Tue, 03 Mar 2009 11:37:56 -0500 |
Frederic Bastien |
added pylearn.datasets.MNIST.first_10 and pylearn.datasets.MNIST.first_100. They are usefull to test with small dataset.
|
Fri, 20 Feb 2009 15:08:46 -0500 |
Pascal Lamblin |
merge
|
Fri, 20 Feb 2009 15:08:29 -0500 |
Pascal Lamblin |
Get rid of old dbdict
|
Fri, 13 Feb 2009 13:22:26 -0500 |
Frederic Bastien |
if PYLEARN_DATA_ROOT don't exist try DBPATH.
|
Wed, 11 Feb 2009 01:43:14 -0500 |
bergstra |
merge
|
Wed, 11 Feb 2009 01:42:58 -0500 |
bergstra |
print warning on undefined PYLEARN_DATA_ROOT
|
Wed, 11 Feb 2009 01:42:26 -0500 |
bergstra |
added image_tiling
|
Wed, 04 Feb 2009 20:02:05 -0500 |
James Bergstra |
revised classification and LogReg_New
|
Wed, 04 Feb 2009 18:04:05 -0500 |
James Bergstra |
factoring out classification from LogReg_New
|
Wed, 04 Feb 2009 15:56:20 -0500 |
James Bergstra |
merge
|
Wed, 04 Feb 2009 15:56:00 -0500 |
James Bergstra |
adding a little hacky script to flickr that renders a few images as png
|
Wed, 04 Feb 2009 15:55:19 -0500 |
James Bergstra |
added new way of writing logistic regression
|
Tue, 03 Feb 2009 16:47:40 -0500 |
Pascal Lamblin |
Get rid of dbdict, it now has its own repository.
|
Mon, 02 Feb 2009 17:41:54 -0500 |
desjagui |
Changed database schema to be more efficient:
|
Fri, 30 Jan 2009 16:54:06 -0500 |
Joseph Turian |
Added tag sequencelabelling 20090130-rerun for changeset 5f9ffefa9ca8
|
Fri, 30 Jan 2009 16:38:46 -0500 |
Joseph Turian |
pylearn/algorithms/logistic_regression.py:
sequencelabelling 20090130-rerun
|
Fri, 30 Jan 2009 16:38:02 -0500 |
Joseph Turian |
Bugfix in cost.py to correctly use theano.tensor.xlogx
|
Sat, 24 Jan 2009 17:25:41 -0500 |
James Bergstra |
merge
|
Sat, 24 Jan 2009 17:24:55 -0500 |
James Bergstra |
revised tzanetakis, added data centering
|
Thu, 22 Jan 2009 21:14:03 -0500 |
Pascal Lamblin |
Add "FUCKED_UP" (666) status.
|
Wed, 21 Jan 2009 18:53:35 -0500 |
desjagui |
Updated sql commands for creating the view
|
Wed, 21 Jan 2009 16:02:07 -0500 |
James Bergstra |
merge
|
Wed, 21 Jan 2009 16:01:16 -0500 |
James Bergstra |
changed insert_ methods in sql to not clobber internal keys STATUS, PRIORITY, HASH
|
Wed, 21 Jan 2009 03:37:58 -0500 |
projects |
Reverting out of changeset 633,634. Hopefully i did this write !
|
Wed, 21 Jan 2009 03:27:13 -0500 |
desjagui |
merge
|
Wed, 21 Jan 2009 03:23:50 -0500 |
desjagui |
merged
|
Wed, 21 Jan 2009 03:20:16 -0500 |
desjagui |
Cost should be summed over the units, but averaged across batches.
|
Tue, 20 Jan 2009 23:32:24 -0500 |
James Bergstra |
added priority keyword arg to sql.insert_job and insert_dict
|
Tue, 20 Jan 2009 23:30:17 -0500 |
James Bergstra |
added priority-based dequeuing to sql.book_dct_postgres
|
Mon, 19 Jan 2009 18:35:43 -0500 |
James Bergstra |
merge
|
Mon, 19 Jan 2009 18:34:13 -0500 |
James Bergstra |
added get by id to api0
|
Mon, 19 Jan 2009 18:10:48 -0500 |
James Bergstra |
moving away from mnist_factory
|
Mon, 19 Jan 2009 00:58:06 -0500 |
desjagui |
remove debug prints
|
Mon, 19 Jan 2009 00:46:28 -0500 |
desjagui |
Added hash value for each dict in Trial table.
