def test_in_memory():
skip_if_not_available(datasets=['mnist.hdf5'])
# Load MNIST and get two batches
mnist = MNIST('train', load_in_memory=True)
data_stream = DataStream(mnist,
iteration_scheme=SequentialScheme(
examples=mnist.num_examples, batch_size=256))
epoch = data_stream.get_epoch_iterator()
for i, (features, targets) in enumerate(epoch):
if i == 1:
break
handle = mnist.open()
known_features, _ = mnist.get_data(handle, slice(256, 512))
mnist.close(handle)
assert numpy.all(features == known_features)
# Pickle the epoch and make sure that the data wasn't dumped
with tempfile.NamedTemporaryFile(delete=False) as f:
filename = f.name
cPickle.dump(epoch, f)
assert os.path.getsize(filename) < 1024 * 1024 # Less than 1MB
# Reload the epoch and make sure that the state was maintained
del epoch
with open(filename, 'rb') as f:
epoch = cPickle.load(f)
features, targets = next(epoch)
handle = mnist.open()
known_features, _ = mnist.get_data(handle, slice(512, 768))
mnist.close(handle)
assert numpy.all(features == known_features)
def test_in_memory():
skip_if_not_available(datasets=['mnist.hdf5'])
# Load MNIST and get two batches
mnist = MNIST(('train',), load_in_memory=True)
data_stream = DataStream(mnist, iteration_scheme=SequentialScheme(
examples=mnist.num_examples, batch_size=256))
epoch = data_stream.get_epoch_iterator()
for i, (features, targets) in enumerate(epoch):
if i == 1:
break
handle = mnist.open()
known_features, _ = mnist.get_data(handle, slice(256, 512))
mnist.close(handle)
assert numpy.all(features == known_features)
# Pickle the epoch and make sure that the data wasn't dumped
with tempfile.NamedTemporaryFile(delete=False) as f:
filename = f.name
cPickle.dump(epoch, f)
assert os.path.getsize(filename) < 1024 * 1024 # Less than 1MB
# Reload the epoch and make sure that the state was maintained
del epoch
with open(filename, 'rb') as f:
epoch = cPickle.load(f)
features, targets = next(epoch)
handle = mnist.open()
known_features, _ = mnist.get_data(handle, slice(512, 768))
mnist.close(handle)
assert numpy.all(features == known_features)
def test_mnist_test():
skip_if_not_available(datasets=["mnist.hdf5"])
dataset = MNIST(("test",), load_in_memory=False)
handle = dataset.open()
data, labels = dataset.get_data(handle, slice(0, 10))
assert data.dtype == "uint8"
assert data.shape == (10, 1, 28, 28)
assert labels.shape == (10, 1)
known = numpy.array([0, 0, 0, 0, 0, 0, 84, 185, 159, 151, 60, 36, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
assert_allclose(data[0][0][7], known)
assert labels[0][0] == 7
assert dataset.num_examples == 10000
dataset.close(handle)
stream = DataStream.default_stream(dataset, iteration_scheme=SequentialScheme(10, 10))
data = next(stream.get_epoch_iterator())[0]
assert data.min() >= 0.0 and data.max() <= 1.0
assert data.dtype == config.floatX
def test_mnist_train():
skip_if_not_available(datasets=['mnist.hdf5'])
dataset = MNIST('train', load_in_memory=False)
handle = dataset.open()
data, labels = dataset.get_data(handle, slice(0, 10))
assert data.dtype == 'uint8'
assert data.shape == (10, 1, 28, 28)
assert labels.shape == (10, 1)
known = numpy.array([0, 0, 0, 0, 0, 0, 0, 0, 30, 36, 94, 154, 170, 253,
253, 253, 253, 253, 225, 172, 253, 242, 195, 64, 0,
0, 0, 0])
assert_allclose(data[0][0][6], known)
assert labels[0][0] == 5
assert dataset.num_examples == 60000
dataset.close(handle)
stream = DataStream.default_stream(
dataset, iteration_scheme=SequentialScheme(10, 10))
data = next(stream.get_epoch_iterator())[0]
assert data.min() >= 0.0 and data.max() <= 1.0
assert data.dtype == config.floatX
def test_mnist_test():
skip_if_not_available(datasets=['mnist.hdf5'])
dataset = MNIST('test', load_in_memory=False)
handle = dataset.open()
data, labels = dataset.get_data(handle, slice(0, 10))
assert data.dtype == 'uint8'
assert data.shape == (10, 1, 28, 28)
assert labels.shape == (10, 1)
known = numpy.array([
0, 0, 0, 0, 0, 0, 84, 185, 159, 151, 60, 36, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0
])
assert_allclose(data[0][0][7], known)
assert labels[0][0] == 7
assert dataset.num_examples == 10000
dataset.close(handle)
stream = DataStream.default_stream(dataset,
iteration_scheme=SequentialScheme(
10, 10))
data = next(stream.get_epoch_iterator())[0]
assert data.min() >= 0.0 and data.max() <= 1.0
assert data.dtype == config.floatX
from fuel.datasets import MNIST
from fuel.schemes import SequentialScheme
from fuel.transformers import Mapping, Flatten
from blocks.graph import ComputationGraph
from blocks.monitoring import aggregation
from blocks.extensions import FinishAfter, Timing, Printing
from blocks.extensions.monitoring import (DataStreamMonitoring,
TrainingDataMonitoring)
from blocks.main_loop import MainLoop
from blocks_contrib.extensions import DataStreamMonitoringAndSaving
floatX = theano.config.floatX
mnist = MNIST('train', sources=['features'])
handle = mnist.open()
data = mnist.get_data(handle, slice(0, 50000))[0]
means = data.reshape((50000, 784)).mean(axis=0)
def autocorrentropy2(X, ksize=np.inf):
b, t, d = X.shape
V = np.zeros((b, t, d))
for i in range(b):
for j in range(t):
if ksize in (np.inf, 0., np.nan):
V[i, j, :] = (X[i, :(t-j), :] * X[i, j:, :]).sum(axis=0) / (t-j)
else:
V[i, j, :] = np.exp((-ksize * (X[i, :(t-j), :]-X[i, j:, :])**2)).sum(axis=0) / (t-j)
return V
for x, y in zip(trX, trY):
train(x, y)
print(w.get_value()) #something around 2
#https://raw.githubusercontent.com/Newmu/Theano-Tutorials/master/2_logistic_regression.py
import theano
from theano import tensor as T
import numpy as np
from fuel.datasets import MNIST
from matplotlib import pyplot, cm
dataset = MNIST(('train',), sources=('features',))
state = dataset.open()
image, = dataset.get_data(state=state, request=[1234])
pyplot.imshow(image.reshape((28, 28)), cmap=cm.Greys_r, interpolation='nearest')
pyplot.show()
dataset.close(state)
def floatX(X):
return np.asarray(X, dtype=theano.config.floatX)
def init_weights(shape):
return theano.shared(floatX(np.random.randn(*shape) * 0.01))
def model(X, w):
return T.nnet.softmax(T.dot(X, w))
trX, teX, trY, teY = mnist(onehot=True)
