Hey, why was this not merged still? just got stuck?

Terminus-IMRC commented 5 years ago

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 :-)

guysoft commented 5 years ago

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)

Terminus-IMRC commented 5 years ago

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

guysoft commented 5 years ago

@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.

Terminus-IMRC commented 5 years ago

I see. In addition to py-videocore, QMKL is a good open-source example if you want to make something faster by using QPU.