Mercurial > pylearn

comparison dataset.py @ 238:ae1d85aca858

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
optimization in ArrayDataSet::__iter__
author Frederic Bastien <bastienf@iro.umontreal.ca>
date Thu, 29 May 2008 10:30:59 -0400
parents a70f2c973ea5
children ef70a665aaaf
comparison
equal deleted inserted replaced
237:584ad7c55876 238:ae1d85aca858
1052 self.dataset=dataset 1052 self.dataset=dataset
1053 self.minibatch_size=minibatch_size 1053 self.minibatch_size=minibatch_size
1054 assert offset>=0 and offset<len(dataset.data) 1054 assert offset>=0 and offset<len(dataset.data)
1055 assert offset+minibatch_size<=len(dataset.data) 1055 assert offset+minibatch_size<=len(dataset.data)
1056 self.current=offset 1056 self.current=offset
1057 self.columns = [self.dataset.fields_columns[f]
1058 for f in self.minibatch._names]
1057 def __iter__(self): 1059 def __iter__(self):
1058 return self 1060 return self
1059 def next(self): 1061 def next(self):
1060 #@todo: we suppose that we need to stop only when minibatch_size == 1. 1062 #@todo: we suppose that we need to stop only when minibatch_size == 1.
1061 # Otherwise, MinibatchWrapAroundIterator do it. 1063 # Otherwise, MinibatchWrapAroundIterator do it.
1062 if self.current>=self.dataset.data.shape[0]: 1064 if self.current>=self.dataset.data.shape[0]:
1063 raise StopIteration 1065 raise StopIteration
1064 sub_data = self.dataset.data[self.current] 1066 sub_data = self.dataset.data[self.current]
1065 self.minibatch._values = [sub_data[self.dataset.fields_columns[f]] for f in self.minibatch._names] 1067 self.minibatch._values = [sub_data[c] for c in self.columns]
1068
1066 self.current+=self.minibatch_size 1069 self.current+=self.minibatch_size
1067 return self.minibatch 1070 return self.minibatch
1068 1071
1069 return ArrayDataSetIterator2(self,self.fieldNames(),1,0,0) 1072 return ArrayDataSetIterator2(self,self.fieldNames(),1,0,0)
1070 1073