def cifar10_load_data(path):
"""Loads CIFAR10 dataset.
# Returns
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
dirname = 'cifar-10-batches-py'
# origin = 'http://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
# path = get_file(dirname, origin=origin, untar=True)
path_ = os.path.join(path, dirname)
num_train_samples = 50000
x_train = np.zeros((num_train_samples, 3, 32, 32), dtype='uint8')
y_train = np.zeros((num_train_samples,), dtype='uint8')
for i in range(1, 6):
fpath = os.path.join(path_, 'data_batch_' + str(i))
data, labels = cifar10.load_batch(fpath)
x_train[(i - 1) * 10000: i * 10000, :, :, :] = data
y_train[(i - 1) * 10000: i * 10000] = labels
fpath = os.path.join(path_, 'test_batch')
x_test, y_test = cifar10.load_batch(fpath)
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
if KB.image_data_format() == 'channels_last':
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
return (x_train, y_train), (x_test, y_test)
def cifar10_load_data(path):
"""Loads CIFAR10 dataset.
# Returns
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
dirname = 'cifar-10-batches-py'
# origin = 'http://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
# path = get_file(dirname, origin=origin, untar=True)
path_ = os.path.join(path, dirname)
num_train_samples = 50000
x_train = np.zeros((num_train_samples, 3, 32, 32), dtype='uint8')
y_train = np.zeros((num_train_samples, ), dtype='uint8')
for i in range(1, 6):
fpath = os.path.join(path_, 'data_batch_' + str(i))
data, labels = cifar10.load_batch(fpath)
x_train[(i - 1) * 10000:i * 10000, :, :, :] = data
y_train[(i - 1) * 10000:i * 10000] = labels
fpath = os.path.join(path_, 'test_batch')
x_test, y_test = cifar10.load_batch(fpath)
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
if KB.image_data_format() == 'channels_last':
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
return (x_train, y_train), (x_test, y_test)
def load_data(data_path=None):
if data_path == None:
path = cifar10_path
else:
path = data_path
num_train_samples = 50000
x_train = np.zeros((num_train_samples, 3, 32, 32), dtype='uint8')
y_train = np.zeros((num_train_samples,), dtype='uint8')
for i in range(1, 6):
fpath = os.path.join(path, 'data_batch_' + str(i))
data, labels = cifar10.load_batch(fpath)
x_train[(i - 1) * 10000: i * 10000, :, :, :] = data
y_train[(i - 1) * 10000: i * 10000] = labels
fpath = os.path.join(path, 'test_batch')
x_test, y_test = cifar10.load_batch(fpath)
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
if K.image_data_format() == 'channels_last':
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
print "loading data done."
return (x_train, y_train), (x_test, y_test)
def load_data_said(org='https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'):
"""Loads CIFAR10 dataset.
# Returns
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
dirname = 'cifar-10-batches-py'
origin = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
path = get_file(dirname, origin=origin, untar=True)
num_train_samples = 50000
x_train = np.empty((num_train_samples, 3, 32, 32), dtype='uint8')
y_train = np.empty((num_train_samples,), dtype='uint8')
for i in range(1, 6):
fpath = os.path.join(path, 'data_batch_' + str(i))
(x_train[(i - 1) * 10000: i * 10000, :, :, :],
y_train[(i - 1) * 10000: i * 10000]) = load_batch(fpath)
fpath = os.path.join(path, 'test_batch')
x_test, y_test = load_batch(fpath)
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
if K.image_data_format() == 'channels_last':
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
return (x_train, y_train), (x_test, y_test)
def load_data():
path = 'data/cifar-10-batches-py'
num_train_samples = 50000
x_train = np.zeros((num_train_samples, 3, 32, 32), dtype='uint8')
y_train = np.zeros((num_train_samples,), dtype='uint8')
for i in range(1, 6):
data, labels = load_batch(os.path.join(path, 'data_batch_' + str(i)))
x_train[(i - 1) * 10000: i * 10000, :, :, :] = data
y_train[(i - 1) * 10000: i * 10000] = labels
x_test, y_test = load_batch(os.path.join(path, 'test_batch'))
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
return (x_train, y_train), (x_test, y_test)
def __load_data(self, data_dir=None):
if data_dir is None:
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
else:
x_train = np.zeros((50000, 3, 32, 32), dtype='uint8')
y_train = np.zeros((50000,), dtype='uint8')
for i in range(1, 6):
fpath = os.path.join(data_dir, 'data_batch_' + str(i))
data, labels = cifar10.load_batch(fpath)
x_train[(i - 1) * 10000: i * 10000, :, :, :] = data
y_train[(i - 1) * 10000: i * 10000] = labels
fpath = os.path.join(data_dir, 'test_batch')
x_test, y_test = cifar10.load_batch(fpath)
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
# Ready the data for use in networks
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
y_train = keras.utils.to_categorical(y_train, 10)
y_test = keras.utils.to_categorical(y_test, 10)
# Data comes as channel first. Transpose the dimensions if necessary
if K.image_data_format() == 'channels_last':
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
# Split off validation data in the ratio described in the paper
x_train, x_val, y_train, y_val = train_test_split(
x_train, y_train, test_size=0.1)
return {
'x_train': x_train,
'x_test': x_test,
'x_val': x_val,
'y_train': y_train,
'y_test': y_test,
'y_val': y_val
}
def test_time(model):
path = cifar10_path
num_samples = 32
x_ = np.zeros((num_samples, 3, 32, 32), dtype='uint8')
fpath = os.path.join(path, 'data_batch_' + str(1))
data, labels = cifar10.load_batch(fpath)
x_[:,:,:,:]=data[:num_samples,:,:,:]
if K.image_data_format() == 'channels_last':
x_ = x_.transpose(0, 2, 3, 1)
x_ = x_.astype('float32') / 255
x_mean = np.mean(x_, axis=0)
x_ -= x_mean
model.predict(x_)
start_time = time.time()
model.predict(x_)
end_time = time.time()
cprint('Time used:' + str(end_time - start_time), 'red')
