def __init__(self, dataset='mnist', data_path='..\\..\\..\\MNIST\\',
file_sample='train-images.idx3-ubyte', file_label='train-labels.idx1-ubyte',
is_normalize=True, par_pool=None):
# MNIST files for training: 'train-images.idx3-ubyte', 'train-labels.idx1-ubyte'
# MNIST files for testing: 't10k-images.idx3-ubyte', 't10k-labels.idx1-ubyte'
self.dataset = dataset
self.dataInfo = dict()
self.images = bf.decode_idx3_ubyte(path.join(data_path, file_sample))
self.labels = bf.decode_idx1_ubyte(path.join(data_path, file_label))
self.length = self.images.shape[0]
if is_normalize:
self.images /= 256
self.analyse_dataset()
self.tmp = None
self.nPool = par_pool
self.parPool = None
if is_debug:
self.check_consistency()
def load_data(self,
data_path=None,
file_sample=None,
file_label=None,
is_normalize=None):
# MNIST files for training: 'train-images.idx3-ubyte', 'train-labels.idx1-ubyte'
# MNIST files for testing: 't10k-images.idx3-ubyte', 't10k-labels.idx1-ubyte'
if data_path is None:
data_path = self.data_path
if file_label is not None:
self.data_samples = path.join(data_path, file_sample)
if self.is_there_labels:
self.data_labels = path.join(data_path, file_label)
if not (is_normalize is None):
self.is_normalize_data = is_normalize
self.images = bf.decode_idx3_ubyte(self.data_samples)
if self.is_there_labels:
self.labels = bf.decode_idx1_ubyte(self.data_labels)
self.length = self.images.shape[0]
if self.is_normalize_data:
self.images /= (254 * (self.images.max() > 2) + 1)