| 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
|
