No subject

- There is a problem to be solved
- It would be nice to have a "one-stop-shop"

I have already though about this issue in the past, and I think I have
a decent grasp of the issues.
I will give a shot on creating such open source tool.
I have decided to name it "sponge" (because "it learns like a sponge")
and it will be hosted at Github.

https://github.com/rodrigob/sponge

Obviously right now the project is empty.
I will be working on the design on the github wiki (and google wave
linked there), and hopefully start pushing code in the next weeks.

Let us hope I get to create code that will be of use to other people.
Best regards,
rodrigob.



On Tue, Nov 23, 2010 at 5:16 PM, Pierre S <pierre.sermanet at gmail.com> wrote=
:
> oui, voila ma reponse:
> Hi Rodrigo,
>
> I maintain the eblearn and visiongrader open-source projects and they mig=
ht
> correspond to what you need. I'll just enumerate some aspects that seem t=
o
> fit your description:
>
> eblearn (http://eblearn.sourceforge.net/)
> - training by minimizing energies (rather than probabilities) is quite
> general and can be applied to lots of tasks (cf. Tutorial on Energy-Based
> Learning, Lecun et al 2006)
> - it is currently mostly focused on classification/detection, but the des=
ign
> is based on generic modules so that anybody can write its own modules and
> use the framework for a new task
>
> - modules are usually serially connected but can also be branched and mer=
ged
> to create more complex machines
> - one can easily create a new network of machines via configuration files=
 by
> defining the list of modules the machine contains, e.g. pre-processing,
> convolutions, pooling, etc, then feed it to the train executable and then
> detection executable. e.g.:
> http://eblearn.svn.sourceforge.net/viewvc/eblearn/trunk/tools/demos/pedes=
trians/inria/inria_meta.conf?revision=3D1391&view=3Dmarkup
> - so currently, training to recognize a new class of images involves taki=
ng
> the existing scripts in demos/pedestrian/inria for example, modify them a
> bit and feed them to the training and detection programs.
> - I am considering adding a graphical tool on top to graphically build an=
d
> connect modules together in serial or parallel to make things even easier=
.
>
> - the metarun executable is a very handy tool that takes a configuration
> file as input, generate all possible configurations if a variable has
> multiple values (e.g. multiple learning rates), runs all of them (in
> parallel or sequentially) and sends you the results by email (ranks and
> plots best solutions). this makes life much easier when having to try
> several configuration and compare them.
> - similarly, the detection executable is multi-threaded so that if you al=
low
> multiple cores, it will process 1 image on each core.
> - the library can be boosted by several other libraries such as IPP or
> openMP.
> - there also is a cluster version of the detector using MPI
>
> - the core libraries are self-contained and don't require any external
> =C2=A0third-party and are clearly separated from the helper libraries suc=
h as
> guis and dataset creation tools.
> - eblearn is therefore available on Android using only the lightweight co=
re
> minimum (even stripped of STL). The android version is currently missing =
the
> fixed-point precision for speed, but is usable.
> - the gui is made simple to use, here is a small example:
> http://eblearn.sourceforge.net/demos/simple/index.shtml
> - eblearn contains a set of tools to compile and preprocess training data
> easily given an image directory. it can also read PASCAL VOC xml.
> - the matrix data format (.mat) is fully compatible with lush (open sourc=
e
> scripted / compiled framework)
> - therefore eblearn is natively compatible with MNIST and NORB datasets
>
> - unsupervised training is being ported right now and boosts performances=
 (I
> obtain state-of-the-art results on INRIA pedestrians)
> - the advantage of this framework over traditional hand-crafted features =
is
> that features can be learned and optimized for a given task
> - it wasn't really designed to contain any handcrafted features, but you =
are
> welcome to add your own modules and plug them into the classifiers or eve=
n
> feed them to a second layer of features to be learned. This is just a mat=
ter
> of writing a SIFT module for example.
>
> - eblearn is written in C++ and contains some shell and python scripts fo=
r
> meta training
> - some scripts are available to automatize boostrapping and perform sever=
al
> passes of training / false positives extraction / data compilation
> - adding a python interface to eblearn might be a good idea for some peop=
le
> - eblearn is lacking more tutorials right now, I will resolve this in the
> near future.
>
> visiongrader (http://visiongrader.sourceforge.net/)
>
> - written in python
> - designed to be a generic evaluation tool
> - one only needs to write a parser for a new dataset, right now it's been
> used to parse INRIA pedestrians and caltech pedestrian datasets
> - multiple curves are currently available: DET and ROC
> - multiple matching criteria can be implemented, currently contains the 5=
