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.p", "rb"))
# compile a predictor function
predict_model = theano.function(
inputs=[classifier.input],
outputs=classifier.y_pred)
# We can test it on some examples from test test
dataset = 'mnist_train.csv'
datasets = DataLoader.load_kaggle_mnist(dataset)
test_set_x, test_set_y = datasets[2]
print(type(test_set_x))
print(type(test_set_y))
test_set_x = test_set_x.get_value()
test_set_y = test_set_y.eval()
predicted_values = predict_model(test_set_x[20:30])
print("Sample Neural Prediction")
print ("Predicted values for the first 20 examples in test set:")
print(predicted_values)
print ("The actual values are")
print(test_set_y[20:30])
def predict_main(classifier_pickle):
data = DataLoader.load_kaggle_mnist("mnist_train.csv", neural=False)
X = numpy.array(data[2][0])
X = X/255.0*2 - 1
Y = numpy.array(data[2][1])
predictor = MLutil.Predictor(classifier_pickle, 'SVM')
predicted_values = predictor.make_prediction(X)
predAnalysis = MLutil.PredictionAccuracies(predicted_values, Y)
print(predAnalysis.get_misclass_rate())
print(predAnalysis.get_indicies_misclassifications())
pickle.dump(predAnalysis.get_indicies_misclassifications(), open("svm_indicies.p", "wb"))
return predAnalysis.get_indicies_misclassifications()
def predict_main(classifier_pickle):
print("This functions is being called")
datasets = DataLoader.load_kaggle_mnist("mnist_train.csv")
test_set_x, test_set_y = datasets[2]
test_set_x = test_set_x.get_value()
test_set_y = test_set_y.eval()
predictor = MLutil.Predictor(classifier_pickle, 'DNN')
predicted_values = predictor.make_prediction(test_set_x)
predAnalysis = MLutil.PredictionAccuracies(predicted_values, test_set_y)
print(predAnalysis.get_misclass_rate())
print(predAnalysis.get_indicies_misclassifications())
pickle.dump(predAnalysis.get_indicies_misclassifications(), open("neural_indicies.p", "wb"))
return predAnalysis.get_indicies_misclassifications()
def svm_main(dataset, pickle_model):
data = DataLoader.load_kaggle_mnist(dataset, neural=False)
classifier = SVM()
start = time.time()
print("Fitting the svm")
X = numpy.array(data[0][0])
X = X/255.0*2 - 1
print(X)
Y = numpy.array(data[0][1])
print(len(X))
print(len(Y))
del data
classifier.fit_multi(X, Y)
fin = time.time() - start
print("Awesome, the SVM has been fit, only took {0} seconds".format(fin))
pickle.dump(classifier, open(pickle_model, "wb"))
def validation_analysis(learning_rate=.001, L1_reg=0.00, L2_reg=0.0001, n_epochs=100,
dataset='mnist_train.csv', batch_size=20, n_hidden=300, num_layers = 2, mlp_in = 784, mlp_out = 10):
"""
Main loop for the mlp
: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: path to appropriate dataset
:type batch_size: int
:param batch_size: number of entries per mini-batch
:type n_hidden: int
:param n_hidden: number of entries per hidden layer
:type num_layers: int
:param num_layers: number of hidden layers
:type mlp_in: int
:param mlp_in: dimension of data loaded from dataset
:type mlp_out: int
:param mlp_out: number of classes in dataset
"""
# Load in the data
datasets = DataLoader.load_kaggle_mnist(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 = math.floor(train_set_x.get_value(borrow=True).shape[0] / batch_size)
n_valid_batches = math.floor(valid_set_x.get_value(borrow=True).shape[0] / batch_size)
n_test_batches = math.floor(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') # n data entries, m features per entry ==> n by m matrix of data
y = T.ivector('y') # the labels are presented as 1D vector of
# [int] labels
# Seed the random number generator
rng = numpy.random.RandomState(1234)
# construct the MLP class (the neural net)
classifier = MLP(
rng=rng,
input=x,
n_in = mlp_in,
n_hidden=n_hidden,
n_out=mlp_out,
num_layers=num_layers
)
# 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 (stored 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 = 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_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
#old_classifier = copy.deepcopy(classifier)
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.))
pickle.dump(classifier, open("best_model.p", "wb"))
# Otherwise, reduce the learning rate (need to fix this/do this in a better way)
'''
else:
classifier = old_classifier
learning_rate = learning_rate / 2
print("Learning rate halved ... the new learning rate is {0}".format(learning_rate))
'''
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' % ((end_time - start_time) / 60.))
