def fn():
for field in standard_fields.get_input_object_fields():
if field in inputs:
inputs[field] = tf.boolean_mask(inputs[field], valid_mask)
for field in standard_fields.get_output_object_fields():
if field in outputs:
outputs[field] = tf.boolean_mask(outputs[field], valid_mask)
return _box_corner_distance_loss(
loss_type=loss_type,
is_balanced=is_balanced,
input_boxes_length=inputs[
standard_fields.InputDataFields.objects_length],
input_boxes_height=inputs[
standard_fields.InputDataFields.objects_height],
input_boxes_width=inputs[standard_fields.InputDataFields.objects_width],
input_boxes_center=inputs[
standard_fields.InputDataFields.objects_center],
input_boxes_rotation_matrix=inputs[
standard_fields.InputDataFields.objects_rotation_matrix],
input_boxes_instance_id=inputs[
standard_fields.InputDataFields.objects_instance_id],
output_boxes_length=outputs[
standard_fields.DetectionResultFields.objects_length],
output_boxes_height=outputs[
standard_fields.DetectionResultFields.objects_height],
output_boxes_width=outputs[
standard_fields.DetectionResultFields.objects_width],
output_boxes_center=outputs[
standard_fields.DetectionResultFields.objects_center],
output_boxes_rotation_matrix=outputs[
standard_fields.DetectionResultFields.objects_rotation_matrix],
delta=delta)
def get_batch_size_1_input_objects(inputs, b):
"""Returns input dictionary containing tensors with batch size of 1.
Note that this function only applies its example selection to the object
tensors.
Args:
inputs: A dictionary of tf.Tensors with our input data.
b: Example index in the batch.
Returns:
inputs_1: A dictionary of tf.Tensors with batch size of one.
"""
b_1_inputs = {}
for field in standard_fields.get_input_object_fields():
if field in inputs:
b_1_inputs[field] = inputs[field][b]
return b_1_inputs
def split_inputs(inputs,
input_field_mapping_fn,
image_preprocess_fn_dic,
images_points_correspondence_fn):
"""Splits inputs to view_image_inputs, view_indices_2d_inputs, mesh_inputs.
Args:
inputs: Input dictionary.
input_field_mapping_fn: A function that maps the input fields to the
fields expected by object detection pipeline.
image_preprocess_fn_dic: A dictionary of image preprocessing functions.
images_points_correspondence_fn: A function that returns image and points
correspondences.
Returns:
view_image_inputs: A dictionary containing image inputs.
view_indices_2d_inputs: A dictionary containing indices 2d inputs.
mesh_inputs: A dictionary containing mesh inputs.
object_inputs: A dictionary containing object inputs.
non_tensor_inputs: Other inputs.
"""
# Initializing empty dictionary for mesh, image, indices_2d and non tensor
# inputs.
non_tensor_inputs = {}
view_image_inputs = {}
view_indices_2d_inputs = {}
mesh_inputs = {}
object_inputs = {}
if image_preprocess_fn_dic is None:
image_preprocess_fn_dic = {}
# Acquire point / image correspondences.
if images_points_correspondence_fn is not None:
fn_outputs = images_points_correspondence_fn(inputs)
if 'points_position' in fn_outputs:
inputs[standard_fields.InputDataFields
.point_positions] = fn_outputs['points_position']
if 'points_intensity' in fn_outputs:
inputs[standard_fields.InputDataFields
.point_intensities] = fn_outputs['points_intensity']
if 'points_elongation' in fn_outputs:
inputs[standard_fields.InputDataFields
.point_elongations] = fn_outputs['points_elongation']
if 'points_normal' in fn_outputs:
inputs[standard_fields.InputDataFields
.point_normals] = fn_outputs['points_normal']
if 'points_color' in fn_outputs:
inputs[standard_fields.InputDataFields
.point_colors] = fn_outputs['points_color']
if 'view_images' in fn_outputs:
for key in sorted(fn_outputs['view_images']):
if len(fn_outputs['view_images'][key].shape) != 4:
raise ValueError(('%s image should have rank 4.' % key))
view_image_inputs = fn_outputs['view_images']
if 'view_indices_2d' in fn_outputs:
for key in sorted(fn_outputs['view_indices_2d']):
if len(fn_outputs['view_indices_2d'][key].shape) != 3:
raise ValueError(('%s indices_2d should have rank 3.' % key))
view_indices_2d_inputs = fn_outputs['view_indices_2d']
if input_field_mapping_fn is not None:
inputs = input_field_mapping_fn(inputs)
# Setting mesh inputs
mesh_keys = []
for key in standard_fields.get_input_point_fields():
if key in inputs:
mesh_keys.append(key)
object_keys = []
for key in standard_fields.get_input_object_fields():
if key in inputs:
object_keys.append(key)
for k, v in inputs.items():
if k in mesh_keys:
mesh_inputs[k] = v
elif k in object_keys:
object_inputs[k] = v
else:
non_tensor_inputs[k] = v
logging.info('view image inputs')
logging.info(view_image_inputs)
logging.info('view indices 2d inputs')
logging.info(view_indices_2d_inputs)
logging.info('mesh inputs')
logging.info(mesh_inputs)
logging.info('object inputs')
logging.info(object_inputs)
logging.info('non_tensor_inputs')
logging.info(non_tensor_inputs)
return (view_image_inputs, view_indices_2d_inputs, mesh_inputs, object_inputs,
non_tensor_inputs)
def prepare_kitti_dataset(inputs, valid_object_classes=None):
"""Maps the fields from loaded input to standard fields.