|
Sun, 18 Jan 2009 22:17:56 -0500 |
James Bergstra |
fixing session management in db dict update
|
Sun, 18 Jan 2009 22:00:16 -0500 |
James Bergstra |
looping works, eagerload of booked jobs works by str() HACK
|
Sun, 18 Jan 2009 21:39:28 -0500 |
James Bergstra |
api0 and sql seem to work with session closing
|
Sun, 18 Jan 2009 21:14:14 -0500 |
James Bergstra |
untested changes to close sessions in api0
|
Sat, 17 Jan 2009 21:23:36 -0500 |
James Bergstra |
changed sql to use filter_eq_dct
|
Sat, 17 Jan 2009 21:20:32 -0500 |
James Bergstra |
added api0.filter_eq_dct
|
Sat, 17 Jan 2009 19:13:17 -0500 |
lamblinp |
Fix typo
|
Sat, 17 Jan 2009 19:06:21 -0500 |
lamblinp |
More complete version of shapeset1 dataset.
|
Sat, 17 Jan 2009 17:38:17 -0500 |
James Bergstra |
merge
|
Sat, 17 Jan 2009 17:37:55 -0500 |
James Bergstra |
updated query to support new dot syntax, and hacked api0 to mirror dbdict.status and dbdict.priority to true columns
|
Sat, 17 Jan 2009 00:34:14 -0500 |
Pascal Lamblin |
Use usual data_root
|
Fri, 16 Jan 2009 19:10:50 -0500 |
lamblinp |
merge.
|
Fri, 16 Jan 2009 19:10:09 -0500 |
lamblinp |
- Account for exception name change in sqlalchemy 0.5.0
|
Fri, 16 Jan 2009 16:27:44 -0500 |
Olivier Breuleux |
removed an obtrusive try/except
|
Fri, 16 Jan 2009 15:53:47 -0500 |
Olivier Breuleux |
merge
|
Fri, 16 Jan 2009 15:53:22 -0500 |
Olivier Breuleux |
added -f flag to sqlschedule and sqlschedule_filemerge
|
Thu, 15 Jan 2009 22:23:43 -0500 |
James Bergstra |
merged
|
Thu, 15 Jan 2009 22:22:45 -0500 |
James Bergstra |
added dbdict-run cmdline option (-2 --allow_sigint) to allow ctrl-c to interrupt progrma
|
Thu, 15 Jan 2009 22:21:35 -0500 |
James Bergstra |
added comments to amat
|
Thu, 15 Jan 2009 22:21:04 -0500 |
James Bergstra |
initial tzanetakis dataset
|
Thu, 15 Jan 2009 17:12:36 -0500 |
Olivier Breuleux |
merge
|
Thu, 15 Jan 2009 17:07:49 -0500 |
Olivier Breuleux |
added sqlschedule_filemerge to newstuff
|
Wed, 14 Jan 2009 17:22:23 -0500 |
James Bergstra |
fixed flickr relpath mistake
|
Wed, 14 Jan 2009 17:00:57 -0500 |
James Bergstra |
updated flickr to row-major files
|
Wed, 14 Jan 2009 15:54:39 -0500 |
James Bergstra |
initial flickr
|
Tue, 13 Jan 2009 20:08:06 -0500 |
James Bergstra |
misc small changes
|
Tue, 13 Jan 2009 16:00:36 -0500 |
james |
merged
|
Tue, 13 Jan 2009 16:00:24 -0500 |
james |
revised newstuff.resolve to do more importing
|
Mon, 12 Jan 2009 18:47:10 -0500 |
Olivier Breuleux |
merge
|
Mon, 12 Jan 2009 18:46:46 -0500 |
Olivier Breuleux |
corrected filemerge
|