SOURCE CODE: http://github.com/schollz/rpi_ai
Sorry for the vertical window….I forgot about that when I was recording.
Everything written on Debian linux with Python and a little bit of bash (for recording)
Music database: Youtube api
Knowledge: WolframAlpha api, Wikipedia api
Personality: Chatterbot api (CleverBot)
STT/TTS: Google api
Recording initialization: Pyaudio checks mean RMS
Facebook’s Caffe2 AI tools reach out to iPhone, Android, and Raspberry Pi
Your mobile may soon have the possibility to know objects in pictures with no need of accessing the cloud
New intelligence can be included in cellular phones for example, the iPhone, Android OS devices, and low-power computer systems such as Raspberry Pi with Facebook’s new open-source Caffe2 deep-learning framework.
Caffe2 can be used to program artificial intelligence features into smartphones and tablets, permitting them to acknowledge images, video clip, text, and speech and be more situationally aware.
You ought to be aware that Caffe2 isn’t an AI program, but a tool allowing for AI to be programmed into smart phones. It does take only a couple of lines of code to write learning models, which could then be incorporated into applications.
The launch of Caffe2 is extremely important. It signifies users will be ready to get image identification, natural language processing, and computer vision right on their mobile. That process is commonly offloaded to remote servers in the cloud, with smart phones then connecting to it.
Mobile devices are having more and more artificial intelligence features. More devices are being included with Amazon’s Alexa and Google Assistant, while Apple’s Siri has been a staple in the iPhone for many years. Samsung’s Galaxy S8 smart phones are going to get the Bixby voice assistant, that ought to make using the mobile phones significantly easier.
Caffe2 can work within the power constraints of mobile devices. It works with mobile hardware to hasten AI apps and create neural networks.
Caffe2 takes advantage of the computing power of latest mobile hardware to increase the speed of deep-learning jobs. For instance, in smart phones, Caffe2 will utilize the computing power of Adreno GPUs and Hexagon DSPs on Qualcomm’s Snapdragon mobile SoC.