Tue, 13 May 2008 13:23:05 -0400 |
Frederic Bastien |
bugfix. Otherwise the example was writed over and not a new one was returned
|
Mon, 12 May 2008 18:51:42 -0400 |
Joseph Turian |
Updated documentation
|
Mon, 12 May 2008 18:40:17 -0400 |
Joseph Turian |
Created exceptions.py
|
Mon, 12 May 2008 17:40:06 -0400 |
Frederic Bastien |
bugfix, we should advence by the minibatch size.
|
Mon, 12 May 2008 16:51:54 -0400 |
Frederic Bastien |
bugfix: make the iterator advance
|
Mon, 12 May 2008 16:13:48 -0400 |
Frederic Bastien |
merge
|
Mon, 12 May 2008 16:12:29 -0400 |
Frederic Bastien |
optimization
|
Mon, 12 May 2008 16:11:24 -0400 |
Yoshua Bengio |
Fixes in CacheDataSet
|
Mon, 12 May 2008 15:51:43 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Mon, 12 May 2008 15:51:30 -0400 |
Frederic Bastien |
bugfix
|
Mon, 12 May 2008 15:50:28 -0400 |
Yoshua Bengio |
Trying to make CacheDataSet work
|
Mon, 12 May 2008 15:08:18 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Mon, 12 May 2008 14:15:16 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Mon, 12 May 2008 14:13:39 -0400 |
Frederic Bastien |
...
|
Mon, 12 May 2008 14:13:19 -0400 |
Frederic Bastien |
bugfix
|
Wed, 07 May 2008 16:26:28 -0400 |
Frederic Bastien |
typo
|
Mon, 12 May 2008 14:30:21 -0400 |
Yoshua Bengio |
Fixed bugs in dataset to make test_mlp.py work
|
Fri, 09 May 2008 17:38:57 -0400 |
Yoshua Bengio |
Fixes to ApplyFunctionDataSet and other things to make learner and mlp work
|
Thu, 08 May 2008 00:54:14 -0400 |
Joseph Turian |
Updated documentation slightly
|
Wed, 07 May 2008 20:51:24 -0400 |
Yoshua Bengio |
minor edits
|
Wed, 07 May 2008 16:22:28 -0400 |
Frederic Bastien |
bugfix
|
Wed, 07 May 2008 16:17:25 -0400 |
Frederic Bastien |
bugfix
|
Tue, 06 May 2008 22:24:55 -0400 |
bengioy |
Worked on OneShotTLearner and implementation of LinearRegression
|
Tue, 06 May 2008 16:34:48 -0400 |
Frederic Bastien |
bugfix, we keep all the line, but only a some columns
|
Tue, 06 May 2008 16:01:53 -0400 |
Frederic Bastien |
by default, in a minibatch without any fixed number of batchs, we need to finish at the end of the dataset. Now we return a minibatch at the end event if this minibacht size != the gived minibatch_size.
|
Tue, 06 May 2008 13:57:36 -0400 |
Frederic Bastien |
in ArrayDataSet.__init__ if a columns is an index, we change it to be a list that containt only this index. This way, we remove the special case where the columns is an index for all subsequent call.
|
Tue, 06 May 2008 13:50:54 -0400 |
Frederic Bastien |
bugfix in DataSet.minibatch to correctly wrap in all corner case.
|
Tue, 06 May 2008 10:52:45 -0400 |
Frederic Bastien |
removed duplicated example in comment
|
Mon, 05 May 2008 17:13:07 -0400 |
Frederic Bastien |
corrected comment
|
Mon, 05 May 2008 14:51:41 -0400 |
Frederic Bastien |
bugfix as numpy numpy don't support self.data[[i1,...],[i2,...]] when their is more then two i1 and i2
|
Mon, 05 May 2008 13:37:39 -0400 |
Frederic Bastien |
bugfix
|
Mon, 05 May 2008 11:14:28 -0400 |
Frederic Bastien |
bugfix
|
Mon, 05 May 2008 11:02:03 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Mon, 05 May 2008 10:56:58 -0400 |
Frederic Bastien |
bugfix
|
Mon, 05 May 2008 09:35:30 -0400 |
bengioy |
In the middle of designing TLearner
|
Sun, 04 May 2008 15:09:22 -0400 |
bengioy |
toying with different ways to implement learners
|
Sat, 03 May 2008 14:41:02 -0400 |
Yoshua Bengio |
Fixed errors raised by test_dataset
|
Sat, 03 May 2008 14:29:56 -0400 |
bengioy |
Coded untested ApplyFunctionDataSet and CacheDataSet
|
Fri, 02 May 2008 18:36:47 -0400 |
Joseph Turian |
Changed docs slightly
|
Fri, 02 May 2008 11:24:17 -0400 |
Frederic Bastien |
fixed test and removed print
|
Fri, 02 May 2008 11:10:20 -0400 |
Yoshua Bengio |
fixed the infinite loop
|
Fri, 02 May 2008 11:01:28 -0400 |
Yoshua Bengio |
trying to fix infinite loop
|
Fri, 02 May 2008 10:14:01 -0400 |
Frederic Bastien |
bugfix
|
Fri, 02 May 2008 09:55:38 -0400 |
Frederic Bastien |
bugfix: in MinibatchDataSet renamed the class variable fields to _fields as parent class have a function called field.
