def data():
fname = _download('http://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz')
with _taropen(fname, 'r') as f:
# The first four batches are used as training set...
datas, labels = [], []
for i in range(1, 5):
with f.extractfile('cifar-10-batches-py/data_batch_' + str(i)) as b:
batch = _pickle.load(b, encoding='latin1')
datas.append(_np.array(batch['data'], dtype=_np.float32))
labels.append(_np.array(batch['labels']))
Xtr = _np.concatenate(datas)
ytr = _np.concatenate(labels)
Xtr /= 255
# ... and the fifth as validation set as described in cuda-convnet:
# https://code.google.com/p/cuda-convnet/wiki/Methodology
with f.extractfile('cifar-10-batches-py/data_batch_5') as b:
batch = _pickle.load(b, encoding='latin1')
Xva = _np.array(batch['data'], dtype=_np.float32)
yva = _np.array(batch['labels'])
Xva /= 255
with f.extractfile('cifar-10-batches-py/test_batch') as b:
batch = _pickle.load(b, encoding='latin1')
Xte = _np.array(batch['data'], dtype=_np.float32)
yte = _np.array(batch['labels'])
Xte /= 255
return (Xtr, ytr), (Xva, yva), (Xte, yte)
def data(fold=False):
fname = df.zoo.download('http://dags.stanford.edu/data/iccv09Data.tar.gz')
# extracting files one-by-one in memory is unfortunately WAY too slow
# for this dataset. So we bite the bullet and extract the full tgz.
where = _p.dirname(fname)
imgdir = 'iccv09Data/images/'
with _taropen(fname, 'r') as f:
f.extractall(where)
ids = [_p.basename(n)[:-4] for n in f.getnames() if n.startswith(imgdir)]
X = [imread(_p.join(where, imgdir, i) + '.jpg') for i in ids]
y = [_np.loadtxt(_p.join(where, 'iccv09Data/labels', i) + '.regions.txt', dtype=_np.int32) for i in ids]
# I personally don't believe in the other label types.
le = _np.array(['sky', 'tree', 'road', 'grass', 'water', 'building', 'mountain', 'foreground', 'object'])
try:
from sklearn.preprocessing import LabelEncoder
le, classes = LabelEncoder(), le
le.classes_ = classes
except ImportError:
pass
if fold is False:
return X, y, le
lo, hi = fold*ntest(), (fold+1)*ntest()
Xtr = X[:lo] + X[hi:]
ytr = y[:lo] + y[hi:]
Xte = X[lo:hi]
yte = y[lo:hi]
return (Xtr, ytr), (Xte, yte), le
def data():
fname = _download('http://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz')
with _taropen(fname, 'r') as f:
# The first four batches are used as training set...
datas, labels = [], []
for i in range(1, 5):
with f.extractfile('cifar-10-batches-py/data_batch_' +
str(i)) as b:
batch = _pickle.load(b, encoding='latin1')
datas.append(_np.array(batch['data'], dtype=_np.float32))
labels.append(_np.array(batch['labels']))
Xtr = _np.concatenate(datas)
ytr = _np.concatenate(labels)
Xtr /= 255
# ... and the fifth as validation set as described in cuda-convnet:
# https://code.google.com/p/cuda-convnet/wiki/Methodology
with f.extractfile('cifar-10-batches-py/data_batch_5') as b:
batch = _pickle.load(b, encoding='latin1')
Xva = _np.array(batch['data'], dtype=_np.float32)
yva = _np.array(batch['labels'])
Xva /= 255
with f.extractfile('cifar-10-batches-py/test_batch') as b:
batch = _pickle.load(b, encoding='latin1')
Xte = _np.array(batch['data'], dtype=_np.float32)
yte = _np.array(batch['labels'])
Xte /= 255
return (Xtr, ytr), (Xva, yva), (Xte, yte)
def data():
fname = _download(
'http://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz')
with _taropen(fname, 'r') as f:
with f.extractfile('cifar-100-python/train') as train:
train = _pickle.load(train, encoding='latin1')
Xtr = _np.array(train['data'], dtype=_np.float32)
ytr_c = _np.array(train['coarse_labels'])
ytr_f = _np.array(train['fine_labels'])
Xtr /= 255
# There is no "official" validation set here that I know of!
# But the maxout paper uses the last 10k samples as validation.
Xtr, Xva = Xtr[:-10000], Xtr[-10000:]
ytr_c, yva_c = ytr_c[:-10000], ytr_c[-10000:]
ytr_f, yva_f = ytr_f[:-10000], ytr_f[-10000:]
with f.extractfile('cifar-100-python/test') as test:
test = _pickle.load(test, encoding='latin1')
Xte = _np.array(test['data'], dtype=_np.float32)
yte_c = _np.array(test['coarse_labels'])
yte_f = _np.array(test['fine_labels'])
Xte /= 255
# Get the label names additionally.
with f.extractfile('cifar-100-python/meta') as m:
m = _pickle.load(m, encoding='latin1')
try:
from sklearn.preprocessing import LabelEncoder
le_c = LabelEncoder()
le_c.classes_ = _np.array(m['coarse_label_names'])
le_f = LabelEncoder()
le_f.classes_ = _np.array(m['fine_label_names'])
except ImportError:
le_c = _np.array(m['coarse_label_names'])
le_f = _np.array(m['fine_label_names'])
return (Xtr, ytr_c, ytr_f), (Xva, yva_c, yva_f), (Xte, yte_c,
yte_f), (le_c, le_f)