|Original author(s)||Yangqing Jia|
|Developer(s)||Berkeley Vision and Learning Center|
1.0 / 18 April 2017
|Operating system||Linux, macOS, Windows|
|Type||Library for deep learning|
|Machine learning and|
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. It is written in C++, with a Python interface.
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. Caffe supports GPU- and CPU-based acceleration computational kernel libraries such as NVIDIA cuDNN and Intel MKL.
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.
- "Release 1.0".
- "Microsoft/caffe". GitHub.
- "caffe/LICENSE at master". GitHub.
- "BVLC/caffe". GitHub.
- "Comparing Frameworks: Deeplearning4j, Torch, Theano, TensorFlow, Caffe, Paddle, MxNet, Keras & CNTK".
- "The Caffe Deep Learning Framework: An Interview with the Core Developers". Embedded Vision.
- "Caffe: a fast open framework for deep learning". GitHub.
- "Caffe tutorial - vision.princeton.edu" (PDF). Archived from the original (PDF) on April 5, 2017.
- "Deep Learning for Computer Vision with Caffe and cuDNN".
- "mkl_alternate.hpp". BVLC Caffe. Retrieved 2018-04-11.
- "Yahoo enters artificial intelligence race with CaffeOnSpark".
- "Caffe2 Open Source Brings Cross Platform Machine Learning Tools to Developers".
- "Caffe2 Merges With PyTorch".