Caffe (software)
Caffe (Convolutional Architecture for Fast Feature Embedding) is
a deep learning framework, originally developed at University of
Caffe
California, Berkeley. It is open source, under a BSD license.[4] It is Original author(s) Yangqing Jia
written in C++, with a Python interface.[5] Developer(s) Berkeley Vision
and Learning
History Center
Stable release 1.0[1] / 18 April
Yangqing Jia created the Caffe project during his PhD at UC 2017
Berkeley.[6] It is currently hosted on GitHub.[7]
Repository github.com
/BVLC/caffe (ht
Features tps://github.co
m/BVLC/caffe)
Caffe supports many different types of deep learning architectures
geared towards image classification and image segmentation. It Written in C++
supports CNN, RCNN, LSTM and fully-connected neural Operating system Linux, macOS,
network designs.[8] Caffe supports GPU- and CPU-based Windows[2]
acceleration computational kernel libraries such as Nvidia cuDNN
Type Library for
and Intel MKL.[9][10]
deep learning
License BSD[3]
Applications
Website caffe
Caffe is being used in academic research projects, startup .berkeleyvision
prototypes, and even large-scale industrial applications in vision, .org (https://caf
speech, and multimedia. Yahoo! has also integrated Caffe with fe.berkeleyvisi
Apache Spark to create CaffeOnSpark, a distributed deep learning on.org/)
framework.[11]
Caffe2
In April 2017, Facebook announced Caffe2,[12] which included new features such as recurrent neural
network (RNN). At the end of March 2018, Caffe2 was merged into PyTorch.[13]
See also
Comparison of deep learning software
References
1. "BVLC/caffe" (https://github.com/BVLC/caffe). GitHub. 31 March 2020.
2. "Microsoft/caffe" (https://github.com/Microsoft/caffe). GitHub. 30 March 2020.
3. "caffe/LICENSE at master" (https://github.com/BVLC/caffe/blob/master/LICENSE). GitHub.
31 March 2020.
4. "BVLC/caffe" (https://github.com/BVLC/caffe/). GitHub. 31 March 2020.
5. "Comparing Frameworks: Deeplearning4j, Torch, Theano, TensorFlow, Caffe, Paddle,
MxNet, Keras & CNTK" (https://web.archive.org/web/20170329233123/https://deeplearning4
j.org/compare-dl4j-torch7-pylearn#caffe). Archived from the original (https://deeplearning4j.or
g/compare-dl4j-torch7-pylearn#caffe) on 2017-03-29. Retrieved 2017-03-29.
6. "The Caffe Deep Learning Framework: An Interview with the Core Developers" (http://www.e
mbedded-vision.com/industry-analysis/technical-articles/caffe-deep-learning-framework-inte
rview-core-developers). Embedded Vision. 17 January 2016.
7. "Caffe: a fast open framework for deep learning" (https://github.com/BVLC/caffe). GitHub. 31
March 2020.
8. "Caffe tutorial - vision.princeton.edu" (https://web.archive.org/web/20170405073658/https://v
ision.princeton.edu/courses/COS598/2015sp/slides/Caffe/caffe_tutorial.pdf) (PDF). Archived
from the original (https://vision.princeton.edu/courses/COS598/2015sp/slides/Caffe/caffe_tut
orial.pdf) (PDF) on April 5, 2017.
9. "Deep Learning for Computer Vision with Caffe and cuDNN" (https://devblogs.nvidia.com/de
ep-learning-computer-vision-caffe-cudnn/). NVIDIA Developer Blog. October 16, 2014.
10. "mkl_alternate.hpp" (https://github.com/BVLC/caffe/blob/3d5bed06a9b6b8a5dfd3db8da33f2f
a3bc9a1213/include/caffe/util/mkl_alternate.hpp). BVLC Caffe. Retrieved 2018-04-11.
11. "Yahoo enters artificial intelligence race with CaffeOnSpark" (https://jaxenter.com/yahoo-ent
ers-artificial-intelligence-race-with-caffeonspark-124324.html). February 29, 2016.
12. Team, Caffe2 (April 18, 2017). "Caffe2 Open Source Brings Cross Platform Machine
Learning Tools to Developers" (http://caffe2.ai/blog/2017/04/18/caffe2-open-source-announc
ement.html). Caffe2.
13. "Caffe2 Merges With PyTorch" (https://medium.com/@Synced/caffe2-merges-with-pytorch-a
89c70ad9eb7). Medium. May 16, 2018.
External links
Official website (https://caffe.berkeleyvision.org/)
Retrieved from "https://en.wikipedia.org/w/index.php?title=Caffe_(software)&oldid=1140918874"