def evaluate_lenet5(learning_rate=0.1, n_epochs=200,
dataset='mnist_train.csv',
nkerns=[20, 50], batch_size=500,
image_height = 28, image_width = 28,
filter_height = 5, filter_width = 5,
hidden_size = 500, pool_size = (2,2),
num_classes = 10, num_standard_layers = 1):
""" Demonstrates lenet on MNIST dataset
: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: path to the dataset used for training /testing (MNIST here)
:type nkerns: list of ints
:param nkerns: number of kernels on each layer
"""
rng = numpy.random.RandomState(23455)
datasets = DataLoader.load_kaggle_mnist(dataset)
#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]
n_valid_batches = valid_set_x.get_value(borrow=True).shape[0]
n_test_batches = test_set_x.get_value(borrow=True).shape[0]
n_train_batches = math.floor(n_train_batches / batch_size)
n_valid_batches = math.floor(n_valid_batches / batch_size)
n_test_batches = math.floor(n_test_batches / batch_size)
# allocate symbolic variables for the data
index = T.lscalar() # index to a [mini]batch
# start-snippet-1
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
######################
# BUILD ACTUAL MODEL #
######################
print('... building the model')
# Reshape matrix of rasterized images of shape (batch_size, 28 * 28)
# to a 4D tensor, compatible with our LeNetConvPoolLayer
# (28, 28) is the size of MNIST images.
layer0_input = x.reshape((batch_size, 1, image_height, image_width))
# Construct the first convolutional pooling layer:
# filtering reduces the image size to (28-5+1 , 28-5+1) = (24, 24)
# maxpooling reduces this further to (24/2, 24/2) = (12, 12)
# 4D output tensor is thus of shape (batch_size, nkerns[0], 12, 12)
layer0 = LeNetConvPoolLayer(
rng,
input=layer0_input,
image_shape=(batch_size, 1, image_height, image_width),
filter_shape=(nkerns[0], 1, filter_height, filter_width),
poolsize=pool_size
)
# Construct the second convolutional pooling layer
# filtering reduces the image size to (12-5+1, 12-5+1) = (8, 8)
# maxpooling reduces this further to (8/2, 8/2) = (4, 4)
# 4D output tensor is thus of shape (batch_size, nkerns[1], 4, 4)
new_height = int((image_height - filter_height + 1) / pool_size[0])
new_width = int((image_width - filter_width + 1) / pool_size[1])
print(new_height, new_width)
layer1 = LeNetConvPoolLayer(
rng,
input=layer0.output,
image_shape=(batch_size, nkerns[0], new_height, new_width),
filter_shape=(nkerns[1], nkerns[0], filter_height, filter_width),
poolsize=pool_size
)
# Again, after filtering/pooling, find new dimension
new_height = int((new_height - filter_height + 1) / pool_size[0])
new_width = int((new_width - filter_width + 1) / pool_size[1])
print(new_height, new_width)
# the HiddenLayer being fully-connected, it operates on 2D matrices of
# shape (batch_size, num_pixels) (i.e matrix of rasterized images).
# This will generate a matrix of shape (batch_size, nkerns[1] * 4 * 4),
# or (500, 50 * 4 * 4) = (500, 800) with the default values.
layer2_input = layer1.output.flatten(2)
# construct a fully-connected sigmoidal layer
layer2 = HiddenLayer(
rng,
input=layer2_input,
n_in=nkerns[1] * new_height * new_width,
n_out=hidden_size,
activation=T.tanh
)
# classify the values of the fully-connected sigmoidal layer
layer3 = LogisticRegression(input=layer2.output, n_in=hidden_size, n_out=num_classes)
# the cost we minimize during training is the NLL of the model
cost = layer3.negative_log_likelihood(y)
# create a function to compute the mistakes that are made by the model
test_model = theano.function(
[index],
layer3.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(
[index],
layer3.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]
}
)
# create a list of all model parameters to be fit by gradient descent
params = layer3.params + layer2.params + layer1.params + layer0.params
# create a list of gradients for all model parameters
grads = T.grad(cost, params)
# train_model is a function that updates the model parameters by
# SGD Since this model has many parameters, it would be tedious to
# manually create an update rule for each model parameter. We thus
# create the updates list by automatically looping over all
# (params[i], grads[i]) pairs.
updates = [
(param_i, param_i - learning_rate * grad_i)
for param_i, grad_i in zip(params, grads)
]
train_model = theano.function(
[index],
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-1
###############
# 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):
iter = (epoch - 1) * n_train_batches + minibatch_index
if iter % 100 == 0:
print('training @ iter =', iter)
cost_ij = train_model(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)
# save best validation score and iteration number
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.')
print('Best validation score of %f %% obtained at iteration %i, '
'with test performance %f %%' %
(best_validation_loss * 100., best_iter + 1, test_score * 100.))
'''
