def test_mean_square_regularization_loss(self):
embedding_unit_length = self.get_embedding2d_unit_length()
loss1 = mll.regularization_loss(embedding_unit_length, 1.0, 'msq')
embedding_0 = self.get_embedding2d_close_to_0()
loss2 = mll.regularization_loss(embedding_0, 1.0, 'msq')
expected_loss1 = np.array(0.5, dtype=np.float32)
self.assertAllClose(loss1.numpy(), expected_loss1)
self.assertLess(loss2.numpy(), loss1.numpy())
def embedding_regularization_loss(inputs,
outputs,
lambda_coef=0.0001,
regularization_type='unit_length',
is_intermediate=False):
"""Classification loss with an iou threshold.
Args:
inputs: A dictionary that contains
num_valid_voxels - A tf.int32 tensor of size [batch_size].
instance_ids - A tf.int32 tensor of size [batch_size, n].
outputs: A dictionart that contains
embeddings - A tf.float32 tensor of size [batch_size, n, f].
lambda_coef: Regularization loss coefficient.
regularization_type: Regularization loss type. Supported values are 'msq'
and 'unit_length'. 'msq' stands for 'mean square' which penalizes the
embedding vectors if they have a length far from zero. 'unit_length'
penalizes the embedding vectors if they have a length far from one.
is_intermediate: True if applied to intermediate predictions;
otherwise, False.
Returns:
A tf.float32 scalar loss tensor.
"""
instance_ids_key = standard_fields.InputDataFields.object_instance_id_voxels
num_voxels_key = standard_fields.InputDataFields.num_valid_voxels
if is_intermediate:
embedding_key = (
standard_fields.DetectionResultFields
.intermediate_instance_embedding_voxels)
else:
embedding_key = (
standard_fields.DetectionResultFields.instance_embedding_voxels)
if instance_ids_key not in inputs:
raise ValueError('instance_ids is missing in inputs.')
if embedding_key not in outputs:
raise ValueError('embedding is missing in outputs.')
if num_voxels_key not in inputs:
raise ValueError('num_voxels is missing in inputs.')
batch_size = inputs[num_voxels_key].get_shape().as_list()[0]
if batch_size is None:
raise ValueError('batch_size is not defined at graph construction time.')
num_valid_voxels = inputs[num_voxels_key]
num_voxels = tf.shape(inputs[instance_ids_key])[1]
valid_mask = tf.less(
tf.tile(tf.expand_dims(tf.range(num_voxels), axis=0), [batch_size, 1]),
tf.expand_dims(num_valid_voxels, axis=1))
valid_mask = tf.reshape(valid_mask, [-1])
embedding_dims = outputs[embedding_key].get_shape().as_list()[-1]
if embedding_dims is None:
raise ValueError(
'Embedding dimension is unknown at graph construction time.')
embedding = tf.reshape(outputs[embedding_key], [-1, embedding_dims])
embedding = tf.boolean_mask(embedding, valid_mask)
return metric_learning_losses.regularization_loss(
embedding=embedding,
lambda_coef=lambda_coef,
regularization_type=regularization_type)