Mercurial > pylearn
changeset 299:eded3cb54930
small bug fixed
| author | Thierry Bertin-Mahieux <bertinmt@iro.umontreal.ca> |
|---|---|
| date | Fri, 06 Jun 2008 17:58:45 -0400 |
| parents | 5987415496df |
| children | 7c5e5356cb11 |
| files | _test_dataset.py denoising_aa.py mlp_factory_approach.py |
| diffstat | 3 files changed, 13 insertions(+), 6 deletions(-) [+] |
line wrap: on
line diff
--- a/_test_dataset.py Fri Jun 06 17:55:14 2008 -0400 +++ b/_test_dataset.py Fri Jun 06 17:58:45 2008 -0400 @@ -480,7 +480,7 @@ def test_ApplyFunctionDataSet(self): ds = T_Exotic1.DataSet() - dsa = ApplyFunctionDataSet(ds,lambda x,y,z: ([x[-1]],[y*10],[int(z)]),['input','target','name'],minibatch_mode=False) #broken!!!!!! + dsa = ApplyFunctionDataSet(ds,lambda x,y,z: (x[-1],y*10,int(z)),['input','target','name'],minibatch_mode=False) #broken!!!!!! for k in range(len(dsa)): res = dsa[k] self.failUnless(ds[k]('input')[0][-1] == res('input')[0] , 'problem in first applied function')
--- a/denoising_aa.py Fri Jun 06 17:55:14 2008 -0400 +++ b/denoising_aa.py Fri Jun 06 17:58:45 2008 -0400 @@ -106,11 +106,14 @@ self.denoising_autoencoder_formula = corruption_formula + autoencoder.rename(x='corrupted_x') def __call__(self, training_set=None): - """ Allocate and optionnaly train a model""" + """ Allocate and optionnaly train a model + + @TODO enables passing in training and valid sets, instead of cutting one set in 80/20 + """ model = DenoisingAutoEncoderModel(self) if training_set: print 'DenoisingAutoEncoder(): what do I do if training_set????' - # copied from mlp_factory_approach: + # copied from old mlp_factory_approach: if len(trainset) == sys.maxint: raise NotImplementedError('Learning from infinite streams is not supported') nval = int(self.validation_portion * len(trainset))
--- a/mlp_factory_approach.py Fri Jun 06 17:55:14 2008 -0400 +++ b/mlp_factory_approach.py Fri Jun 06 17:58:45 2008 -0400 @@ -4,7 +4,8 @@ import theano from theano import tensor as T -from pylearn import dataset, nnet_ops, stopper, LookupList, filetensor +import dataset, nnet_ops, stopper, filetensor +from lookup_list import LookupList class AbstractFunction (Exception): pass @@ -54,7 +55,9 @@ return d[key] def update_minibatch(self, minibatch): - #assert isinstance(minibatch, LookupList) # why false??? + if not isinstance(minibatch, LookupList): + print type(minibatch) + assert isinstance(minibatch, LookupList) self.update_fn(minibatch['input'], minibatch['target'], *self.params) def update(self, dataset, @@ -216,6 +219,7 @@ l2coef = T.constant(l2coef_val) input = T.matrix() # n_examples x n_inputs target = T.ivector() # len: n_examples + #target = T.matrix() W2, b2 = T.matrix(), T.vector() W1, b1 = T.matrix(), T.vector() @@ -224,7 +228,7 @@ params = [W1, b1, W2, b2] activations = b2 + T.dot(hid, W2) - nll, predictions = nnet_ops.crossentropy_softmax_1hot(activations, target) + nll, predictions = nnet_ops.crossentropy_softmax_1hot(activations, target ) regularization = l2coef * T.sum(W2*W2) + hid_regularization output_class = T.argmax(activations,1) loss_01 = T.neq(output_class, target)