def _train_model(self, train_X, train_Y=None, val_X=None, val_Y=None):
"""Train the model.
Parameters
----------
train_X : array_like
Training data, shape (num_samples, num_features).
train_Y : array_like, optional (default = None)
Reference training data, shape (num_samples, num_features).
val_X : array_like, optional, default None
Validation data, shape (num_val_samples, num_features).
val_Y : array_like, optional, default None
Reference validation data, shape (num_val_samples, num_features).
Returns
-------
self : trained model instance
"""
pbar = tqdm(range(self.num_epochs))
for i in pbar:
self._run_train_step(train_X)
if val_X is not None:
feed = {self.input_data_orig: val_X,
self.input_data: val_X}
err = tf_utils.run_summaries(
self.tf_session, self.tf_merged_summaries,
self.tf_summary_writer, i, feed, self.cost)
pbar.set_description("Reconstruction loss: %s" % (err))
return self
def _train_model(self, train_set, train_ref,
validation_set, validation_ref):
"""Train the model.
:param train_set: training set
:param train_ref: training reference data
:param validation_set: validation set
:param validation_ref: validation reference data
:return: self
"""
shuff = list(zip(train_set, train_ref))
pbar = tqdm(range(self.num_epochs))
for i in pbar:
np.random.shuffle(shuff)
batches = [_ for _ in utilities.gen_batches(
shuff, self.batch_size)]
for batch in batches:
x_batch, y_batch = zip(*batch)
self.tf_session.run(
self.train_step,
feed_dict={self.input_data: x_batch,
self.input_labels: y_batch,
self.keep_prob: self.dropout})
if validation_set is not None:
feed = {self.input_data: validation_set,
self.input_labels: validation_ref,
self.keep_prob: 1}
err = tf_utils.run_summaries(
self.tf_session, self.tf_merged_summaries,
self.tf_summary_writer, i, feed, self.cost)
pbar.set_description("Reconstruction loss: %s" % (err))
def _train_model(self, train_set, train_labels,
validation_set, validation_labels):
"""Train the model.
:param train_set: training set
:param train_labels: training labels
:param validation_set: validation set
:param validation_labels: validation labels
:return: self
"""
shuff = list(zip(train_set, train_labels))
pbar = tqdm(range(self.num_epochs))
for i in pbar:
np.random.shuffle(shuff)
batches = [_ for _ in utilities.gen_batches(
shuff, self.batch_size)]
for batch in batches:
x_batch, y_batch = zip(*batch)
self.tf_session.run(
self.train_step, feed_dict={
self.input_data: x_batch,
self.input_labels: y_batch,
self.keep_prob: self.dropout})
if validation_set is not None:
feed = {self.input_data: validation_set,
self.input_labels: validation_labels,
self.keep_prob: 1}
acc = tf_utils.run_summaries(
self.tf_session, self.tf_merged_summaries,
self.tf_summary_writer, i, feed, self.accuracy)
pbar.set_description("Accuracy: %s" % (acc))
def _train_model(self, train_set, train_labels,
validation_set, validation_labels):
"""Train the model.
:param train_set: training set
:param train_labels: training labels
:param validation_set: validation set
:param validation_labels: validation labels
:return: self
"""
pbar = tqdm(range(self.num_epochs))
for i in pbar:
shuff = list(zip(train_set, train_labels))
np.random.shuffle(shuff)
batches = [_ for _ in utilities.gen_batches(shuff, self.batch_size)]
for batch in batches:
x_batch, y_batch = zip(*batch)
self.tf_session.run(
self.train_step,
feed_dict={self.input_data: x_batch,
self.input_labels: y_batch})
if validation_set is not None:
feed = {self.input_data: validation_set,
self.input_labels: validation_labels}
acc = tf_utils.run_summaries(
self.tf_session, self.tf_merged_summaries,
self.tf_summary_writer, i, feed, self.accuracy)
pbar.set_description("Accuracy: %s" % (acc))
def _train_model(self, train_set, train_ref=None, validation_set=None,
Validation_ref=None):
"""Train the model.
:param train_set: training set
:param validation_set: validation set. optional, default None
:return: self
"""
pbar = tqdm(range(self.num_epochs))
for i in pbar:
self._run_train_step(train_set, train_ref)
if validation_set is not None:
feed = self._create_feed_dict(validation_set)
err = tf_utils.run_summaries(
self.tf_session, self.tf_merged_summaries,
self.tf_summary_writer, i, feed, self.cost)
pbar.set_description("Reconstruction loss: %s" % (err))
def _train_model(self, train_set, train_ref, validation_set,
validation_ref):
"""Train the model.
:param train_set: training set
:param train_ref: training reference data
:param validation_set: validation set
:param validation_ref: validation reference data
:return: self
"""
shuff = list(zip(train_set, train_ref))
pbar = tqdm(list(range(self.num_epochs)))
for i in pbar:
np.random.shuffle(shuff)
batches = [
_ for _ in utilities.gen_batches(shuff, self.batch_size)
]
for batch in batches:
x_batch, y_batch = list(zip(*batch))
self.tf_session.run(self.train_step,
feed_dict={
self.input_data: x_batch,
self.input_labels: y_batch,
self.keep_prob: self.dropout
})
if validation_set is not None:
feed = {
self.input_data: validation_set,
self.input_labels: validation_ref,
self.keep_prob: 1
}
err = tf_utils.run_summaries(self.tf_session,
self.tf_merged_summaries,
self.tf_summary_writer, i, feed,
self.cost)
pbar.set_description("Reconstruction loss: %s" % (err))
