def input_fn(labeled: DataSet, unlabeled: DataSet, labeled_size,
unlabeled_size):
input_dict = {}
# labeled data
labeled = labeled.get_batch(labeled_size)
input_dict['labeled_inputs'] = tf.constant(np.array(labeled.inputs()))
input_dict['labeled_sequence_length'] = tf.constant(labeled.lengths())
input_dict['labeled_mask'] = tf.constant(labeled.masks())
labels = tf.constant(labeled.labels())
# unlabeled data
unlabeled = unlabeled.get_batch(unlabeled_size)
input_dict['unlabeled_inputs'] = tf.constant(
np.array(unlabeled.inputs()))
input_dict['unlabeled_sequence_length'] = tf.constant(
unlabeled.lengths())
input_dict['unlabeled_mask'] = tf.constant(unlabeled.masks())
return input_dict, labels
def input_fn(data_set: DataSet, size):
input_dict = {}
# labeled data
data_set = data_set.get_batch(size)
input_dict['inputs'] = tf.constant(np.array(data_set.inputs()))
input_dict['sequence_length'] = tf.constant(data_set.lengths())
input_dict['mask'] = tf.constant(data_set.masks())
labels = tf.constant(data_set.labels())
return input_dict, labels
def input_fn(labeled: DataSet, unlabeled: DataSet = None, size: int = BATCH_SIZE):
input_dict = {
}
if unlabeled is not None and unlabeled.size() == 0:
unlabeled = None
# labeled data
labeled = labeled.get_batch(size)
input_dict['labeled_inputs'] = tf.constant(np.array(labeled.inputs()))
input_dict['labeled_sequence_length'] = tf.constant(labeled.lengths())
input_dict['labeled_mask'] = tf.constant(labeled.masks())
labels = tf.constant(labeled.labels())
# unlabeled data
unlabeled = unlabeled is None and labeled or unlabeled.get_batch(labeled.size())
input_dict['unlabeled_inputs'] = tf.constant(np.array(unlabeled.inputs()))
input_dict['unlabeled_sequence_length'] = tf.constant(unlabeled.lengths())
input_dict['unlabeled_mask'] = tf.constant(unlabeled.masks())
input_dict['unlabeled_size'] = tf.constant(unlabeled.size())
input_dict['unlabeled_target'] = tf.constant(unlabeled.labels())
return input_dict, labels
