Caffe (software)

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search
Caffe
Original author(s)Yangqing Jia
Developer(s)Berkeley Vision and Learning Center
Stable release
1.0[1] / 18 April 2017; 22 months ago (2017-04-18)
Repository Edit this at Wikidata
Written inC++
Operating systemLinux, macOS, Windows[2]
TypeLibrary for deep learning
LicenseBSD[3]
Websitecaffe.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.[4] It is written in C++, with a Python interface.[5]

History[edit]

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]

Features[edit]

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]

Applications[edit]

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]

References[edit]

  1. ^ "Release 1.0".
  2. ^ "Microsoft/caffe". GitHub.
  3. ^ "caffe/LICENSE at master". GitHub.
  4. ^ "BVLC/caffe". GitHub.
  5. ^ "Comparing Frameworks: Deeplearning4j, Torch, Theano, TensorFlow, Caffe, Paddle, MxNet, Keras & CNTK".
  6. ^ "The Caffe Deep Learning Framework: An Interview with the Core Developers". Embedded Vision.
  7. ^ "Caffe: a fast open framework for deep learning". GitHub.
  8. ^ "Caffe tutorial - vision.princeton.edu" (PDF). Archived from the original (PDF) on April 5, 2017.
  9. ^ "Deep Learning for Computer Vision with Caffe and cuDNN".
  10. ^ "mkl_alternate.hpp". BVLC Caffe. Retrieved 2018-04-11.
  11. ^ "Yahoo enters artificial intelligence race with CaffeOnSpark".
  12. ^ "Caffe2 Open Source Brings Cross Platform Machine Learning Tools to Developers".
  13. ^ "Caffe2 Merges With PyTorch".

External links[edit]