Share to: share facebook share twitter share wa share telegram print page

Caffe (software)

Caffe
Original author(s)Yangqing Jia
Developer(s)Berkeley Vision and Learning Center
Stable release
1.0[1] / 18 April 2017; 7 years ago (2017-04-18)
Repository
Written inC++
Operating systemLinux, macOS, Windows[2]
TypeLibrary for deep learning
LicenseBSD[3]
Websitecaffe.berkeleyvision.org
Part of a series on
Machine learning
and data mining
Paradigms
Problems
Clustering
Dimensionality reduction
Structured prediction
Anomaly detection
Artificial neural network
Reinforcement learning
Learning with humans
Model diagnostics
Mathematical foundations
Journals and conferences
Related articles

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

Yangqing Jia created the Caffe project during his PhD at UC Berkeley, while working the lab of Trevor Darrell.[6] 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.[6] It reached end-of-support in 2018. It is hosted on GitHub.[7]

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

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.[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

References

  1. ^ "BVLC/caffe". GitHub. 31 March 2020.
  2. ^ "Microsoft/caffe". GitHub. 30 March 2020.
  3. ^ "caffe/LICENSE at master". GitHub. 31 March 2020.
  4. ^ "BVLC/caffe". GitHub. 31 March 2020.
  5. ^ "Comparing Frameworks: Deeplearning4j, Torch, Theano, TensorFlow, Caffe, Paddle, MxNet, Keras & CNTK". Archived from the original on 2017-03-29. Retrieved 2017-03-29.
  6. ^ a b "The Caffe Deep Learning Framework: An Interview with the Core Developers". Embedded Vision. 17 January 2016.
  7. ^ "Caffe: a fast open framework for deep learning". GitHub. 31 March 2020.
  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". NVIDIA Developer Blog. October 16, 2014.
  10. ^ "mkl_alternate.hpp". BVLC Caffe. Retrieved 2018-04-11.
  11. ^ "Yahoo enters artificial intelligence race with CaffeOnSpark". February 29, 2016.
  12. ^ Team, Caffe2 (April 18, 2017). "Caffe2 Open Source Brings Cross Platform Machine Learning Tools to Developers". Caffe2.{{cite web}}: CS1 maint: numeric names: authors list (link)
  13. ^ "Caffe2 Merges With PyTorch". Medium. May 16, 2018.
Kembali kehalaman sebelumnya