149 lines
5.4 KiB
Python
149 lines
5.4 KiB
Python
|
|
#!/usr/bin/env python
|
|
|
|
"""Functions for downloading and reading MNIST data."""
|
|
import gzip
|
|
import os
|
|
from six.moves import xrange
|
|
from six.moves.urllib.request import urlretrieve
|
|
import numpy
|
|
|
|
def _read32(bytestream):
|
|
dt = numpy.dtype(numpy.uint32).newbyteorder('>')
|
|
return numpy.frombuffer(bytestream.read(4), dtype=dt)[0]
|
|
|
|
|
|
def extract_images(filename):
|
|
"""Extract the images into a 4D uint8 numpy array [index, y, x, depth]."""
|
|
print('Extracting', filename)
|
|
with gzip.open(filename) as bytestream:
|
|
magic = _read32(bytestream)
|
|
if magic != 2051:
|
|
raise ValueError(
|
|
'Invalid magic number %d in MNIST image file: %s' %
|
|
(magic, filename))
|
|
num_images = _read32(bytestream)
|
|
rows = _read32(bytestream)
|
|
cols = _read32(bytestream)
|
|
buf = bytestream.read(rows * cols * num_images)
|
|
data = numpy.frombuffer(buf, dtype=numpy.uint8)
|
|
data = data.reshape(num_images, rows, cols, 1)
|
|
return data
|
|
|
|
|
|
def dense_to_one_hot(labels_dense, num_classes=10):
|
|
"""Convert class labels from scalars to one-hot vectors."""
|
|
num_labels = labels_dense.shape[0]
|
|
index_offset = numpy.arange(num_labels) * num_classes
|
|
labels_one_hot = numpy.zeros((num_labels, num_classes))
|
|
labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
|
|
return labels_one_hot
|
|
|
|
|
|
def extract_labels(filename, one_hot=False):
|
|
"""Extract the labels into a 1D uint8 numpy array [index]."""
|
|
print('Extracting', filename)
|
|
with gzip.open(filename) as bytestream:
|
|
magic = _read32(bytestream)
|
|
if magic != 2049:
|
|
raise ValueError(
|
|
'Invalid magic number %d in MNIST label file: %s' %
|
|
(magic, filename))
|
|
num_items = _read32(bytestream)
|
|
buf = bytestream.read(num_items)
|
|
labels = numpy.frombuffer(buf, dtype=numpy.uint8)
|
|
if one_hot:
|
|
return dense_to_one_hot(labels)
|
|
return labels
|
|
|
|
|
|
class DataSet(object):
|
|
def __init__(self, images, labels, fake_data=False):
|
|
if fake_data:
|
|
self._num_examples = 10000
|
|
else:
|
|
assert images.shape[0] == labels.shape[0], (
|
|
"images.shape: %s labels.shape: %s" % (images.shape,
|
|
labels.shape))
|
|
self._num_examples = images.shape[0]
|
|
# Convert shape from [num examples, rows, columns, depth]
|
|
# to [num examples, rows*columns] (assuming depth == 1)
|
|
assert images.shape[3] == 1
|
|
images = images.reshape(images.shape[0],
|
|
images.shape[1] * images.shape[2])
|
|
# Convert from [0, 255] -> [0.0, 1.0].
|
|
images = images.astype(numpy.float32)
|
|
images = numpy.multiply(images, 1.0 / 255.0)
|
|
self._images = images
|
|
self._labels = labels
|
|
self._epochs_completed = 0
|
|
self._index_in_epoch = 0
|
|
|
|
@property
|
|
def images(self):
|
|
return self._images
|
|
|
|
@property
|
|
def labels(self):
|
|
return self._labels
|
|
|
|
@property
|
|
def num_examples(self):
|
|
return self._num_examples
|
|
|
|
@property
|
|
def epochs_completed(self):
|
|
return self._epochs_completed
|
|
|
|
def next_batch(self, batch_size, fake_data=False):
|
|
"""Return the next `batch_size` examples from this data set."""
|
|
if fake_data:
|
|
fake_image = [1.0 for _ in xrange(784)]
|
|
fake_label = 0
|
|
return [fake_image for _ in xrange(batch_size)], [
|
|
fake_label for _ in xrange(batch_size)]
|
|
start = self._index_in_epoch
|
|
self._index_in_epoch += batch_size
|
|
if self._index_in_epoch > self._num_examples:
|
|
# Finished epoch
|
|
self._epochs_completed += 1
|
|
# Shuffle the data
|
|
perm = numpy.arange(self._num_examples)
|
|
numpy.random.shuffle(perm)
|
|
self._images = self._images[perm]
|
|
self._labels = self._labels[perm]
|
|
# Start next epoch
|
|
start = 0
|
|
self._index_in_epoch = batch_size
|
|
assert batch_size <= self._num_examples
|
|
end = self._index_in_epoch
|
|
return self._images[start:end], self._labels[start:end]
|
|
|
|
|
|
def read_data_sets(train_images_file, train_labels_file, test_images_file, test_labels_file, fake_data=False, one_hot=False):
|
|
class DataSets(object):
|
|
pass
|
|
data_sets = DataSets()
|
|
if fake_data:
|
|
data_sets.train = DataSet([], [], fake_data=True)
|
|
data_sets.validation = DataSet([], [], fake_data=True)
|
|
data_sets.test = DataSet([], [], fake_data=True)
|
|
return data_sets
|
|
TRAIN_IMAGES = train_images_file
|
|
TRAIN_LABELS = train_labels_file
|
|
TEST_IMAGES = test_images_file
|
|
TEST_LABELS = test_labels_file
|
|
VALIDATION_SIZE = 5000
|
|
train_images = extract_images(TRAIN_IMAGES)
|
|
train_labels = extract_labels(TRAIN_LABELS, one_hot=one_hot)
|
|
test_images = extract_images(TEST_IMAGES)
|
|
test_labels = extract_labels(TEST_LABELS, one_hot=one_hot)
|
|
validation_images = train_images[:VALIDATION_SIZE]
|
|
validation_labels = train_labels[:VALIDATION_SIZE]
|
|
train_images = train_images[VALIDATION_SIZE:]
|
|
train_labels = train_labels[VALIDATION_SIZE:]
|
|
data_sets.train = DataSet(train_images, train_labels)
|
|
data_sets.validation = DataSet(validation_images, validation_labels)
|
|
data_sets.test = DataSet(test_images, test_labels)
|
|
return data_sets
|