Before reading on, be sure to check out Deep Learning and Machine Learning Killer Tools, Libraries, and Apps and Deep Learning and Machine Learning Guide: Part I.
In Deep Learning and Machine Learning Guide: Part I, we left off at checking out distributed deep learning frameworks. The next step focuses on MXNet. MXNet is getting a major push by Amazon and has just entered Apache as a project in incubation. (Take a look at Awesome MXNet for some great articles and information.)
MXNet will run on many platforms, including on a Raspberry Pi, so give it a try and install MXNet on Raspian. For the RPi, they have a great tutorial on running against images pulled from your RPi camera.
sudo apt-get -y install git cmake build-essential g++-4.8 c++-4.8 liblapack* libblas* libopencv* git clone https://github.com/dmlc/mxnet.git --recursive cd mxnet make cd python sudo python setup.py install curl --header 'Host: data.mxnet.io' --header 'User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:45.0) Gecko/20100101 Firefox/45.0' --header 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' --header 'Accept-Language: en-US,en;q=0.5' --header 'Referer: http://data.mxnet.io/models/imagenet/' --header 'Connection: keep-alive' 'http://data.mxnet.io/models/imagenet/inception-bn.tar.gz' -o 'inception-bn.tar.gz' -L tar -xvzf inception-bn.tar.gz mv Inception_BN-0126.params Inception_BN-0000.params
Check out my modified example for working with RPi, MQTT, and MXNet.
Here are some other MXNet resources:
Spark Summit East just happened in Boston and there are a ton of great talks that have already released their slide decks. I have picked the ones that I think are the most interesting for machine learning, streaming, and deep learning: