def mlp_train(train_file_name, test_file_name, model_file_name, n_dim, n_label, n_hidden, learning_rate, L1_reg=0.00, L2_reg=0.0001, batch_size=20):
logger.info('loading data')
train_set_x, train_set_y, test_set_x, test_set_y = load_data(train_file_name, test_file_name, n_dim)
n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
n_test_batches = test_set_x.get_value(borrow=True).shape[0] / batch_size
logger.info('building the model')
idx = T.lscalar()
x = T.matrix('x')
y = T.ivector('y')
rng = np.random.RandomState(1234)
hidden_W = None
hidden_b = None
sgd_W = None
sgd_b = None
if os.path.isfile(model_file_name):
logger.debug('load existing model')
hidden_W, hidden_b, sgd_W, sgd_b = np.load(model_file_name)
classifier = MLP(rng=rng, input=x, n_in=n_dim, n_hidden=n_hidden, n_out=n_label, hidden_W=hidden_W, hidden_b=hidden_b, sgd_W=sgd_W, sgd_b=sgd_b)
cost = classifier.negative_log_likelihood(y) + L1_reg * classifier.L1 + L2_reg * classifier.L2_sqr
test_model = theano.function(inputs=[idx],
outputs=classifier.errors(y),
givens={
x: test_set_x[idx * batch_size:(idx + 1) * batch_size],
y: test_set_y[idx * batch_size:(idx + 1) * batch_size]
})
gparams = []
for param in classifier.params:
gparam = T.grad(cost, param)
gparams.append(gparam)
updates = []
for param, gparam in zip(classifier.params, gparams):
updates.append((param, param - learning_rate * gparam))
train_model = theano.function(inputs=[idx],
outputs=cost,
updates=updates,
givens={
x: train_set_x[idx * batch_size:(idx + 1) * batch_size],
y: train_set_y[idx * batch_size:(idx + 1) * batch_size]
})
logger.info('training the model')
best_test_score = np.inf
epoch = 0
start_time = time.clock()
while True:
epoch = epoch + 1
for minibatch_idx in xrange(n_train_batches):
train_model(minibatch_idx)
iter = (epoch - 1) * n_train_batches + minibatch_idx
if (iter + 1) % n_train_batches == 0:
test_loss = [test_model(i) for i in xrange(n_test_batches)]
test_score = np.mean(test_loss)
logger.info(('epoch %i, ran for %.5f hr, minibatch %i/%i, test error %f %%') % (epoch, (time.clock() - start_time)/3600.0, minibatch_idx + 1, n_train_batches, test_score * 100.))
if test_score < best_test_score:
np.save(model_file_name, (classifier.hiddenLayer.W.get_value(), classifier.hiddenLayer.b.get_value(), classifier.logRegressionLayer.W.get_value(), classifier.logRegressionLayer.b.get_value()))
best_test_score = test_score
logger.info(('epoch %i, minibatch %i/%i, test error of best model %f %%') % (epoch, minibatch_idx + 1, n_train_batches, best_test_score * 100.))
def sgd_train(train_file_name, test_file_name, model_file_name, n_dim, n_label, learning_rate, batch_size=600):
logger.info('loading data')
train_set_x, train_set_y, test_set_x, test_set_y = load_data(train_file_name, test_file_name, n_dim)
n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
n_test_batches = test_set_x.get_value(borrow=True).shape[0] / batch_size
logger.info('building the model')
idx = T.lscalar()
x = T.matrix('x')
y = T.ivector('y')
W = None
b = None
if os.path.isfile(model_file_name):
logger.debug('load existing model')
W, b = np.load(model_file_name)
classifier = LogisticRegression(input=x, n_in=n_dim, n_out=n_label, W=W, b=b)
cost = classifier.negative_log_likelihood(y)
test_model = theano.function(inputs=[idx],
outputs=classifier.errors(y),
givens={
x: test_set_x[idx * batch_size: (idx + 1) * batch_size],
y: test_set_y[idx * batch_size: (idx + 1) * batch_size]
})
g_W = T.grad(cost=cost, wrt=classifier.W)
g_b = T.grad(cost=cost, wrt=classifier.b)
updates = [(classifier.W, classifier.W - learning_rate * g_W),
(classifier.b, classifier.b - learning_rate * g_b)]
train_model = theano.function(inputs=[idx],
outputs=cost,
updates=updates,
givens={
x: train_set_x[idx * batch_size: (idx + 1) * batch_size],
y: train_set_y[idx * batch_size: (idx + 1) * batch_size]
})
logger.info('training the model')
best_test_score = np.inf
epoch = 0
start_time = time.clock()
while True:
epoch = epoch + 1
for minibatch_idx in xrange(n_train_batches):
train_model(minibatch_idx)
iter = (epoch - 1) * n_train_batches + minibatch_idx
if (iter + 1) % n_train_batches == 0:
test_loss = [test_model(i) for i in xrange(n_test_batches)]
test_score = np.mean(test_loss)
logger.info(('epoch %i, ran for %.5f hr, minibatch %i/%i, test error %f %%') % (epoch, (time.clock() - start_time)/3600.0, minibatch_idx + 1, n_train_batches, test_score * 100.))
if test_score < best_test_score:
np.save(model_file_name, (classifier.W.get_value(), classifier.b.get_value()))
best_test_score = test_score
logger.info(('epoch %i, minibatch %i/%i, test error of best model %f %%') % (epoch, minibatch_idx + 1, n_train_batches, best_test_score * 100.))
