def test_rbm(learning_rate=0.1, training_epochs=15,
dataset='mnist.pkl.gz', batch_size=20,
n_chains=20, n_samples=10, output_folder='rbm_plots',
n_hidden=500):
"""
Demonstrate how to train and afterwards sample from it using Theano.
This is demonstrated on MNIST.
:param learning_rate: learning rate used for training the RBM
:param training_epochs: number of epochs used for training
:param dataset: path the the pickled dataset
:param batch_size: size of a batch used to train the RBM
:param n_chains: number of parallel Gibbs chains to be used for sampling
:param n_samples: number of samples to plot for each chain
"""
datasets = load_data(dataset)
train_set_x, train_set_y = datasets[0]
test_set_x, test_set_y = datasets[2]
# compute number of minibatches for training, validation and testing
n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
# 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
rng = numpy.random.RandomState(123)
theano_rng = RandomStreams(rng.randint(2 ** 30))
# initialize storage for the persistent chain (state = hidden
# layer of chain)
persistent_chain = theano.shared(numpy.zeros((batch_size, n_hidden),
dtype=theano.config.floatX),
borrow=True)
# construct the RBM class
rbm = RBM(input=x, n_visible=28 * 28,
n_hidden=n_hidden, numpy_rng=rng, theano_rng=theano_rng)
# get the cost and the gradient corresponding to one step of CD-15
cost, updates = rbm.get_cost_updates(lr=learning_rate,
persistent=persistent_chain, k=15)
#################################
# Training the RBM #
#################################
if not os.path.isdir(output_folder):
os.makedirs(output_folder)
os.chdir(output_folder)
# it is ok for a theano function to have no output
# the purpose of train_rbm is solely to update the RBM parameters
train_rbm = theano.function([index], cost,
updates=updates,
givens={x: train_set_x[index * batch_size:
(index + 1) * batch_size]},
name='train_rbm')
plotting_time = 0.
start_time = time.clock()
# go through training epochs
for epoch in xrange(training_epochs):
# go through the training set
mean_cost = []
for batch_index in xrange(n_train_batches):
mean_cost += [train_rbm(batch_index)]
print 'Training epoch %d, cost is ' % epoch, numpy.mean(mean_cost)
# Plot filters after each training epoch
plotting_start = time.clock()
# Construct image from the weight matrix
image = PIL.Image.fromarray(tile_raster_images(
X=rbm.W.get_value(borrow=True).T,
img_shape=(28, 28), tile_shape=(10, 10),
tile_spacing=(1, 1)))
image.save('filters_at_epoch_%i.png' % epoch)
plotting_stop = time.clock()
plotting_time += (plotting_stop - plotting_start)
end_time = time.clock()
pretraining_time = (end_time - start_time) - plotting_time
print ('Training took %f minutes' % (pretraining_time / 60.))
#################################
# Sampling from the RBM #
#################################
# find out the number of test samples
number_of_test_samples = test_set_x.get_value(borrow=True).shape[0]
# pick random test examples, with which to initialize the persistent chain
test_idx = rng.randint(number_of_test_samples - n_chains)
persistent_vis_chain = theano.shared(numpy.asarray(
test_set_x.get_value(borrow=True)[test_idx:test_idx + n_chains],
dtype=theano.config.floatX))
plot_every = 1000
# define one step of Gibbs sampling (mf = mean-field) define a
# function that does `plot_every` steps before returning the
# sample for plotting
[presig_hids, hid_mfs, hid_samples, presig_vis,
vis_mfs, vis_samples], updates = \
theano.scan(rbm.gibbs_vhv,
outputs_info=[None, None, None, None,
None, persistent_vis_chain],
n_steps=plot_every)
# add to updates the shared variable that takes care of our persistent
# chain :.
updates.update({persistent_vis_chain: vis_samples[-1]})
# construct the function that implements our persistent chain.
# we generate the "mean field" activations for plotting and the actual
# samples for reinitializing the state of our persistent chain
sample_fn = theano.function([], [vis_mfs[-1], vis_samples[-1]],
updates=updates,
name='sample_fn')
# create a space to store the image for plotting ( we need to leave
# room for the tile_spacing as well)
image_data = numpy.zeros((29 * n_samples + 1, 29 * n_chains - 1),
dtype='uint8')
for idx in xrange(n_samples):
# generate `plot_every` intermediate samples that we discard,
# because successive samples in the chain are too correlated
vis_mf, vis_sample = sample_fn()
print ' ... plotting sample ', idx
image_data[29 * idx:29 * idx + 28, :] = tile_raster_images(
X=vis_mf,
img_shape=(28, 28),
tile_shape=(1, n_chains),
tile_spacing=(1, 1))
# construct image
image = PIL.Image.fromarray(image_data)
image.save('samples.png')
os.chdir('../')
def test_rbm(learning_rate=0.1,
training_epochs=15,
dataset='mnist.pkl.gz',
batch_size=20,
n_chains=20,
n_samples=10,
output_folder='rbm_plots',
n_hidden=500):
"""
Demonstrate how to train and afterwards sample from it using Theano.
This is demonstrated on MNIST.
