Mercurial > pylearn
changeset 871:fafe796ad5ff
merge
| author | James Bergstra <bergstrj@iro.umontreal.ca> |
|---|---|
| date | Wed, 11 Nov 2009 10:47:15 -0500 |
| parents | bd7d540db70d (diff) 2fffbfa41920 (current diff) |
| children | b2821fce15de |
| files | |
| diffstat | 1 files changed, 6 insertions(+), 6 deletions(-) [+] |
line wrap: on
line diff
--- a/pylearn/algorithms/logistic_regression.py Tue Nov 10 17:59:54 2009 -0500 +++ b/pylearn/algorithms/logistic_regression.py Wed Nov 11 10:47:15 2009 -0500 @@ -101,7 +101,7 @@ nnet.crossentropy_softmax_max_and_argmax_1hot( self.linear_output, self.target) - self.unregularized_cost = T.sum(self._xent) + self.unregularized_cost = T.mean(self._xent) self.l1_cost = self.l1 * T.sum(abs(self.w)) self.l2_cost = self.l2 * T.sum(self.w**2) self.regularized_cost = self.unregularized_cost + self.l1_cost + self.l2_cost @@ -245,12 +245,12 @@ output = nnet.sigmoid(T.dot(self.x, self.w) + self.b) xent = -self.targ * T.log(output) - (1.0 - self.targ) * T.log(1.0 - output) - sum_xent = T.sum(xent) + mean_xent = T.mean(xent) self.output = output self.xent = xent - self.sum_xent = sum_xent - self.cost = sum_xent + self.mean_xent = mean_xent + self.cost = mean_xent #define the apply method self.pred = (T.dot(self.input, self.w) + self.b) > 0.0 @@ -258,8 +258,8 @@ #if this module has any internal parameters, define an update function for them if self.params: - gparams = T.grad(sum_xent, self.params) - self.update = module.Method([self.input, self.targ], sum_xent, + gparams = T.grad(mean_xent, self.params) + self.update = module.Method([self.input, self.targ], mean_xent, updates = dict((p, p - self.lr * g) for p, g in zip(self.params, gparams)))