Caffe

Openness:3 ★★★
Document quality:3 ★★★

An open-source library for machine learning. Various functions on deep learning based on neural network can be used by this package. This package is especially customised for image identification, and a number of sample codes are prepared. Users can also use pre-trained models, which are open in Caffe Model Zoo. Since this package is written in C++, high-speed operation is realised.

Information

Official site

http://caffe.berkeleyvision.org/

Download

License

BSD 2-Clause license

Availability	Unix/Linux, MacOS, Windows
Core Developers	Berkeley AI Research
Target substance/model	Image identification, voice recognition, natural language processing
Methodology	Machine learning, Deep learning, Neural network
Parallelization	GPGPU parallel computing is supported.
Document	J. Yangqing, et. al., arXiv:1408.5093 (2014)
Other	CUDA, BLAS and Boost are needed. Implemented by C++. An interface for Python and MATLAB is available.