The Convolution Architecture for Feature Extration (Caffe) framework from UC Berkeley is designed to let researchers create and explore CNNs and other Deep Neural Networks (DNNs) easily, while delivering high speed needed for both experiments and industrial deployment. Caffe provides state-of-the-art modeling for advancing and deploying deep learning in research and industry with support for a wide variety of architectures and efficient implementations of prediction and learning.

Caffe supports cuDNN v5 for GPU acceleration.

Supported interfaces: C, C++, Python, MATLAB, Command line interface


Caffe is an open framework, models, and worked examples for deep learning. It features:

  • 1,000+ citations, 150+ contributors, 9,000 stars, 5000+ forks, >1 pull request / day average
  • Pure C++/CUDA architecture for deep learning
  • Command line, Python, MATLAB interfaces
  • Fast, well-tested code
  • Tools, reference models, demos, and receips
  • Seamless switch between CPU and GPU

    Expressive architecture encourages application and innovation. Models and optimization are defined by configuration without hard-coding. Switch between CPU and GPU by setting a single flag to train on a GPU machine then deploy to commodity clusters or mobile devices.

    Extensible code fosters active development. In Caffe’s first year, it has been forked by over 1,000 developers and had many significant changes contributed back. Thanks to these contributors the framework tracks the state-of-the-art in both code and models.

    Speed makes Caffe perfect for research experiments and industry deployment. Caffe can process over 60M images per day with a single NVIDIA K40 GPU. That’s 1 ms/image for inference and 4 ms/image for learning. We believe that Caffe is the fastest convnet implementation available.

    Community: Caffe already powers academic research projects, startup prototypes, and even large-scale industrial applications in vision, speech, and multimedia.


Exxact Deep Learning GPU Solutions are powered by the leading hardware, software, and system engineering. With pre-installed Caffe, as well as other leading deep machine learning software packages, Exxact Deep Learning GPU Solutions are fully turn-key and designed for rapid development and deployment of optimized deep neural networks with multiple GPUs.


Image Recognition
One of the hallmark tasks of computer vision, allowing definition of a context for object recognition.

Visual Style Recognition
Predicting style of images by performing a thorough evaluation of different image features.

Object Detection
The process of finding instances of real-world objects such as faces, bicycles, and buildings in images or videos.

Pixelwise Prediction
Learning to make dense predictions for per-pixel tasks like semnatic segmentation.