Args:
inputs: A dictionary of input tensors.
valid_object_classes: List of valid object classes. if None, it is ignored.
Returns:
A dictionary of input tensors with standard field names.
"""
prepared_inputs = {}
prepared_inputs[standard_fields.InputDataFields.point_positions] = inputs[
standard_fields.InputDataFields.point_positions]
prepared_inputs[standard_fields.InputDataFields.point_intensities] = inputs[
standard_fields.InputDataFields.point_intensities]
prepared_inputs[standard_fields.InputDataFields
.camera_intrinsics] = inputs['cameras/cam02/intrinsics/K']
prepared_inputs[standard_fields.InputDataFields.
camera_rotation_matrix] = inputs['cameras/cam02/extrinsics/R']
prepared_inputs[standard_fields.InputDataFields
.camera_translation] = inputs['cameras/cam02/extrinsics/t']
prepared_inputs[standard_fields.InputDataFields
.camera_image] = inputs['cameras/cam02/image']
prepared_inputs[standard_fields.InputDataFields
.camera_raw_image] = inputs['cameras/cam02/image']
prepared_inputs[standard_fields.InputDataFields
.camera_original_image] = inputs['cameras/cam02/image']
if 'scene_name' in inputs and 'frame_name' in inputs:
prepared_inputs[
standard_fields.InputDataFields.camera_image_name] = tf.strings.join(
[inputs['scene_name'], inputs['frame_name']], separator='_')
if 'objects/pose/R' in inputs:
prepared_inputs[standard_fields.InputDataFields
.objects_rotation_matrix] = inputs['objects/pose/R']
if 'objects/pose/t' in inputs:
prepared_inputs[standard_fields.InputDataFields
.objects_center] = inputs['objects/pose/t']
if 'objects/shape/dimension' in inputs:
prepared_inputs[
standard_fields.InputDataFields.objects_length] = tf.reshape(
inputs['objects/shape/dimension'][:, 0], [-1, 1])
prepared_inputs[standard_fields.InputDataFields.objects_width] = tf.reshape(
inputs['objects/shape/dimension'][:, 1], [-1, 1])
prepared_inputs[
standard_fields.InputDataFields.objects_height] = tf.reshape(
inputs['objects/shape/dimension'][:, 2], [-1, 1])
if 'objects/category/label' in inputs:
prepared_inputs[standard_fields.InputDataFields.objects_class] = tf.reshape(
inputs['objects/category/label'], [-1, 1])
if valid_object_classes is not None:
valid_objects_mask = tf.cast(
tf.zeros_like(
prepared_inputs[standard_fields.InputDataFields.objects_class],
dtype=tf.int32),
dtype=tf.bool)
for object_class in valid_object_classes:
valid_objects_mask = tf.logical_or(
valid_objects_mask,
tf.equal(
prepared_inputs[standard_fields.InputDataFields.objects_class],
object_class))
valid_objects_mask = tf.reshape(valid_objects_mask, [-1])
for key in standard_fields.get_input_object_fields():
if key in prepared_inputs:
prepared_inputs[key] = tf.boolean_mask(prepared_inputs[key],
valid_objects_mask)
return prepared_inputs
def prepare_waymo_open_dataset(inputs,
valid_object_classes=None,
max_object_distance_from_source=74.88):
"""Maps the fields from loaded input to standard fields.
Args:
inputs: A dictionary of input tensors.
valid_object_classes: List of valid object classes. if None, it is ignored.
max_object_distance_from_source: Maximum distance of objects from source. It
will be ignored if None.
Returns:
A dictionary of input tensors with standard field names.
"""
prepared_inputs = {}
if standard_fields.InputDataFields.point_positions in inputs:
prepared_inputs[standard_fields.InputDataFields.point_positions] = inputs[
standard_fields.InputDataFields.point_positions]
if standard_fields.InputDataFields.point_intensities in inputs:
prepared_inputs[standard_fields.InputDataFields.point_intensities] = inputs[
standard_fields.InputDataFields.point_intensities]
if standard_fields.InputDataFields.point_elongations in inputs:
prepared_inputs[standard_fields.InputDataFields.point_elongations] = inputs[
standard_fields.InputDataFields.point_elongations]
if standard_fields.InputDataFields.point_normals in inputs:
prepared_inputs[standard_fields.InputDataFields.point_normals] = inputs[
standard_fields.InputDataFields.point_normals]
if 'cameras/front/intrinsics/K' in inputs:
prepared_inputs[standard_fields.InputDataFields
.camera_intrinsics] = inputs['cameras/front/intrinsics/K']
if 'cameras/front/extrinsics/R' in inputs:
prepared_inputs[
standard_fields.InputDataFields
.camera_rotation_matrix] = inputs['cameras/front/extrinsics/R']
if 'cameras/front/extrinsics/t' in inputs:
prepared_inputs[standard_fields.InputDataFields
.camera_translation] = inputs['cameras/front/extrinsics/t']
if 'cameras/front/image' in inputs:
prepared_inputs[standard_fields.InputDataFields
.camera_image] = inputs['cameras/front/image']
prepared_inputs[standard_fields.InputDataFields
.camera_raw_image] = inputs['cameras/front/image']
prepared_inputs[standard_fields.InputDataFields
.camera_original_image] = inputs['cameras/front/image']
if 'scene_name' in inputs and 'frame_name' in inputs:
prepared_inputs[
standard_fields.InputDataFields.camera_image_name] = tf.strings.join(
[inputs['scene_name'], inputs['frame_name']], separator='_')
if 'objects/pose/R' in inputs:
prepared_inputs[standard_fields.InputDataFields
.objects_rotation_matrix] = inputs['objects/pose/R']
if 'objects/pose/t' in inputs:
prepared_inputs[standard_fields.InputDataFields
.objects_center] = inputs['objects/pose/t']
if 'objects/shape/dimension' in inputs:
prepared_inputs[
standard_fields.InputDataFields.objects_length] = tf.reshape(
inputs['objects/shape/dimension'][:, 0], [-1, 1])
prepared_inputs[standard_fields.InputDataFields.objects_width] = tf.reshape(
inputs['objects/shape/dimension'][:, 1], [-1, 1])
prepared_inputs[
standard_fields.InputDataFields.objects_height] = tf.reshape(
inputs['objects/shape/dimension'][:, 2], [-1, 1])
if 'objects/category/label' in inputs:
prepared_inputs[standard_fields.InputDataFields.objects_class] = tf.reshape(
inputs['objects/category/label'], [-1, 1])
if valid_object_classes is not None:
valid_objects_mask = tf.cast(
tf.zeros_like(
prepared_inputs[standard_fields.InputDataFields.objects_class],
dtype=tf.int32),
dtype=tf.bool)
for object_class in valid_object_classes:
valid_objects_mask = tf.logical_or(
valid_objects_mask,
tf.equal(
prepared_inputs[standard_fields.InputDataFields.objects_class],
object_class))
valid_objects_mask = tf.reshape(valid_objects_mask, [-1])
for key in standard_fields.get_input_object_fields():
if key in prepared_inputs:
prepared_inputs[key] = tf.boolean_mask(prepared_inputs[key],
valid_objects_mask)
if max_object_distance_from_source is not None:
if standard_fields.InputDataFields.objects_center in prepared_inputs:
object_distances = tf.norm(
prepared_inputs[standard_fields.InputDataFields.objects_center][:,
0:2],
axis=1)
valid_mask = tf.less(object_distances, max_object_distance_from_source)
for key in standard_fields.get_input_object_fields():
if key in prepared_inputs:
prepared_inputs[key] = tf.boolean_mask(prepared_inputs[key],
valid_mask)
return prepared_inputs
