Mercurial > ift6266
comparison deep/stacked_dae/v_sylvain/sgd_optimization.py @ 457:78ed4628071d
Rajout de la ligne qui compte le nombre de mini-batch (enleve precedemment)
| author | SylvainPL <sylvain.pannetier.lebeuf@umontreal.ca> |
|---|---|
| date | Wed, 26 May 2010 20:25:39 -0400 |
| parents | 09e1c5872c2b |
| children |
comparison
equal
deleted
inserted
replaced
| 456:66b05c6077c7 | 457:78ed4628071d |
|---|---|
| 414 name = 'test' | 414 name = 'test' |
| 415 train_losses2 = [test_model(x,y) for x,y in iter2] | 415 train_losses2 = [test_model(x,y) for x,y in iter2] |
| 416 train_score2 = numpy.mean(train_losses2) | 416 train_score2 = numpy.mean(train_losses2) |
| 417 print 'On the ' + name + 'dataset' | 417 print 'On the ' + name + 'dataset' |
| 418 print(('\t the error is %f')%(train_score2*100.)) | 418 print(('\t the error is %f')%(train_score2*100.)) |
| 419 #print len(train_losses2) | |
| 419 stderr = math.sqrt(train_score2-train_score2**2)/math.sqrt(len(train_losses2)*self.hp.minibatch_size) | 420 stderr = math.sqrt(train_score2-train_score2**2)/math.sqrt(len(train_losses2)*self.hp.minibatch_size) |
| 420 print (('\t the stderr is %f')%(stderr*100.)) | 421 print (('\t the stderr is %f')%(stderr*100.)) |
| 421 | 422 |
| 422 #To see the prediction of the model, the real answer and the image to judge | 423 #To see the prediction of the model, the real answer and the image to judge |
| 423 def see_error(self, dataset): | 424 def see_error(self, dataset): |