def get_training_subset(train_X, name):
if name == 'omnivore':
coarse_class = 11
num_ex = 40
else:
coarse_class = 4
num_ex = 25
tlc = TL_Challenge(which_set='train')
mask = tlc.y_coarse == coarse_class
sub_X = train_X[mask, :]
sub_y = tlc.y_fine[mask]
assert sub_X.shape[0] == num_ex
assert sub_y.shape == (num_ex, )
fold_indices = np.zeros((num_ex, num_ex - 1), dtype='uint16')
idx_list = np.cast['uint16'](np.arange(1, num_ex +
1)) #mimic matlab format of stl10
for i in xrange(num_ex):
mask = idx_list < i + 1
mask += idx_list >= (i + 1) + 1
fold_indices[i, :] = idx_list[mask]
assert fold_indices.min() == 1
assert fold_indices.max() == num_ex
return sub_X, sub_y, fold_indices
class TestTL_Challenge(unittest.TestCase):
def setUp(self):
skip_if_no_data()
self.train = TL_Challenge(which_set='train')
self.unlabeled = TL_Challenge(which_set='unlabeled')
self.test = TL_Challenge(which_set='test')
def test_topo(self):
"""Tests that a topological batch has 4 dimensions"""
topo = self.train.get_batch_topo(1)
assert topo.ndim == 4
def get_labels():
cifar100 = CIFAR100(which_set="train")
train_y = cifar100.y_coarse
assert train_y.shape == (50000, )
for i in xrange(50000):
if train_y[i] not in [3, 4, 6, 7, 11, 12]:
train_y[i] = 0
tlc = TL_Challenge(which_set='train')
test_y = tlc.y_coarse
return train_y, test_y
def get_labels_and_fold_indices():
tlc = TL_Challenge(which_set='train')
train_y = tlc.y_fine
assert train_y is not None
fold_indices = np.zeros((120, 119), dtype='uint16')
idx_list = np.cast['uint16'](np.arange(1,
121)) #mimic matlab format of stl10
for i in xrange(120):
mask = idx_list < i + 1
mask += idx_list >= (i + 1) + 1
fold_indices[i, :] = idx_list[mask]
assert fold_indices.min() == 1
assert fold_indices.max() == 120
return tlc.y_fine, tlc.y_coarse, fold_indices
def setUp(self):
skip_if_no_data()
self.train = TL_Challenge(which_set='train')
self.unlabeled = TL_Challenge(which_set='unlabeled')
self.test = TL_Challenge(which_set='test')
def test_topo(self):
"""Tests that a topological batch has 4 dimensions"""
train = TL_Challenge(which_set='train')
topo = train.get_batch_topo(1)
assert topo.ndim == 4
def test_topo(self):
"""Tests that a topological batch has 4 dimensions"""
train = TL_Challenge(which_set='train')
topo = train.get_batch_topo(1)
assert topo.ndim == 4
def test_load(self):
TL_Challenge(which_set='unlabeled')
TL_Challenge(which_set='test')
from pylearn2.utils import serial
from pylearn2.datasets.cifar100 import CIFAR100
from pylearn2.datasets.tl_challenge import TL_Challenge
from pylearn2.datasets import preprocessing
import os
import numpy as np
goodfeli_tmp = os.environ['GOODFELI_TMP']
train = CIFAR100(which_set="train")
aug = TL_Challenge(which_set="unlabeled")
aug2 = TL_Challenge(which_set="train")
train.set_design_matrix(np.concatenate((train.X, aug.X, aug2.X), axis=0))
del aug
del aug2
pipeline = preprocessing.Pipeline()
pipeline.items.append(
preprocessing.ExtractPatches(patch_shape=(6, 6), num_patches=2000000))
pipeline.items.append(preprocessing.GlobalContrastNormalization())
pipeline.items.append(preprocessing.ZCA())
train.apply_preprocessor(preprocessor=pipeline, can_fit=True)
train.use_design_loc(goodfeli_tmp + '/tl_challenge_patches_2M_6x6_design.npy')
serial.save(goodfeli_tmp + '/tl_challenge_patches_2M_6x6.pkl', train)
