Skip to content

Commit

Permalink
removing notebooks in docs, updating instructions
Browse files Browse the repository at this point in the history
  • Loading branch information
sergeyk committed Mar 18, 2014
1 parent bc37a0f commit 34e04cf
Show file tree
Hide file tree
Showing 64 changed files with 312 additions and 1,238 deletions.
3 changes: 2 additions & 1 deletion .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -55,4 +55,5 @@ data/*
examples/*

# Don't version the generated documentation
docs/_site
docs/_site
_site
16 changes: 16 additions & 0 deletions docs/getting_pretrained_models.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
---
layout: default
---

# Pre-trained models

[BVLC](http://bvlc.eecs.berkeley.edu) aims to provide a variety of high quality pre-trained models.
Note that unlike Caffe itself, these models are licensed for **academic research / non-commercial use only**.
If you have any questions, please get in touch with us.

This page will be updated as more models become available.

### ImageNet
The AlexNet model trained on ILSVRC-2010 can be downloaded (232.57MB) by running `models/get_caffe_reference_imagenet_model.sh` from the Caffe root directory.

Additionally, you will probably eventually need some auxiliary data (mean image, synset list, etc.): run `data/ilsvrc12/get_ilsvrc_aux.sh` from the root directory to obtain it.
477 changes: 0 additions & 477 deletions docs/imagenet_detection.md

This file was deleted.

125 changes: 0 additions & 125 deletions docs/imagenet_pretrained.md

This file was deleted.

This file was deleted.

This file was deleted.

Binary file not shown.

This file was deleted.

This file was deleted.

This file was deleted.

This file was deleted.

Binary file not shown.

This file was deleted.

This file was deleted.

Binary file removed docs/images/arrow-down.png
Binary file not shown.
Binary file removed docs/images/octocat-small.png
Binary file not shown.
54 changes: 26 additions & 28 deletions docs/index.md
Original file line number Diff line number Diff line change
@@ -1,48 +1,47 @@
---
layout: default
title: Caffe
---

Welcome to Caffe
================
# Welcome to Caffe

Caffe is a framework for convolutional neural network algorithms, developed with speed in mind.
It was created by [Yangqing Jia](http://www.eecs.berkeley.edu/~jiayq/) as a replacement of [decaf](http://decaf.berkeleyvision.org/), Yangqing's earlier Python implementation of CNNs.
It is maintained by the [Berkeley Vision and Learning Center](http://bvlc.eecs.berkeley.edu) and several Berkeley vision group members are actively contributing to the codebase.

Caffe is released under [the BSD 2-Clause license](license.html).
It was created by [Yangqing Jia](http://daggerfs.com), and is in active development by the [Berkeley Vision and Learning Center](http://bvlc.eecs.berkeley.edu).
Caffe is released under [the BSD 2-Clause license](https://github.com/BVLC/caffe/blob/master/LICENSE).

Decaf, the big brother of Caffe, has a cool [demo](http://decaf.berkeleyvision.org). Caffe's own demo will come soon.
<!-- BVLC hosts a quick [classification demo](http://demo.caffe.berkeleyvision.org/) using Caffe. -->

Why Caffe?
----------
## Why Caffe?

Caffe aims to provide computer vision scientists with a **clean, modifiable implementation** of state-of-the-art deep learning algorithms.
Caffe aims to provide computer vision practicioners with a **clean and 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.

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 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 20 ms when images are processed in batch mode.

Quick Links
-----------
## Documentation

* [Introductory slides](/caffe-presentation.pdf): slides about the Caffe architecture, *updated 03/14*.
* [Installation](/installation.html): Instructions on installing Caffe (works on Ubuntu, Red Hat, OS X).
* [Pre-trained models](/getting_pretrained_models.html): BVLC provides some pre-trained models for non-commercial use.
* [Development](/development.html): Guidelines for development and contributing to Caffe.

### Examples

* [LeNet / MNIST Demo](/mnist.html): end-to-end training and testing of LeNet on MNIST.
* [CIFAR-10 Demo](/cifar10.html): training and testing on the CIFAR-10 data.
* [Training ImageNet](/imagenet_training.html): end-to-end training of an ImageNet classifier.
* [Running Pretrained ImageNet \[notebook\]][pretrained_imagenet]: run classification with the pretrained ImageNet model using the Python interface.
* [Running Detection \[notebook\]][imagenet_detection]: run a pretrained model as a detector.
* [Visualizing Features and Filters \[notebook\]][visualizing_filters]: trained filters and an example image, viewed layer-by-layer.

* [Presentation](caffe-presentation.pdf): The Caffe presentation, *updated 03/14*.
* [Installation](installation.html): Instructions on installing Caffe (tested on Ubuntu 12.04, but works on Red Hat, OS X, etc.).
* [Development](development.html): Guidelines for development and contributing to Caffe.
* [LeNet / MNIST Demo](mnist.html): example of end-to-end training and testing of LeNet on MNIST.
* [CIFAR-10 Demo](cifar10.html): example of training and testing on the CIFAR-10 data.
* [Training ImageNet](imagenet_training.html): tutorial on end-to-end training of an ImageNet classifier.
* [Running Pretrained ImageNet](imagenet_pretrained.html): simply runs in Python!
* [Running Detection](imagenet_detection.html): run a pretrained model as a detector.
* [Visualizing Features and Filters](lena_imagenet.html): Lena viewed layer-by-layer.
[pretrained_imagenet]: http://nbviewer.ipython.org/github/BVLC/caffe/blob/master/examples/imagenet_pretrained.ipynb
[imagenet_detection]: http://nbviewer.ipython.org/github/BVLC/caffe/blob/master/examples/selective_search_demo.ipynb
[visualizing_filters]: http://nbviewer.ipython.org/github/BVLC/caffe/blob/master/examples/filter_visualization.ipynb

## Citing Caffe

Citing Caffe
------------
Please kindly cite Caffe in your publications if it helps your research:

@misc{Jia13caffe,
Expand All @@ -54,12 +53,11 @@ Please kindly cite Caffe in your publications if it helps your research:

### Acknowledgements

Yangqing would like to thank the NVidia Academic program for providing a K20 GPU.
Yangqing would like to thank the NVidia Academic program for providing K20 GPUs.
The Caffe Matlab wrapper is courtesy of [Dr. Ross Girshick](http://www.cs.berkeley.edu/~rbg/).
The detection module (`power_wrapper`) is courtesy of [Sergey Karayev](http://sergeykarayev.com/).
Our thanks also go to [Jeff Donahue](http://jeffdonahue.com/) and [Oriol Vinyals](http://www1.icsi.berkeley.edu/~vinyals/) for various discussions along the journey.

---

\*: 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.
Loading

0 comments on commit 34e04cf

Please sign in to comment.