def test_mlp(learning_rate=0.01,
L1_reg=0.00,
L2_reg=0.0001,
n_epochs=1000,
dataset='../data/mnist/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 = np.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 (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 = 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 = np.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 = np.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 = np.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' %
((end_time - start_time) / 60.)),
file=sys.stderr)
if __name__ == '__main__':
df = read_csv('./../data/africa-soil/training.csv')
x = df.as_matrix(columns=df.columns[1:3595])
x[:, -1] = (x[:, -1] == 'Topsoil') * 1.0
x = x.astype(float)
y = df.as_matrix(columns=df.columns[3595:])
y = y.astype(float)
idx_train = list(
np.random.choice(range(x.shape[0]), size=int(round(0.8 * x.shape[0]))))
idx_cv = list(set(range(x.shape[0])) - set(idx_train))
nn = MLP(3594, (50, 5),
activation_functions=[tanh, identity],
rng=(lambda n: np.random.normal(0, 0.01, n)))
train_cost, cv_cost = \
nn.train_backprop(x[idx_train, :], y[idx_train, :],
d_f_list=[d_tanh, d_identity],
batch_size=None,
max_iter=1000,
learning_rate=0.001,
momentum_rate=0.9,
neural_local_gain=(0.0005, 0.9995, 0.001, 1000),
stop_threshold=0.05,
cv_input_data=x[idx_cv, :],
cv_output_data=y[idx_cv, :],
#regularization_rate=0.1,
#regularization_norm=l2,
#d_regularization_norm=d_l2
i = int(parts[1])
o = np.zeros(26)
o[i] = 1.0
if len(parts) == 5 and parts[2] in ['7', '8']:
cv_input = np.vstack([cv_input, v])
cv_output = np.vstack([cv_output, o])
elif len(parts) == 5 and parts[2] in ['5', '6']:
test_input = np.vstack([cv_input, v])
test_output = np.vstack([cv_output, o])
else:
train_input = np.vstack([train_input, v])
train_output = np.vstack([train_output, o])
nn = MLP(841, (100, 26),
activation_functions=[tanh, softmax],
rng=(lambda n: np.random.normal(0, 0.01, n)))
train_cost, cv_cost = \
nn.train_backprop(train_input, train_output,
d_f_list=[d_tanh, d_softmax],
goal=cross_entropy,
d_goal=d_cross_entropy,
batch_size=1,
max_iter=100,
learning_rate=0.01,
momentum_rate=0.9,
#neural_local_gain=(0.0005, 0.9995, 0.001, 1000),
stop_threshold=0.05,
cv_input_data=cv_input,
cv_output_data=cv_output,
#regularization_rate=0.1,
parts = re.split('[-\.]', f)
i = int(parts[1])
o = np.zeros(26)
o[i] = 1.0
if len(parts) == 5 and parts[2] in ['7', '8']:
cv_input = np.vstack([cv_input, v])
cv_output = np.vstack([cv_output, o])
elif len(parts) == 5 and parts[2] in ['5', '6']:
test_input = np.vstack([cv_input, v])
test_output = np.vstack([cv_output, o])
else:
train_input = np.vstack([train_input, v])
train_output = np.vstack([train_output, o])
nn = MLP(841, (100, 26),
activation_functions=[sigmoid, sigmoid],
rng=(lambda n: np.random.normal(0, 0.01, n)))
train_cost, cv_cost = \
nn.train_backprop(train_input, train_output,
d_f_list=[d_sigmoid, d_sigmoid],
goal=log_Bernoulli_likelihood,
d_goal=d_log_Bernoulli_likelihood,
batch_size=None,
max_iter=2500,
learning_rate=0.1,
momentum_rate=0.9,
neural_local_gain=(0.005, 0.995, 0.001, 1000),
stop_threshold=0.05,
cv_input_data=cv_input,
cv_output_data=cv_output,
#regularization_rate=0.1,