class ClassifierConfig():
def __init__(self, dataset, L, numfolds=4):
self.d = Dataset(dataset)
self.e = Extractor()
self.dense_codebook = self.e.get_codebook(self.d, 'dsift')
self.sparse_codebook = self.e.get_codebook(self.d, 'sift')
self.L = L
self.numfolds = numfolds
def kfold(self):
train_idx, val_idx = KFold(len(len(self.d.images), self.numfolds))
self.d.create_folds(self.numfolds)
class ClassifierConfig():
def __init__(self, dataset, L, numfolds=4):
self.d = Dataset(dataset)
self.e = Extractor()
self.dense_codebook = self.e.get_codebook(self.d, 'dsift')
self.sparse_codebook = self.e.get_codebook(self.d, 'sift')
self.L = L
self.numfolds = numfolds
def kfold(self):
train_idx, val_idx = KFold(len(len(self.d.images), self.numfolds))
self.d.create_folds(self.numfolds)
def test_kfold(self):
"""
'sizes' here are empirical values over the trainval set.
"""
d = Dataset('full_pascal_trainval')
numfolds = 4
d.create_folds(numfolds)
cls = 'dog'
sizes = [314, 308, 321, 320]
for i in range(len(d.folds)):
d.next_folds()
pos = d.get_pos_samples_for_fold_class(cls)
neg = d.get_neg_samples_for_fold_class(cls, pos.shape[0])
assert (pos.shape[0] == sizes[i])
assert (neg.shape[0] == sizes[i])
def test_kfold(self):
"""
'sizes' here are empirical values over the trainval set.
"""
d = Dataset('full_pascal_trainval')
numfolds = 4
d.create_folds(numfolds)
cls = 'dog'
sizes = [314, 308, 321, 320]
for i in range(len(d.folds)):
d.next_folds()
pos = d.get_pos_samples_for_fold_class(cls)
neg = d.get_neg_samples_for_fold_class(cls, pos.shape[0])
assert(pos.shape[0] == sizes[i])
assert(neg.shape[0] == sizes[i])