Caffe (software)

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search
Original author(s) Yangqing Jia
Developer(s) Berkeley Vision and Learning Center
Stable release
1.0[1] / 18 April 2017; 15 months ago (2017-04-18)
Repository Edit this at Wikidata
Written in C++
Operating system Linux, macOS, Windows[2]
Type Library for deep learning
License BSD[3]

CAFFE (Convolutional Architecture for Fast Feature Embedding) is a deep learning framework, originally developed at UC Berkeley. It is open source, under a BSD license.[4] It is written in C++, with a Python interface.[5]


Yangqing Jia created the caffe project during his PhD at UC Berkeley.[6] Now there are many contributors to the project, and it is hosted at GitHub.[7]


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.[8] Caffe supports GPU- and CPU-based acceleration computational kernel libraries such as NVIDIA cuDNN and Intel MKL.[9][10]


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, a distributed deep learning framework.[11]

In April 2017, Facebook announced Caffe2,[12] which includes new features such as Recurrent Neural Networks. At the end of March 2018, Caffe2 was merged into PyTorch[13].

See also[edit]


External links[edit]