Hu guys,
I\'m new to python/anaconda/jupyter/numPy, panda, etc.... so please excuse me if it\'s a really stupid question. I\'m trying to obtain MNIST database by using a
Found a good solution here: https://github.com/Lasagne/Lasagne/blob/master/examples/mnist.py
It downloads dataset from Yan LeCun's website (http://yann.lecun.com/exdb/mnist/).
import os
from urllib import urlretrieve
def download(filename, source='http://yann.lecun.com/exdb/mnist/'):
print("Downloading %s" % filename)
urlretrieve(source + filename, filename)
# We then define functions for loading MNIST images and labels.
# For convenience, they also download the requested files if needed.
import gzip
def load_mnist_images(filename):
if not os.path.exists(filename):
download(filename)
# Read the inputs in Yann LeCun's binary format.
with gzip.open(filename, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=16)
# The inputs are vectors now, we reshape them to monochrome 2D images,
# following the shape convention: (examples, channels, rows, columns)
data = data.reshape(-1, 1, 28, 28)
# The inputs come as bytes, we convert them to float32 in range [0,1].
# (Actually to range [0, 255/256], for compatibility to the version
# provided at http://deeplearning.net/data/mnist/mnist.pkl.gz.)
return data / np.float32(256)
def load_mnist_labels(filename):
if not os.path.exists(filename):
download(filename)
# Read the labels in Yann LeCun's binary format.
with gzip.open(filename, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=8)
# The labels are vectors of integers now, that's exactly what we want.
return data
X_train = load_mnist_images('train-images-idx3-ubyte.gz')
y_train = load_mnist_labels('train-labels-idx1-ubyte.gz')
X_test = load_mnist_images('t10k-images-idx3-ubyte.gz')
y_test = load_mnist_labels('t10k-labels-idx1-ubyte.gz')