Favourite Code

In gerneral I use Python with Numpy/Scipy/Matplotlib for most of my experiments, so most of these are python tools.

Here are some projects I find helpful:

Computer Vision:

Scikits-Image:
Python library for image processing. Contains many elementary methods and algorithms and some descriptors. A fast growing project that is worth a look.
 
VlFeat:
This library contains very fast SIFT computation, Kmeans, QuickShift, MSER and other tools. Very fast, very easy to use. Matlab, C++ and binaries.

There is also a github clone which provides Python bindings for some of the functionality and my updated Python bindings.

Damascene
A CUDA implementation of the gPb operator by Malik .
This includes an implementation of textons and also normalized cuts on GPU. I have Python and Matlab bindings if any one needs them.




General Machine Learning:
Take a look at this post on many toolkits (not all of which I have used) for more.

scikit-learn:
A machine learning library for python. I use this for nearly everything. Mature, easy to use and has lots of algorithms. Includes LibSVM wrappers, Linear SGD classifiers, K-means, cross-validation and grid search tools, manifold learning, Gaussian processes, spectral clustering, ICA, dictionary learning, decision trees... you name it.
Very well documented and many examples, also featuring a cool example gallery!

Other Programming Tools

CUV Library
A C++/Cuda/Python library with basic matrix, vector and convolution routines developed at my group. It was intended for running Restricted Boltzmann Machines and neural networks on the GPU.
The idea is to call CUDA functions from python, thus having the speed of CUDA as well as the ease of development of python.
If only simple matrix computations are involved, a algorithm can be transfered to the GPU just by line-by-line replacement of Matlab or Python code to library calls.


joblib
A python package for parallelization and persistence. Very easy to use to
parallelize across multiple CPUs, does not work over multiple boxes, though.

Popular posts from this blog

Machine Learning Cheat Sheet (for scikit-learn)

Image
As you hopefully have heard, we at scikit-learn are doing a user survey (which is still open by the way). One of the requests there was to provide some sort of flow chart on how to do machine learning. As this is clearly impossible, I went to work straight away. This is the result: [edit2] clarification: With ensemble classifiers and ensemble regressors I mean random forests , extremely randomized trees, gradient boosted trees , and the soon-to-be-come weight boosted trees (adaboost). [/edit2] Needless to say, this sheet is completely authoritative.
Read more

A Wordcloud in Python

Image
Last week I was at Pycon DE , the German Python conference. After hacking on scikit-learn a lot last week, I decided to to something different on my way back, that I had planned for quite a while: doing a wordl -like word cloud . I know, word clouds are a bit out of style but I kind of like them any way. My motivation to think about word clouds was that I thought these could be combined with topic-models to give somewhat more interesting visualizations. So I looked around to find a nice open-source implementation of word-clouds ... only to find none. (This has been a while, maybe it has changed since). While I was bored in the train last week, I came up with this code . A little today-themed taste:
Read more

MNIST for ever....

Image
[update] This post is a bit old, but many people still seem interested. So just a short update: Nowadays I would use Python and scikit-learn to do this. Here is an example of how to do cross-validation for SVMs in scikit-learn. Scikit-learn even downloads MNIST for you. [/update] MNIST is, for better or worse, one of the standard benchmarks for machine learning and is also widely used in then neural networks community as a toy vision problem. Just for the unlikely case that anyone is not familiar with it: It is a dataset of handwritten digits, 0-9, in black on white background. It looks something like this: There are 60000 training and 10000 test images, each 28x28 gray scale. There are roughly the same number of examples of each category in the test and training datasets. I used it in some papers myself even though there are some reasons why it is a little weird. Some not-so-obvious (or maybe they are) facts are: - The images actually contain a 20x20 patch of digi
Read more

Python things you never need: Empty lambda functions

Ever wanted to create an empty Python function in-line? No? Me neither. But my coworker does... We found the answer: <pre> x = lambda : None </pre> If you ever needed this, please tell me ;) [Edit] Apparently some people do need it :) Btw, most people seem to try Most people try lambda: pass first. But you have to remember, the thing at the right side of the colon is the return value of the function, not the body! So an expression is needed, not a statement. [\Edit]
Read more