From ae9b54a141ac3250dc06bc059ff1f10ce87f900b Mon Sep 17 00:00:00 2001 From: Sergey Karayev Date: Wed, 4 Dec 2013 12:31:58 -0800 Subject: [PATCH] small changes to front page --- _layouts/default.html | 7 +++---- index.md | 40 ++++++++++++++++++++++++---------------- installation.md | 4 ++-- 3 files changed, 29 insertions(+), 22 deletions(-) diff --git a/_layouts/default.html b/_layouts/default.html index 65073a92e3e..4464ee9c20c 100644 --- a/_layouts/default.html +++ b/_layouts/default.html @@ -17,7 +17,7 @@

Caffe

-

Convolutional Architecture for Feature Embedding

+

Convolutional Architecture for Fast Feature Embedding

    - diff --git a/index.md b/index.md index d25cd4c2a39..7a34ec901c1 100644 --- a/index.md +++ b/index.md @@ -6,28 +6,32 @@ title: Caffe Welcome to Caffe ================ -Caffe is a framework for the recent convolutional neural networks algorithms, developed with speed in mind. It is written and maintained by [Yangqing Jia](http://www.eecs.berkeley.edu/~jiayq/) as a replacement of [decaf](http://decaf.berkeleyvision.org/), the python implementation of CNNs. Several [Berkeley vision group](http://ucbvlc.org/) members are actively contributing to the codebase. +Caffe is a framework for convolutional neural network algorithms, developed with speed in mind. +It is written and maintained by [Yangqing Jia](http://www.eecs.berkeley.edu/~jiayq/) as a replacement of [decaf](http://decaf.berkeleyvision.org/), Yangqing's first Python implementation of CNNs. +Several [Berkeley vision group](http://ucbvlc.org/) members are actively contributing to the codebase. Caffe is currently released under [the UC Berkeley non-commercial license](license.html). Why Caffe? ---------- -Caffe aims to expand deep learning research by providing computer vision scientists easier access to state-of-the-art deep learning implementations. At the same time, caffe also aims for fast computation that fits industry needs, with codes in C++/Cuda providing maximum performance through efficient GPU computations. Being able to process more than **20 million images per day**\*, Caffe is currently the fastest GPU CNN implementation publicly available. +Caffe aims to provide computer vision scientists with a **clean, modifiable implementation** of state-of-the-art deep learning algorithms. +For example, network structure is easily specified in separate config files, with no mess of hard-coded parameters in the code. -Caffe also provides **seamless switch between CPU and GPU**, which allows one to train models with fast GPUs, but to still have the flexibility of deploying models on cheaper, non-GPU clusters, with only one line of code necessary: +At the same time, Caffe fits industry needs, with blazing fast C++/Cuda code for GPU computation. +Caffe is currently the fastest GPU CNN implementation publicly available, and is able to process more than **20 million images per day** on a single Tesla K20 machine \*. -``` -Caffe::set_mode(Caffe::CPU); -``` +Caffe also provides **seamless switching between CPU and GPU**, which allows one to train models with fast GPUs and then deploy them on non-GPU clusters with one line of code: `Caffe::set_mode(Caffe::CPU)`. + +Even in CPU mode, computing predictions on an image takes only 200 ms. Quick Links ----------- -* [Presentation](https://docs.google.com/presentation/d/1lzyXMRQFlOYE2Jy0lCNaqltpcCIKuRzKJxQ7vCuPRc8/edit?usp=sharing): Yangqing's presentation on Caffe at the Berkeley vision group meeting. -* [Installation](installation.html): Instructions on installing Caffe, mainly with Ubuntu 12.04LTS. -* [MNIST Demo](mnist.html): end-to-end training and testing on the MNIST data. -* [Training ImageNet](imagenet.html): on how to train an ImageNet classifier. +* [Presentation](https://docs.google.com/presentation/d/1lzyXMRQFlOYE2Jy0lCNaqltpcCIKuRzKJxQ7vCuPRc8/edit?usp=sharing): Presentation on Caffe at the UC Berkeley Vision Group meeting. +* [Installation](installation.html): Instructions on installing Caffe (tested on Ubuntu 12.04, but works on Red Hat, OS X, etc.). +* [MNIST Demo](mnist.html): example of end-to-end training and testing on the MNIST data. +* [Training ImageNet](imagenet.html): tutorial on training an ImageNet classifier. * [Pretrained ImageNet](imagenet_pretrained.html): start running ImageNet classification in minutes. Citing Caffe @@ -36,13 +40,17 @@ Please kindly cite Caffe in your publications if it helps your research: @misc{Jia13caffe, Author = {Yangqing Jia}, - Title = { {Caffe}: An Open Source Convolutional Architecture - for Feature Embedding}, + Title = { {Caffe}: An Open Source Convolutional Architecture for Fast Feature Embedding}, Year = {2013}, - Howpublished = {\url{http://yangqing.github.io/caffe/}} + Howpublished = {\url{http://yangqing.github.io/caffe/} + } + +### Acknowledgements -\* When measured with the [SuperVision](http://www.image-net.org/challenges/LSVRC/2012/supervision.pdf) model that won the ImageNet Large Scale Visual Recognition Challenge 2012, and run on a single machine with Intel i5 processor and Tesla K20. Benchmark details coming soon. +Yangqing would like to thank the NVidia Academic program for providing a K20 GPU. +The Caffe Matlab wrapper is courtesy of [Dr. Ross Girshick](http://www.cs.berkeley.edu/~rbg/). -\*\* Yangqing would like to thank the NVidia Academic program for providing a K20 GPU. +--- -\*\*\* Matlab wrapper courtsy of [Dr Ross Girshick](http://www.cs.berkeley.edu/~rbg/). +\*: When measured with the [SuperVision](http://www.image-net.org/challenges/LSVRC/2012/supervision.pdf) model that won the ImageNet Large Scale Visual Recognition Challenge 2012. +More benchmarks coming soon. diff --git a/installation.md b/installation.md index 78a253e1f3e..471791b6f3d 100644 --- a/installation.md +++ b/installation.md @@ -6,7 +6,7 @@ title: Caffe Installation ================ -Here are some installation notes on various platforms. We have used Ubuntu 12.04 for development, so here describes the step-to-step guide on installing caffe with Ubuntu. You will be able to install Caffe on other platforms but you may need to tinker with paths in `Makefile.config` and maybe `Makefile` a little bit. +We mostly used Ubuntu 12.04 for development, and here we describe the step-to-step guide on installing Caffe on Ubuntu. You will be able to install Caffe on other platforms, but you may need to minimally tinker with paths in `Makefile.config` and maybe the `Makefile` itself. Prerequisites ------------- @@ -42,4 +42,4 @@ Optionally, you can run `make distribute` to create a `build` directory that con To use Caffe with python, you will need to add `/path/to/caffe/python` or `/path/to/caffe/build/python` to your `PYTHONPATH`. -Now that you have compiled Caffe, check out the [MNIST demo](mnist.html) and the pretrained [ImageNet example](imagenet.html). +Now that you have compiled Caffe, check out the [MNIST demo](mnist.html) and the pretrained [ImageNet example](imagenet.html).