def _set_model(self, data_set, errors, batch_size=None):
set_x, set_y = data_set
if batch_size is None:
model = my_theano.function([], errors, givens={
self.x: set_x,
self.y: set_y
})
else:
index = self.index
model = my_theano.function([index], errors, givens={
self.x: self._get_mini_batch(set_x, batch_size, index),
self.y: self._get_mini_batch(set_y, batch_size, index),
})
return model
def _set_train_model(self, train_set, cost, batch_size, learning_rate):
print('compiling train model..')
# compute gradients of weights and biases
updates = []
for i in range(self.depth):
g_w = T.grad(cost, self.weights[i])
g_b = T.grad(cost, self.biases[i])
updates += [(self.weights[i], self.weights[i] - learning_rate * g_w),
(self.biases[i], self.biases[i] - learning_rate * g_b)]
# print(self.train_set[1:3])
train_set_x, train_set_y = train_set
index = self.index
self.train_model = my_theano.function([index], cost, updates=updates, givens={
self.x: self._get_mini_batch(train_set_x, batch_size, index),
self.y: self._get_mini_batch(train_set_y, batch_size, index)
})
if any([x.op.__class__.__name__ in ['Gemv', 'CGemv', 'Gemm', 'CGemm'] for x in
self.train_model.maker.fgraph.toposort()]):
print('Used the cpu')
elif any([x.op.__class__.__name__ in ['GpuGemm', 'GpuGemv'] for x in
self.train_model.maker.fgraph.toposort()]):
print('Used the gpu')
else:
print('ERROR, not able to tell if my_theano used the cpu or the gpu')
print(self.train_model.maker.fgraph.toposort())
def get_b(self):
print('_get_b:')
layer = self.weighted_layers[1]
print(layer.b.get_value())
# print(layer.w.get_value())
_get_b = my_theano.function([], layer.b)
print(_get_b())
def set_train_model(self, train_set, cost_func, batch_size, learning_rate, l1_a=0.0, l2_a=0.0001):
cost = cost_func(self.p_y, self.y) \
+ self.l1 * l1_a + self.l2 * l2_a
print('compiling train model..')
# compute gradients of weights and biases
updates = []
for i in range(self.depth):
g_w = T.grad(cost, self.weights[i])
g_b = T.grad(cost, self.biases[i])
updates += [(self.weights[i], self.weights[i] - learning_rate * g_w),
(self.biases[i], self.biases[i] - learning_rate * g_b)]
# print(self.train_set[1:3])
train_set_x, train_set_y = train_set
index = self.index
self.train_model = my_theano.function([index], cost, updates=updates, givens={
self.x: self._get_mini_batch(train_set_x, batch_size, index),
self.y: self._get_mini_batch(train_set_y, batch_size, index)
})
# check if using gpu
tu.check_gpu(self.train_model)
def get_b(self):
print('_get_b:')
layer = self.weighted_layers[1]
print(layer.b.get_value())
# print(layer.w.get_value())
_get_b = my_theano.function([], layer.b)
print(_get_b())
def set_train_model(self, train_set, cost_func, batch_size, learning_rate, l1_a=0.0, l2_a=0.0001):
self.p_y = self.forward(self.x, batch_size)
cost = cost_func(self.p_y, self.y) + self.l1 * l1_a + self.l2 * l2_a
# set early stopping patience
self.patience = 20
self.lest_valid_error = np.inf
print('compiling train model..')
