Mercurial > pylearn
comparison pylearn/datasets/MNIST.py @ 563:16f91ca016b1
* added NStages as a stopper (moved from hpu/conv)
* added a argmax_standalone output to logistic_regression which is independent
of the targets, which was needed to compute an output independently of the
target
* fixed some import discrepancies between pylearn and pylearn_refactor (mostly
for datasets)
* added testDataset which generates sequential or random data for a given shape
author | desjagui@atchoum.iro.umontreal.ca |
---|---|
date | Wed, 03 Dec 2008 17:21:05 -0500 |
parents | b054271b2504 |
children | ec27e19bb6eb |
comparison
equal
deleted
inserted
replaced
560:96221aa02fcb | 563:16f91ca016b1 |
---|---|
44 y=all_targ[ntrain:ntrain+nvalid]) | 44 y=all_targ[ntrain:ntrain+nvalid]) |
45 rval.test = Dataset.Obj(x=all_x[ntrain+nvalid:ntrain+nvalid+ntest], | 45 rval.test = Dataset.Obj(x=all_x[ntrain+nvalid:ntrain+nvalid+ntest], |
46 y=all_targ[ntrain+nvalid:ntrain+nvalid+ntest]) | 46 y=all_targ[ntrain+nvalid:ntrain+nvalid+ntest]) |
47 | 47 |
48 rval.n_classes = 10 | 48 rval.n_classes = 10 |
49 rval.img_shape = (28,28) | |
49 return rval | 50 return rval |
50 | 51 |
51 | 52 |
52 | 53 |
53 @dataset_factory('MNIST') | 54 @dataset_factory('MNIST') |