|
Thu, 01 May 2008 16:26:34 -0400 |
Frederic Bastien |
bugfix
|
Tue, 29 Apr 2008 17:45:16 -0400 |
Yoshua Bengio |
Added empty classes with doc: CachedDataSet and ApplyFunctionDataSet
|
Tue, 29 Apr 2008 16:09:17 -0400 |
Yoshua Bengio |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Tue, 29 Apr 2008 15:05:12 -0400 |
Yoshua Bengio |
Efficient implementation of getitem for ArrayDataSet
|
Tue, 29 Apr 2008 14:40:44 -0400 |
Frederic Bastien |
Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
|
Tue, 29 Apr 2008 14:40:06 -0400 |
Frederic Bastien |
fix comment
|
Tue, 29 Apr 2008 13:40:13 -0400 |
bengioy |
Fixing MinibatchDataSet getitem
|
Tue, 29 Apr 2008 12:37:11 -0400 |
Frederic Bastien |
comments modif made by Yoshua
|
Tue, 29 Apr 2008 11:25:36 -0400 |
bengioy |
Test functions for dataset.py
|
Mon, 28 Apr 2008 13:52:54 -0400 |
bengioy |
Fixed some more iterator bugs
|
Mon, 28 Apr 2008 11:41:28 -0400 |
bengioy |
Corrected iterator logic errors
|
Fri, 25 Apr 2008 16:00:31 -0400 |
bengioy |
Testing basic functionality and removing obvious bugs
|
Fri, 25 Apr 2008 12:04:55 -0400 |
bengioy |
Added ArrayDataSet
|
Fri, 25 Apr 2008 10:41:19 -0400 |
bengioy |
replaced infinity for length by raise UnboundedDataSet and use & instead of + to concatenate datasets
|
Thu, 24 Apr 2008 14:46:10 -0400 |
bengioy |
Minor edits
|
Thu, 24 Apr 2008 13:25:39 -0400 |
bengioy |
Finished first untested version of VStackedDataset
|
Thu, 24 Apr 2008 12:03:06 -0400 |
bengioy |
Factored the minibatch-writing code into an iterator class inside DataSet
|
Tue, 22 Apr 2008 18:03:11 -0400 |
bengioy |
Rewriting dataset.py completely
|
Fri, 11 Apr 2008 15:46:18 -0400 |
bengioy |
Changed apply_function so that it propagates methods of the source.
|
Fri, 11 Apr 2008 13:08:51 -0400 |
bengioy |
Removed __array__ method from dataset, whose
|
Fri, 11 Apr 2008 11:14:54 -0400 |
bengioy |
Fixed dataset errors so that _test_dataset.py works again.
|
Wed, 09 Apr 2008 18:27:13 -0400 |
bengioy |
Working on ApplyFunctionDataSet, added constraint that
|
Mon, 07 Apr 2008 20:44:37 -0400 |
bengioy |
Created virtual sub-classes of DataSet: {Finite{Length,Width},Sliceable}DataSet,
|
Mon, 07 Apr 2008 09:48:39 -0400 |
bengioy |
Minor editions, plus adding untested ApplyFunctionDataset for GradientLearner in the works.
|
Thu, 27 Mar 2008 01:59:44 -0400 |
bergstrj |
Iterators extend LookupList
|
Wed, 26 Mar 2008 21:05:14 -0400 |
bergstrj |
more comments, looping ArrayDataSet iterator, bugfixes to lookup_list, more tests
|
Wed, 26 Mar 2008 18:23:44 -0400 |
bergstrj |
commenting
|
Tue, 25 Mar 2008 13:38:51 -0400 |
bergstrj |
comment re: ArrayDataSet.__array__
|
Wed, 26 Mar 2008 18:21:57 -0400 |
bengioy |
Added LookupList type in lookup_list.py and used it to keep order
|
Wed, 26 Mar 2008 15:01:30 -0400 |
bengioy |
Debugged (to the extent of my tests) the new version of dataset
|
Mon, 24 Mar 2008 16:52:47 -0400 |
bengioy |
Improving comments in dataset.py
|
Mon, 24 Mar 2008 15:56:53 -0400 |
bengioy |
Replaced asarray() method by __array__ method which gets called automatically when
|
Mon, 24 Mar 2008 13:20:15 -0400 |
bengioy |
Moved iterating counter into a FiniteDataSetIterator to allow embedded iterations and multiple threads iterating at the same time on a dataset.
|
Mon, 24 Mar 2008 09:04:06 -0400 |
bengioy |
Removed MinibatchIterator and instead made minibatch_size a field of all DataSets,
|
Sun, 23 Mar 2008 22:44:43 -0400 |
bengioy |
Added MinibatchIterator
|
Sun, 23 Mar 2008 22:14:10 -0400 |
bengioy |
Added test for dataset.
|
Sun, 23 Mar 2008 14:41:22 -0400 |
bengioy |
Added first (untested) version of ArrayDataSet
|
Sat, 22 Mar 2008 22:21:59 -0400 |
bengioy |
Rewrote DataSet interface and created FiniteDataSet interface.
|
Fri, 14 Mar 2008 11:28:08 -0400 |
bengioy |
Added statscollector and started writing dataset and learner.
|
Fri, 14 Mar 2008 10:07:50 -0400 |
bengioy |
Creating project for learning algorithms on top of Theano
|