# compute gradients of weights and biases
updates = []
for layer in reversed(self.weighted_layers):
g_w = T.grad(cost, layer.w)
g_b = T.grad(cost, layer.b)
updates += [(layer.w, layer.w - learning_rate * g_w),
(layer.b, layer.b - learning_rate * g_b)]
train_set_x, train_set_y = train_set
index = self.index
self.train_model = my_theano.function([index], cost, updates=updates, givens={
self.x: self._get_mini_batch(train_set_x, batch_size, index),
self.y: self._get_mini_batch(train_set_y, batch_size, index)
})
# check if using gpu
tu.check_gpu(self.train_model)
def _set_model(self, data_set, errors, batch_size=None):
set_x, set_y = data_set
if batch_size is None:
model = my_theano.function([], errors, givens={
self.x: set_x,
self.y: set_y
})
else:
raise NotImplementedError
return model
def _set_model(self, data_set, errors, batch_size=None):
set_x, set_y = data_set
if batch_size is None:
model = my_theano.function([],
errors,
givens={
self.x: set_x,
self.y: set_y
})
else:
index = self.index
model = my_theano.function(
[index],
errors,
givens={
self.x: self._get_mini_batch(set_x, batch_size, index),
self.y: self._get_mini_batch(set_y, batch_size, index),
})
return model
def _set_model(self, data_set, errors, batch_size=None):
set_x, set_y = data_set
if batch_size is None:
model = my_theano.function([], errors, givens={
self.x: set_x,
self.y: set_y
})
else:
raise NotImplementedError
return model
def predict():
"""
An example of how to load a trained model and use it
to predict labels.
"""
# load the saved model
classifier = pickle.load(open('best_model.pkl'))
# compile a predictor function
predict_model = my_theano.function(
inputs=[classifier.input],
outputs=classifier.y_pred)
# We can test it on some examples from test test
dataset='mnist.pkl.gz'
datasets = load_data(dataset)
test_set_x, test_set_y = datasets[2]
test_set_x = test_set_x.get_value()
predicted_values = predict_model(test_set_x[:10])
print("Predicted values for the first 10 examples in test set:")
print(predicted_values)
def set_train_model(self,
train_set,
cost_func,
batch_size,
learning_rate,
l1_a=0.0,
l2_a=0.0001):
self.p_y = self.forward(self.x, batch_size)
cost = cost_func(self.p_y, self.y) + self.l1 * l1_a + self.l2 * l2_a
# set early stopping patience
self.patience = 20
self.lest_valid_error = np.inf
print('compiling train model..')
# compute gradients of weights and biases
updates = []
for layer in reversed(self.weighted_layers):
g_w = T.grad(cost, layer.w)
g_b = T.grad(cost, layer.b)
updates += [(layer.w, layer.w - learning_rate * g_w),
(layer.b, layer.b - learning_rate * g_b)]
train_set_x, train_set_y = train_set
index = self.index
self.train_model = my_theano.function(
[index],
cost,
updates=updates,
givens={
self.x: self._get_mini_batch(train_set_x, batch_size, index),
self.y: self._get_mini_batch(train_set_y, batch_size, index)
})
# check if using gpu
tu.check_gpu(self.train_model)
def sgd_optimization_mnist(learning_rate=0.13, n_epochs=1000,
dataset='data/mnist/mnist.pkl.gz',
batch_size=600):
"""
Demonstrate stochastic gradient descent optimization of a log-linear
model
This is demonstrated on MNIST.
:type learning_rate: float
:param learning_rate: learning rate used (factor for the stochastic
gradient)
: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
# generate symbolic variables for input (x and y represent a
# minibatch)
x = T.matrix('x') # data, presented as rasterized images
y = T.ivector('y') # labels, presented as 1D vector of [int] labels
# construct the logistic regression class
# Each MNIST image has size 28*28
classifier = LogisticRegression(input=x, n_in=28 * 28, n_out=10)
# the cost we minimize during training is the negative log likelihood of
# the model in symbolic format
cost = classifier.negative_log_likelihood(y)
# compiling a Theano function that computes the mistakes that are made by
# the model on a minibatch
test_model = my_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 = my_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 = (W,b)
g_W = T.grad(cost=cost, wrt=classifier.W)
g_b = T.grad(cost=cost, wrt=classifier.b)
# start-snippet-3
# specify how to update the parameters of the model as a list of
# (variable, update expression) pairs.
updates = [(classifier.W, classifier.W - learning_rate * g_W),
(classifier.b, classifier.b - learning_rate * g_b)]
# 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 = my_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]
}
)
# end-snippet-3
###############
# TRAIN MODEL #
###############
print('... training the model')
# early-stopping parameters
patience = 5000 # 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_validation_loss = numpy.inf
test_score = 0.
start_time = timeit.default_timer()
done_looping = False
epoch = 0
while (epoch < n_epochs) and (not done_looping):
epoch = epoch + 1
for minibatch_index in range(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 range(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
# test it on the test set
test_losses = [test_model(i)
for i in range(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.
