def test_salt_and_pepper_noise_with_min_max(self):
""" test the salt and pepper function with specified min and max values.
"""
x_sp = utils.salt_and_pepper_noise(self.x, self.v, 0, 1)
for sample in x_sp:
salted_elems = sum([i == 0 or i == 1 for i in sample])
self.assertEqual(salted_elems, self.v)
def test_salt_and_pepper_noise_with_min_max(self):
""" test the salt and pepper function with specified min and max values.
"""
x_sp = utils.salt_and_pepper_noise(self.x, self.v, 0, 1)
for sample in x_sp:
salted_elems = sum([i == 0 or i == 1 for i in sample])
self.assertEqual(salted_elems, self.v)
def test_salt_and_pepper_noise_without_min_max(self):
""" test the salt and pepper function without specified min and max values.
"""
x_sp = utils.salt_and_pepper_noise(self.x, self.v)
mn = self.x.min()
mx = self.x.max()
for sample in x_sp:
salted_elements = sum([i == mn or i == mx for i in sample])
self.assertAlmostEqual(salted_elements, self.v, delta=2)
def test_salt_and_pepper_noise_without_min_max(self):
""" test the salt and pepper function without specified min and max values.
"""
x_sp = utils.salt_and_pepper_noise(self.x, self.v)
mn = self.x.min()
mx = self.x.max()
for sample in x_sp:
salted_elements = sum([i == mn or i == mx for i in sample])
self.assertAlmostEqual(salted_elements, self.v, delta=2)
def corrupt_input(self, data, v):
if self.corruption_type == 'masking':
x_corrupted = utils.masking_noise(data, v)
elif self.corruption_type == 'salt_and_pepper':
x_corrupted = utils.salt_and_pepper_noise(data, v)
elif self.corruption_type == 'gaussian':
x_corrupted = utils.gaussian_noise(data, v)
elif self.corruption_type == 'none':
x_corrupted = data
else:
x_corrupted = None
return x_corrupted
def _corrupt_input(self, data, v): ''' Corrupt a fraction 'v' of 'data' according to the noise method of this autoencoder. Returns ------- corrupted data ''' if self.corr_type == 'none': return np.copy(data) if v > 0.0: if self.corr_type == 'masking': return utils.masking_noise(data, v) elif self.corr_type == 'salt_and_pepper': return utils.salt_and_pepper_noise(data, v) else: return np.copy(data)
def _corrupt_input(self, data, v):
""" Corrupt a fraction 'v' of 'data' according to the
noise method of this autoencoder.
:return: corrupted data
"""
if self.corr_type == 'masking':
x_corrupted = utils.masking_noise(data, v)
elif self.corr_type == 'salt_and_pepper':
x_corrupted = utils.salt_and_pepper_noise(data, v)
elif self.corr_type == 'none':
x_corrupted = data
else:
x_corrupted = None
return x_corrupted
def fit(self, trX, vlX=None, restore_previous_model=False):
""" Fit the model to the data.
:type trX: array_like, shape (n_samples, n_features).
:param trX: Training data.
:type vlX: array_like, shape (n_validation_samples, n_features).
:param vlX: optional, default None. Validation data.
:return: self
"""
n_features = trX.shape[1]
self._create_graph(n_features)
# Merge all the summaries
merged = tf.merge_all_summaries()
# Initialize variables
init_op = tf.initialize_all_variables()
# Add ops to save and restore all the variables
self.saver = tf.train.Saver()
with tf.Session() as self.sess:
self.sess.run(init_op)
if restore_previous_model:
# Restore previous model
self.saver.restore(self.sess,
self.models_dir + self.model_name)
# Change model name
self.model_name += '-restored{}'.format(self.n_iter)
# ################## #
# Training phase #
# ################## #
v = np.round(self.corr_frac * n_features).astype(np.int)
# Write the summaries to summary_dir
writer = tf.train.SummaryWriter(self.summary_dir,
self.sess.graph_def)
for i in range(self.n_iter):
# #################### #
# Input Corruption #
# #################### #
if self.corr_type == 'masking':
x_corrupted = utils.masking_noise(trX, v)
elif self.corr_type == 'salt_and_pepper':
x_corrupted = utils.salt_and_pepper_noise(trX, v)
else: # none, normal autoencoder
x_corrupted = trX
# Randomly shuffle the input
shuff = zip(trX, x_corrupted)
np.random.shuffle(shuff)
# # Divide dataset into mini-batches
batches = [
_ for _ in utils.gen_batches(shuff, self.batch_size)
]
# All the batches for each epoch
for batch in batches:
x_batch, x_corr_batch = zip(*batch)
tr_feed = {
self.x: x_batch,
self.x_corr: x_corr_batch,
self.keep_prob: self.dropout
}
self.sess.run(self.train_step, feed_dict=tr_feed)
# Record summary data
if vlX is not None:
vl_feed = {
self.x: vlX,
self.x_corr: vlX,
self.keep_prob: 1.
}
result = self.sess.run([merged, self.cost],
feed_dict=vl_feed)
summary_str = result[0]
err = result[1]
writer.add_summary(summary_str, i)
if self.verbose == 1:
print("Validation cost at step %s: %s" % (i, err))
# Save trained model
self.saver.save(self.sess, self.models_dir + self.model_name)