:param learning_rate: learning rate used for training the RBM
:param training_epochs: number of epochs used for training
:param dataset: path the the pickled dataset
:param batch_size: size of a batch used to train the RBM
:param n_chains: number of parallel Gibbs chains to be used for sampling
:param n_samples: number of samples to plot for each chain
"""
datasets = load_data(dataset)
train_set_x, train_set_y = datasets[0]
test_set_x, test_set_y = datasets[2]
# compute number of minibatches for training, validation and testing
n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
# 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
rng = numpy.random.RandomState(123)
theano_rng = RandomStreams(rng.randint(2**30))
# initialize storage for the persistent chain (state = hidden
# layer of chain)
persistent_chain = theano.shared(numpy.zeros((batch_size, n_hidden),
dtype=theano.config.floatX),
borrow=True)
# construct the RBM class
rbm = RBM(input=x,
n_visible=28 * 28,
n_hidden=n_hidden,
numpy_rng=rng,
theano_rng=theano_rng)
# get the cost and the gradient corresponding to one step of CD-15
cost, updates = rbm.get_cost_updates(lr=learning_rate,
persistent=persistent_chain,
k=15)
#################################
# Training the RBM #
#################################
if not os.path.isdir(output_folder):
os.makedirs(output_folder)
os.chdir(output_folder)
# it is ok for a theano function to have no output
# the purpose of train_rbm is solely to update the RBM parameters
train_rbm = theano.function(
[index],
cost,
updates=updates,
givens={x: train_set_x[index * batch_size:(index + 1) * batch_size]},
name='train_rbm')
plotting_time = 0.
start_time = time.clock()
# go through training epochs
for epoch in xrange(training_epochs):
# go through the training set
mean_cost = []
for batch_index in xrange(n_train_batches):
mean_cost += [train_rbm(batch_index)]
print 'Training epoch %d, cost is ' % epoch, numpy.mean(mean_cost)
# Plot filters after each training epoch
plotting_start = time.clock()
# Construct image from the weight matrix
image = PIL.Image.fromarray(
tile_raster_images(X=rbm.W.get_value(borrow=True).T,
img_shape=(28, 28),
tile_shape=(10, 10),
tile_spacing=(1, 1)))
image.save('filters_at_epoch_%i.png' % epoch)
plotting_stop = time.clock()
plotting_time += (plotting_stop - plotting_start)
end_time = time.clock()
pretraining_time = (end_time - start_time) - plotting_time
print('Training took %f minutes' % (pretraining_time / 60.))
#################################
# Sampling from the RBM #
#################################
# find out the number of test samples
number_of_test_samples = test_set_x.get_value(borrow=True).shape[0]
# pick random test examples, with which to initialize the persistent chain
test_idx = rng.randint(number_of_test_samples - n_chains)
persistent_vis_chain = theano.shared(
numpy.asarray(test_set_x.get_value(borrow=True)[test_idx:test_idx +
n_chains],
dtype=theano.config.floatX))
plot_every = 1000
# define one step of Gibbs sampling (mf = mean-field) define a
# function that does `plot_every` steps before returning the
# sample for plotting
[presig_hids, hid_mfs, hid_samples, presig_vis,
vis_mfs, vis_samples], updates = \
theano.scan(rbm.gibbs_vhv,
outputs_info=[None, None, None, None,
None, persistent_vis_chain],
n_steps=plot_every)
# add to updates the shared variable that takes care of our persistent
# chain :.
updates.update({persistent_vis_chain: vis_samples[-1]})
# construct the function that implements our persistent chain.
# we generate the "mean field" activations for plotting and the actual
# samples for reinitializing the state of our persistent chain
sample_fn = theano.function([], [vis_mfs[-1], vis_samples[-1]],
updates=updates,
name='sample_fn')
# create a space to store the image for plotting ( we need to leave
# room for the tile_spacing as well)
image_data = numpy.zeros((29 * n_samples + 1, 29 * n_chains - 1),
dtype='uint8')
for idx in xrange(n_samples):
# generate `plot_every` intermediate samples that we discard,
# because successive samples in the chain are too correlated
vis_mf, vis_sample = sample_fn()
print ' ... plotting sample ', idx
image_data[29 * idx:29 * idx + 28, :] = tile_raster_images(
X=vis_mf,
img_shape=(28, 28),
tile_shape=(1, n_chains),
tile_spacing=(1, 1))
# construct image
image = PIL.Image.fromarray(image_data)
image.save('samples.png')
os.chdir('../')
def test_mlp(learning_rate=0.01, L1_reg=0.00, L2_reg=0.0001, n_epochs=1000,
dataset='mnist.pkl.gz', batch_size=20, n_hidden=500):
"""
Demonstrate stochastic gradient descent optimization for a multilayer
perceptron
This is demonstrated on MNIST.