)
)
# save the best model
with open('best_model.pkl', 'wb') as f:
pickle.dump(classifier, f)
if patience <= iter:
done_looping = True
break
end_time = timeit.default_timer()
print(
(
'Optimization complete with best validation score of %f %%,'
'with test performance %f %%'
)
% (best_validation_loss * 100., test_score * 100.)
)
print('The code run for %d epochs, with %f epochs/sec' % (
epoch, 1. * epoch / (end_time - start_time)))
print(('The code for file ' +
os.path.split(__file__)[1] +
' ran for %.1fs' % ((end_time - start_time))), file=sys.stderr)
def get_b(self):
print(self.biases[0].get_value())
print(self.weights[0].get_value())
_get_b = my_theano.function([], self.biases[0])
print(_get_b())
def test_mlp(learning_rate=0.01, L1_reg=0.00, L2_reg=0.0001, n_epochs=1000,
dataset='mnist.pkl.gz', batch_size=600, n_hidden=50):
"""
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 = mnist.MNIST()
train_set_x, train_set_y = datasets.theano_train_set()
valid_set_x, valid_set_y = datasets.theano_valid_set()
test_set_x, test_set_y = datasets.theano_test_set()
# 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
)
# start-snippet-4
# 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
)
# end-snippet-4
# compiling a Theano function that computes the mistakes that are made
# by the model on a minibatch
test_model = my_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 = my_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]
}
)
# start-snippet-5
# compute the gradient of cost with respect to theta (sorted in params)
# the resulting gradients will be stored in a list gparams
gparams = [T.grad(cost, param) for param in classifier.params]
# specify how to update the parameters of the model as a list of
# (variable, update expression) pairs
# given two lists of the same length, A = [a1, a2, a3, a4] and
# B = [b1, b2, b3, b4], 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)]
updates = [
(param, param - learning_rate * gparam)
for param, gparam in zip(classifier.params, gparams)
]
# 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 = my_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]
}
)
# end-snippet-5
###############
# 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_validation_loss = numpy.inf
best_iter = 0
test_score = 0.
start_time = timeit.default_timer()
epoch = 0
done_looping = False
while (epoch < n_epochs) and (not done_looping):
epoch = epoch + 1
for minibatch_index in range(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 range(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 range(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 = timeit.default_timer()
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(('The code for file ' +
os.path.split(__file__)[1] +
' ran for %.2fm / %f epochs per sec' % ((end_time - start_time) / 60., epoch/(end_time-start_time))), file=sys.stderr)
from my_theano import function, config, shared, sandbox
import my_theano.sandbox.cuda.basic_ops
import my_theano.tensor as T
import numpy
import time
vlen = 10 * 30 * 768 # 10 x #cores x # threads per core
iters = 1000
rng = numpy.random.RandomState(22)
x = shared(numpy.asarray(rng.rand(vlen), 'float32'))
f = function([], T.exp(x))
print(f.maker.fgraph.toposort())
t0 = time.time()
for i in range(iters):
r = f()
t1 = time.time()
print("Looping %d times took %f seconds" % (iters, t1 - t0))
print("Result is %s" % (r,))
print("Numpy result is %s" % (numpy.asarray(r),))
if numpy.any([isinstance(x.op, T.Elemwise) for x in f.maker.fgraph.toposort()]):
print('Used the cpu')
else:
print('Used the gpu')
def get_b(self):
print(self.biases[0].get_value())
print(self.weights[0].get_value())
_get_b = my_theano.function([], self.biases[0])
print(_get_b())