Caffe (software)

{{Short description|Deep learning framework}} {{Infobox software | name = Caffe | logo = | screenshot = | caption = | collapsible = | author = Yangqing Jia | developer = Berkeley Vision and Learning Center | released = | latest release version = 1.0<ref>{{cite web|url=https://github.com/BVLC/caffe|title=BVLC/caffe|website=GitHub|date=31 March 2020}}</ref> | latest release date = {{Start date and age|2017|04|18|df=yes}} | latest preview version = | latest preview date = | programming language = C++ | operating system = Linux, macOS, Windows<ref>{{cite web|url=https://github.com/Microsoft/caffe|title=Microsoft/caffe|work=GitHub|date=30 March 2020}}</ref> | platform = | size = | language = | genre = Library for deep learning | license = BSD<ref>{{cite web|url=https://github.com/BVLC/caffe/blob/master/LICENSE|title=caffe/LICENSE at master|work=GitHub|date=31 March 2020}}</ref> | website = {{URL|https://caffe.berkeleyvision.org/}} }}

'''Caffe''' (Convolutional Architecture for Fast Feature Embedding) is a deep learning framework, originally developed at University of California, Berkeley. It is open source, under a BSD license.<ref>{{cite web|url=https://github.com/BVLC/caffe|title=BVLC/caffe|website=GitHub|date=31 March 2020}}</ref> It is written in C++, with a Python interface.<ref>{{cite web|url=https://deeplearning4j.org/compare-dl4j-torch7-pylearn#caffe|title=Comparing Frameworks: Deeplearning4j, Torch, Theano, TensorFlow, Caffe, Paddle, MxNet, Keras & CNTK|access-date=2017-03-29|archive-url=https://web.archive.org/web/20170329233123/https://deeplearning4j.org/compare-dl4j-torch7-pylearn#caffe|archive-date=2017-03-29|url-status=dead}}</ref>

== History == Yangqing Jia created the Caffe project during his PhD at UC Berkeley, while working the lab of Trevor Darrell.<ref name="history">{{cite web|title=The Caffe Deep Learning Framework: An Interview with the Core Developers|date=17 January 2016|url=http://www.embedded-vision.com/industry-analysis/technical-articles/caffe-deep-learning-framework-interview-core-developers|publisher=Embedded Vision}}</ref> The first version, called "DeCAF", made its first appearance in Spring 2013 when it was used for the ILSVRC challenge (later called ImageNet). The library was named Caffe and released to the public in December 2013.<ref name="history"/> It reached end-of-support in 2018. It is hosted on GitHub.<ref>{{cite web|title=Caffe: a fast open framework for deep learning.|date=31 March 2020|url=https://github.com/BVLC/caffe|publisher=GitHub}}</ref>

== Features == 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.<ref>{{cite web|title=Caffe tutorial - vision.princeton.edu|url=https://vision.princeton.edu/courses/COS598/2015sp/slides/Caffe/caffe_tutorial.pdf|archiveurl=https://web.archive.org/web/20170405073658/https://vision.princeton.edu/courses/COS598/2015sp/slides/Caffe/caffe_tutorial.pdf|archivedate=April 5, 2017}}</ref> Caffe supports GPU- and CPU-based acceleration computational kernel libraries such as Nvidia cuDNN and Intel MKL.<ref>{{Cite web|url=https://devblogs.nvidia.com/deep-learning-computer-vision-caffe-cudnn/|title=Deep Learning for Computer Vision with Caffe and cuDNN|date=October 16, 2014|website=NVIDIA Developer Blog}}</ref><ref>{{Cite web|url=https://github.com/BVLC/caffe/blob/3d5bed06a9b6b8a5dfd3db8da33f2fa3bc9a1213/include/caffe/util/mkl_alternate.hpp|title=mkl_alternate.hpp|website=BVLC Caffe|access-date=2018-04-11}}</ref>

== Applications == 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.<ref>{{Cite web|url=https://jaxenter.com/yahoo-enters-artificial-intelligence-race-with-caffeonspark-124324.html|title=Yahoo enters artificial intelligence race with CaffeOnSpark|date=February 29, 2016}}</ref>

== Caffe2 == In April 2017, Facebook announced Caffe2,<ref>{{Cite web|url=http://caffe2.ai/blog/2017/04/18/caffe2-open-source-announcement.html|title=Caffe2 Open Source Brings Cross Platform Machine Learning Tools to Developers|first=Caffe2|last=Team|date=April 18, 2017|website=Caffe2}}</ref> which included new features such as recurrent neural network (RNN). At the end of March 2018, Caffe2 was merged into PyTorch.<ref>{{Cite web|url=https://medium.com/@Synced/caffe2-merges-with-pytorch-a89c70ad9eb7|title=Caffe2 Merges With PyTorch|date=May 16, 2018|website=Medium}}</ref>

==References== {{Reflist}}

==External links== * {{Official website|https://caffe.berkeleyvision.org/}}

{{DEFAULTSORT:Caffe}} Category:Deep learning software Category:Free science software Category:Free statistical software Category:Image processing Category:Software using the BSD license