0%
> overlap criteria.
> - a visualizer allows to show bounding boxes overlayed on images, show wh=
ich
> ones are matched or not, and a slider bar allows to vary detection thresh=
old
> - the visualizer also allows to select and save new bounding boxes in
> different formats (work in progress)
> - it is still a bit rough but usable
>
> Pierre
> On Tue, Nov 23, 2010 at 11:11 AM, Rodrigo Benenson
> <rodrigo.benenson at gmail.com> wrote:
>>
>> Ca prend plusieurs heures avant d'etre mis en ligne (inspection
>> manuelle de tout les messages).
>> Peut-etre un copier coler en courriel direct pour voir le message
>> aujourd'hui ?
>>
>> Merci beaucoup de votre reponse.
>> Cordialement,
>> rodrigob.
>>
>> On Tue, Nov 23, 2010 at 2:16 PM, Pierre S <pierre.sermanet at gmail.com>
>> wrote:
>> > J'ai repondu sur yahoogroups mais le message n'apparait pas, ca prend
>> > peut
>> > etre un peu de temps, dis moi si tu le recois.
>> >
>> > On Tue, Nov 23, 2010 at 6:01 AM, Pierre S <pierre.sermanet at gmail.com>
>> > wrote:
>> >>
>> >> Salut Rodrigo,
>> >> Effectivement c'est une bonne idee, je vais repondre sur la liste
>> >> merci.
>> >> Pierre
>> >>
>> >> On Mon, Nov 22, 2010 at 6:13 AM, Rodrigo Benenson
>> >> <rodrigo.benenson at gmail.com> wrote:
>> >>>
>> >>> D=C3=A9sol=C3=A9 pour le double courriel.
>> >>> En temps que contributeur principal dans EbLearn je pense que vous
>> >>> avez votre mot =C3=A0 dire sur cette question (active dans les liste=
s de
>> >>> courriel OpenCv-users et Ros-users ).
>> >>>
>> >>> Je serais tr=C3=A8s content si vous pouviez participer =C3=A0 la dis=
cussion,
>> >>> donner votre avis et partager votre exp=C3=A9rience sur le sujet.
>> >>>
>> >>> Je consid=C3=A8re EbLearn un "tr=C3=A8s bon exemple" de je ce que j'=
imagine,
>> >>> mais avec un support pour plus de bases de donn=C3=A9es et pour plus
>> >>> d'algorithmes diff=C3=A9rents.
>> >>>
>> >>> Tr=C3=A8s cordialement,
>> >>> rodrigo benenson phd.
>> >>>
>> >>> On Mon, Nov 22, 2010 at 12:00 PM, Rodrigo Benenson
>> >>> <rodrigo.benenson at gmail.com> wrote:
>> >>> > ---------- Forwarded message ----------
>> >>> > To: OpenCV at yahoogroups.com
>> >>> >
>> >>> >
>> >>> > Hello all.
>> >>> >
>> >>> > I'm contacting you because I am considering starting a new open
>> >>> > source
>> >>> > project to solve a specific problem: training and evaluating objec=
ts
>> >>> > detection algorithms.
>> >>> >
>> >>> > Hundreds of students have been there before: "I want to create a
>> >>> > program that detects objects in images".
>> >>> > They choose a dataset for training (e.g. INRIA pedestrians), a
>> >>> > feature
>> >>> > descriptor (e.g. HOG), a machine learning method (e.g. linear SVM)=
,
>> >>> > and then, they write the code to get it all together.
>> >>> >
>> >>> > In the best case they will take bits and pieces from multiple plac=
es
>> >>> > and spend a few weeks on the glue code. In the worst case they wil=
l
>> >>> > spend months reimplementing existing methods.
>> >>> >
>> >>> > It is time to stop the madness.
>> >>> > Training detectors for objects detection in images is a specific a=
nd
>> >>> > well defined problem.
>> >>> > It is time to share our effort and build a reference open source
>> >>> > tool
>> >>> > to solve this common problem.
>> >>> > We should have an open source tool that provides all the common
>> >>> > bits,
>> >>> > the glue and allows us to focus on what we really care: the
>> >>> > algorithms.
>> >>> >
>> >>> > In some sense OpenCv 2.2 helps a lot to the task, however OpenCv i=
s
>> >>> > aimed to be a generic library not a specific application framework=
.
>> >>> > In
>> >>> > that sense it will never provide the desired "install, run, see th=
e
>> >>> > graphs coming out" experience.
>> >>> >
>> >>> > Also ROS.org helps a lot the task, by providing a generic framewor=
k
>> >>> > to
>> >>> > create and exchange software modules, along with standard tools fo=
r
>> >>> > messages passing, data storage and exploration. However this
>> >>> > framework
>> >>> > by itself has a non negligible learning curve and it is unfamiliar
>> >>> > to
>> >>> > anyone outside the robotics community.
>> >>> >
>> >>> > I currently have my own idea of how things could be. However befor=
e
>> >>> > creating "yet one more framework" I would like to have your input =
on
>> >>> > the topic.
>> >>> >
>> >>> > I have created a short form to collect your opinions. I would be
>> >>> > very
>> >>> > glad if you could help me go in the right direction by giving your
>> >>> > input.
>> >>> >
>> >>> >
>> >>> >
>> >>> > https://spreadsheets.google.com/viewform?formkey=3DdFFzaDlLM1liVGN=
OS2FENnhrc1VWckE6MQ
>> >>> >
>> >>> > The form is anonymous and the results are public.
>> >>> >
>> >>> > Based your opinions and ideas I will do my best to move forward an
>> >>> > usable open source solution.
>> >>> > Further information will be posted at
>> >>> > https://wave.google.com/wave/waveref/googlewave.com/w+yH-HOCb6H
>> >>> >
>> >>> > Best regards,
>> >>> > rodrigo benenson phd.
>> >>> >
>> >>> > ps: If you are interested do not hesitate to send a message. You c=
an
>> >>> > contact me via github as "rodrigob".
>> >>> >
>> >>
>> >
>> >
>
>