Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

small changes to front page #8

Merged
merged 1 commit into from
Dec 5, 2013
Merged

small changes to front page #8

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 3 additions & 4 deletions _layouts/default.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
<div class="wrapper">
<header>
<h1 class="header"><a href="index.html">Caffe</a></h1>
<p class="header">Convolutional Architecture for Feature Embedding</p>
<p class="header">Convolutional Architecture for Fast Feature Embedding</p>

<ul>
<!--<li class="download"><a class="buttons" href="https://github.com/Yangqing/caffe/zipball/master">Download ZIP</a></li>
Expand All @@ -30,13 +30,12 @@ <h1 class="header"><a href="index.html">Caffe</a></h1>
<section>

{{ content }}

</section>
<footer>
<p><small>Hosted on <a href="http://pages.github.com">GitHub Pages</a> using the Dinky theme</small></p>
<p><small>Hosted on <a href="http://pages.github.com">GitHub Pages</a>.</small></p>
</footer>
</div>
<!--[if !IE]><script>fixScale(document);</script><![endif]-->

</body>
</html>
40 changes: 24 additions & 16 deletions index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you remove this line? The CPU code is actually faster (something around 20ms with C++ and batch mode), but I haven't extensively benchmarked it. It would be safer to not mention it right now :)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it's important to advertise the fact that this is totally useable
without a GPU though. 200 ms is accurate from unopened file to predictions,
right? We can say (on an image already loaded into memory, Caffe takes only
20 ms). We can always change the numbers as we get more accurate ones.

On Wed, Dec 4, 2013 at 12:38 PM, Yangqing Jia notifications@github.comwrote:

In index.md:

- -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.

Could you remove this line? The CPU code is actually faster (something
around 20ms with C++ and batch mode), but I haven't extensively benchmarked
it. It would be safer to not mention it right now :)

—
Reply to this email directly or view it on GitHubhttps://github.com/Yangqing/caffe/pull/8/files#r8109227
.


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
Expand All @@ -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.
4 changes: 2 additions & 2 deletions installation.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
-------------
Expand Down Expand Up @@ -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).