def train(self, train_data):
index = T.lscalar()
x = T.matrix('x')
cost,updates=self.get_cost_updates(x)
train_da = th.function(
[index],
cost,
updates=updates,
givens={
x: train_data[index * self.batch_size: (index + 1) * self.batch_size]
}
)
n_train_batches = (int) (train_data.get_value(borrow=True).shape[0] / self.batch_size)
start_time = timeit.default_timer()
for epoch in range(self.training_epochs):
# go through trainng set
c = []
for batch_index in range(int(n_train_batches)):
c.append(train_da(batch_index))
print ('Training epoch %d, cost ' % epoch, np.mean(c))
end_time = timeit.default_timer()
training_time = (end_time - start_time)
print (('The no corruption code for file ' +
os.path.split(__file__)[1] +
' ran for %.2fm' % ((training_time) / 60.)))
image = Image.fromarray(
tile_raster_images(X=self.W.get_value(borrow=True).T,
img_shape=(28, 28), tile_shape=(10, 10),
tile_spacing=(1, 1)))
image.save('filters_corruption_0.png')
def fit(self, train_data, batch_size, training_epochs, learning_rate):
self.net.fit(train_data, train_data, batch_size, training_epochs, learning_rate)
image = Image.fromarray(
tile_raster_images(X=self.net.connections[0].W.get_value(borrow=True).T,
img_shape=(28, 28), tile_shape=(10, 10),
tile_spacing=(1, 1)))
image.save('test_ae.png')
def fit(self, train_data, batch_size, training_epochs, learning_rate, knowledge=None, l=None, llamda=None):
if l is not None:
self.setRegularization(l, llamda)
self.knowledge=knowledge
NNNet.fit(self, train_data, train_data, batch_size, training_epochs, learning_rate)
image = Image.fromarray(
tile_raster_images(X=self.connections[0].W.get_value(borrow=True).T,
img_shape=(np.sqrt(self.nIn), np.sqrt(self.nIn)), tile_shape=(10, 10),
tile_spacing=(1, 1)))
image.save('test'+self.id+ '.png')
def test_dA(learning_rate=0.1, training_epochs=5,
dataset='/Users/quynhdo/Downloads/mnist.pkl',
batch_size=20, output_folder='dA_plots'):
"""
This demo is tested on MNIST
:type learning_rate: float
:param learning_rate: learning rate used for training the DeNosing
AutoEncoder
:type training_epochs: int
:param training_epochs: number of epochs used for training
:type dataset: string
:param dataset: path to the picked dataset
"""
datasets = load_data(dataset)
train_set_x, train_set_y = datasets[0]
# compute number of minibatches for training, validation and testing
n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
# start-snippet-2
# allocate symbolic variables for the data
index = T.lscalar() # index to a [mini]batch
x = T.matrix('x') # the data is presented as rasterized images
# end-snippet-2
if not os.path.isdir(output_folder):
os.makedirs(output_folder)
os.chdir(output_folder)
####################################
# BUILDING THE MODEL NO CORRUPTION #
####################################
rng = numpy.random.RandomState(123)
theano_rng = RandomStreams(rng.randint(2 ** 30))
da = dA(
numpy_rng=rng,
theano_rng=theano_rng,
input=x,
n_visible=28 * 28,
n_hidden=500
)
cost, updates = da.get_cost_updates(
corruption_level=0.,
learning_rate=learning_rate
)
train_da = theano.function(
[index],
cost,
updates=updates,
givens={
x: train_set_x[index * batch_size: (index + 1) * batch_size]
}
)
start_time = timeit.default_timer()
############
# TRAINING #
############
# go through training epochs
for epoch in range(training_epochs):
# go through trainng set
c = []
for batch_index in range(int(n_train_batches)):
c.append(train_da(batch_index))
print ('Training epoch %d, cost ' % epoch, numpy.mean(c))
end_time = timeit.default_timer()
training_time = (end_time - start_time)
print (('The no corruption code for file ' +
os.path.split(__file__)[1] +
' ran for %.2fm' % ((training_time) / 60.)))
image = Image.fromarray(
tile_raster_images(X=da.W.get_value(borrow=True).T,
img_shape=(28, 28), tile_shape=(10, 10),
tile_spacing=(1, 1)))
image.save('filters_corruption_0.png')
# start-snippet-3
#####################################
# BUILDING THE MODEL CORRUPTION 30% #
#####################################
rng = numpy.random.RandomState(123)
theano_rng = RandomStreams(rng.randint(2 ** 30))
da = dA(
numpy_rng=rng,
theano_rng=theano_rng,
input=x,
n_visible=28 * 28,
n_hidden=500
)
cost, updates = da.get_cost_updates(
corruption_level=0.3,
learning_rate=learning_rate
)
train_da = theano.function(
[index],
cost,
updates=updates,
givens={
x: train_set_x[index * batch_size: (index + 1) * batch_size]
}
)
start_time = timeit.default_timer()
############
# TRAINING #
############
# go through training epochs
for epoch in range(training_epochs):
# go through trainng set
c = []
for batch_index in range(int(n_train_batches)):
c.append(train_da(batch_index))
print ('Training epoch %d, cost ' % epoch, numpy.mean(c))
end_time = timeit.default_timer()
training_time = (end_time - start_time)
print ( ('The 30% corruption code for file ' +
os.path.split(__file__)[1] +
' ran for %.2fm' % (training_time / 60.)))
# end-snippet-3
# start-snippet-4
image = Image.fromarray(tile_raster_images(
X=da.W.get_value(borrow=True).T,
img_shape=(28, 28), tile_shape=(10, 10),
tile_spacing=(1, 1)))
image.save('filters_corruption_30.png')
# end-snippet-4
os.chdir('../')
