def test_reconstruction_error(self):
sys.stdout.write(
'RBM Estimator -> Performing reconstruction_error test ...')
sys.stdout.flush()
numx.random.seed(42)
rec = Estimator.reconstruction_error(self.bbrbm,
self.bbrbmData,
k=1,
beta=1.0,
use_states=True,
absolut_error=False)
assert numx.all(numx.abs(rec) < self.epsilon)
rec = Estimator.reconstruction_error(self.bbrbm,
self.bbrbmData,
k=1,
beta=1.0,
use_states=False,
absolut_error=False)
assert numx.all(numx.abs(rec) < self.epsilon)
rec = Estimator.reconstruction_error(self.bbrbm,
self.bbrbmData,
k=1,
beta=1.0,
use_states=True,
absolut_error=True)
assert numx.all(numx.abs(rec) < self.epsilon)
rec = Estimator.reconstruction_error(self.bbrbm,
self.bbrbmData,
k=1,
beta=1.0,
use_states=False,
absolut_error=True)
assert numx.all(numx.abs(rec) < self.epsilon)
rec = Estimator.reconstruction_error(self.bbrbm,
self.bbrbmData,
k=10,
beta=1.0,
use_states=False,
absolut_error=False)
assert numx.all(numx.abs(rec) < self.epsilon)
# Test List
testList = []
for i in range(self.bbrbmData.shape[0]):
testList.append(self.bbrbmData[i].reshape(1, 4))
rec = Estimator.reconstruction_error(self.bbrbm,
testList,
k=10,
beta=1.0,
use_states=False,
absolut_error=False)
assert numx.all(numx.abs(rec) < self.epsilon)
print(' successfully passed!')
sys.stdout.flush()
for epoch in range(epochs):
# Loop over all batches
for b in range(0, train_data.shape[0], batch_size):
batch = train_data[b:b + batch_size, :]
trainer_pcd.train(data=batch,
epsilon=0.01,
update_visible_offsets=update_offsets,
update_hidden_offsets=update_offsets)
# Calculate Log-Likelihood, reconstruction error and expected end time every 5th epoch
if (epoch == 0 or (epoch + 1) % 5 == 0):
logZ = estimator.partition_function_factorize_h(rbm)
ll_train = numx.mean(estimator.log_likelihood_v(rbm, logZ, train_data))
ll_test = numx.mean(estimator.log_likelihood_v(rbm, logZ, test_data))
re = numx.mean(estimator.reconstruction_error(rbm, train_data))
print('{}\t\t{:.4f}\t\t\t{:.4f}\t\t\t\t{:.4f}\t\t\t{}'.format(
epoch + 1, re, ll_train, ll_test,
measurer.get_expected_end_time(epoch + 1, epochs)))
else:
print(epoch + 1)
measurer.end()
# Print end/training time
print("End-time: \t{}".format(measurer.get_end_time()))
print("Training time:\t{}".format(measurer.get_interval()))
# Calculate true partition function
logZ = estimator.partition_function_factorize_h(rbm,
batchsize_exponent=h1,
# Training with CD-1
k = 1
trainer_cd = trainer.CD(rbm)
# Train model, status every 10th epoch
step = 10
print 'Training'
print 'Epoch\tRE train\tRE test \tLL train\tLL test '
for epoch in range(0, max_epochs + 1, 1):
# Shuffle training samples (optional)
train_data = numx.random.permutation(train_data)
# Print epoch and reconstruction errors every 'step' epochs.
if epoch % step == 0:
RE_train = numx.mean(estimator.reconstruction_error(rbm, train_data))
RE_test = numx.mean(estimator.reconstruction_error(rbm, test_data))
print '%5d \t%0.5f \t%0.5f' % (epoch, RE_train, RE_test)
# Train one epoch with gradient restriction/clamping
# No weight decay, momentum or sparseness is used
for b in range(0, train_data.shape[0], batch_size):
trainer_cd.train(data=train_data[b:(b + batch_size), :],
num_epochs=1,
epsilon=[eps, 0.0, eps, eps * 0.1],
k=k,
momentum=0.0,
reg_l1norm=0.0,
reg_l2norm=0.0,
reg_sparseness=0,
desired_sparseness=None,
# Measuring time
measurer = MEASURE.Stopwatch()
# Train model
print 'Training'
print 'Epoch\tRecon. Error\tExpected End-Time'
for epoch in range(1, epochs+1):
train_data = numx.random.permutation(train_data)
for b in range(0, train_data.shape[0], batch_size):
batch = train_data[b:b + batch_size, :]
trainer.train(data=batch, epsilon=0.1, regL2Norm= 0.001)
# Calculate Log-Likelihood, reconstruction error and expected end time every 10th epoch
if (epoch % 10 == 0):
RE = numx.mean(ESTIMATOR.reconstruction_error(rbm, train_data))
print '%d\t\t%8.6f\t\t' % (epoch, RE),
print measurer.get_expected_end_time(epoch , epochs),
print
measurer.end()
# Print end time
print
print 'End-time: \t', measurer.get_end_time()
print 'Training time:\t', measurer.get_interval()
# Reorder RBM features by average activity decreasingly
reordered_rbm = STATISTICS.reorder_filter_by_hidden_activation(rbm, train_data)
# Display RBM parameters
VISUALIZATION.imshow_standard_rbm_parameters(reordered_rbm, v1, v2, h1, h2)
