Caffe (software)

Caffe is a deep learning framework, originally developed by Yangqing Jia as part of his PhD at UC Berkley. It is open source, under a BSD license. It is written in C++, with a Python interface.

Yangqing Jia created the caffe project during his PhD at UC Berkeley. Now there are many contributors to the project, and it is hosted at GitHub.

Caffe supports many different types of deep learning architectures geared towards image classification and image segmentation. It supports CNN, RCNN, LSTM and fully connected neural network designs. Caffe supports GPU based accleration using CuDNN of Nvidia

Caffe is being used in academic research projects, startup prototypes, and even large-scale industrial applications in vision, speech, and multimedia. Yahoo! has also integrated caffe with Apache Spark to create caffeonspark that integrates caffe framework with Apache Spark for distributed deep learning.

In April 2017, Facebook announced Caffe2, which includes new features such as Recurrent Neural Networks.