:type learning_rate: float
:param learning_rate: learning rate used (factor for the stochastic
gradient
:type L1_reg: float
:param L1_reg: L1-norm's weight when added to the cost (see
regularization)
:type L2_reg: float
:param L2_reg: L2-norm's weight when added to the cost (see
regularization)
:type n_epochs: int
:param n_epochs: maximal number of epochs to run the optimizer
:type dataset: string
:param dataset: the path of the MNIST dataset file from
http://www.iro.umontreal.ca/~lisa/deep/data/mnist/mnist.pkl.gz
"""
datasets = load_data(dataset)
train_set_x, train_set_y = datasets[0]
valid_set_x, valid_set_y = datasets[1]
test_set_x, test_set_y = datasets[2]
# compute number of minibatches for training, validation and testing
n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
n_valid_batches = valid_set_x.get_value(borrow=True).shape[0] / batch_size
n_test_batches = test_set_x.get_value(borrow=True).shape[0] / batch_size
######################
# BUILD ACTUAL MODEL #
######################
print '... building the model'
# 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
y = T.ivector('y') # the labels are presented as 1D vector of
# [int] labels
rng = numpy.random.RandomState(1234)
# construct the MLP class
classifier = MLP(rng=rng, input=x, n_in=28 * 28,
n_hidden=n_hidden, n_out=10)
# the cost we minimize during training is the negative log likelihood of
# the model plus the regularization terms (L1 and L2); cost is expressed
# here symbolically
cost = classifier.negative_log_likelihood(y) \
+ L1_reg * classifier.L1 \
+ L2_reg * classifier.L2_sqr
# compiling a Theano function that computes the mistakes that are made
# by the model on a minibatch
test_model = theano.function(inputs=[index],
outputs=classifier.errors(y),
givens={
x: test_set_x[index * batch_size:(index + 1) * batch_size],
y: test_set_y[index * batch_size:(index + 1) * batch_size]})
validate_model = theano.function(inputs=[index],
outputs=classifier.errors(y),
givens={
x: valid_set_x[index * batch_size:(index + 1) * batch_size],
y: valid_set_y[index * batch_size:(index + 1) * batch_size]})
# compute the gradient of cost with respect to theta (sotred in params)
# the resulting gradients will be stored in a list gparams
gparams = []
for param in classifier.params:
gparam = T.grad(cost, param)
gparams.append(gparam)
# specify how to update the parameters of the model as a list of
# (variable, update expression) pairs
updates = []
# given two list the zip A = [a1, a2, a3, a4] and B = [b1, b2, b3, b4] of
# same length, zip generates a list C of same size, where each element
# is a pair formed from the two lists :
# C = [(a1, b1), (a2, b2), (a3, b3), (a4, b4)]
for param, gparam in zip(classifier.params, gparams):
updates.append((param, param - learning_rate * gparam))
# compiling a Theano function `train_model` that returns the cost, but
# in the same time updates the parameter of the model based on the rules
# defined in `updates`
train_model = theano.function(inputs=[index], outputs=cost,
updates=updates,
givens={
x: train_set_x[index * batch_size:(index + 1) * batch_size],
y: train_set_y[index * batch_size:(index + 1) * batch_size]})
###############
# TRAIN MODEL #
###############
print '... training'
# early-stopping parameters
patience = 10000 # look as this many examples regardless
patience_increase = 2 # wait this much longer when a new best is
# found
improvement_threshold = 0.995 # a relative improvement of this much is
# considered significant
validation_frequency = min(n_train_batches, patience / 2)
# go through this many
# minibatche before checking the network
# on the validation set; in this case we
# check every epoch
best_params = None
best_validation_loss = numpy.inf
best_iter = 0
test_score = 0.
start_time = time.clock()
epoch = 0
done_looping = False
while (epoch < n_epochs) and (not done_looping):
epoch = epoch + 1
for minibatch_index in xrange(n_train_batches):
minibatch_avg_cost = train_model(minibatch_index)
# iteration number
iter = (epoch - 1) * n_train_batches + minibatch_index
if (iter + 1) % validation_frequency == 0:
# compute zero-one loss on validation set
validation_losses = [validate_model(i) for i
in xrange(n_valid_batches)]
this_validation_loss = numpy.mean(validation_losses)
print('epoch %i, minibatch %i/%i, validation error %f %%' %
(epoch, minibatch_index + 1, n_train_batches,
this_validation_loss * 100.))
# if we got the best validation score until now
if this_validation_loss < best_validation_loss:
#improve patience if loss improvement is good enough
if this_validation_loss < best_validation_loss * \
improvement_threshold:
patience = max(patience, iter * patience_increase)
best_validation_loss = this_validation_loss
best_iter = iter
# test it on the test set
test_losses = [test_model(i) for i
in xrange(n_test_batches)]
test_score = numpy.mean(test_losses)
print((' epoch %i, minibatch %i/%i, test error of '
'best model %f %%') %
(epoch, minibatch_index + 1, n_train_batches,
test_score * 100.))
if patience <= iter:
done_looping = True
break
end_time = time.clock()
print(('Optimization complete. Best validation score of %f %% '
'obtained at iteration %i, with test performance %f %%') %
(best_validation_loss * 100., best_iter + 1, test_score * 100.))
print >> sys.stderr, ('The code for file ' +
os.path.split(__file__)[1] +
' ran for %.2fm' % ((end_time - start_time) / 60.))
