def test_randomly_sample_points(self):
mesh_inputs = {
'point_positions':
tf.random.uniform([100000, 3],
minval=-10.0,
maxval=10.0,
dtype=tf.float32)
}
preprocessor_utils.randomly_sample_points(mesh_inputs=mesh_inputs,
view_indices_2d_inputs={},
target_num_points=1000)
sampled_points = mesh_inputs['point_positions']
self.assertAllEqual(sampled_points.shape, np.array([1000, 3]))
def preprocess(inputs,
output_keys=None,
is_training=False,
input_field_mapping_fn=None,
image_preprocess_fn_dic=None,
images_points_correspondence_fn=None,
points_pad_or_clip_size=None,
voxels_pad_or_clip_size=None,
voxel_grid_cell_size=(0.1, 0.1, 0.1),
num_offset_bins_x=4,
num_offset_bins_y=4,
num_offset_bins_z=4,
point_feature_keys=('point_offset_bins',),
point_to_voxel_segment_func=tf.math.unsorted_segment_mean,
x_min_degree_rotation=None,
x_max_degree_rotation=None,
y_min_degree_rotation=None,
y_max_degree_rotation=None,
z_min_degree_rotation=None,
z_max_degree_rotation=None,
rotation_center=(0.0, 0.0, 0.0),
min_scale_ratio=None,
max_scale_ratio=None,
translation_range=None,
points_within_box_margin=0.0,
num_points_to_randomly_sample=None,
crop_points_around_random_seed_point=False,
crop_num_points=None,
crop_radius=None,
crop_num_background_points=None,
make_objects_axis_aligned=False,
min_num_points_in_objects=0,
fit_objects_to_instance_id_points=False,
voxel_density_threshold=None,
voxel_density_grid_cell_size=None):
"""Preprocesses data before running 3D object detection.
Args:
inputs: A dictionary of inputs. Each value must be a `Tensor`.
output_keys: Either None, or a list of strings containing the keys in the
dictionary that is returned by the preprocess function.
is_training: Whether at training stage or not.
input_field_mapping_fn: A function that maps the input fields to the
fields expected by object detection pipeline.
image_preprocess_fn_dic: Image preprocessing function. Maps view names to
their image preprocessing functions. Set it to None, if there are no
images to preprocess or you are not interested in preprocessing images.
images_points_correspondence_fn: The function that computes correspondence
between images and points.
points_pad_or_clip_size: Number of target points to pad or clip to. If None,
it will not perform the padding.
voxels_pad_or_clip_size: Number of target voxels to pad or clip to. If None,
it will not perform the voxel padding.
voxel_grid_cell_size: A three dimensional tuple determining the voxel grid
size.
num_offset_bins_x: Number of bins for point offsets in x direction.
num_offset_bins_y: Number of bins for point offsets in y direction.
num_offset_bins_z: Number of bins for point offsets in z direction.
point_feature_keys: The keys used to form the voxel features.
point_to_voxel_segment_func: The function used to aggregate the features
of the points that fall in the same voxel.
x_min_degree_rotation: Min degree of rotation around the x axis.
x_max_degree_rotation: Max degree of rotation around the x axis.
y_min_degree_rotation: Min degree of rotation around the y axis.
y_max_degree_rotation: Max degree of rotation around the y axis.
z_min_degree_rotation: Min degree of rotation around the z axis.
z_max_degree_rotation: Max degree of rotation around the z axis.
rotation_center: Center of rotation.
min_scale_ratio: Minimum scale ratio.
max_scale_ratio: Maximum scale ratio.
translation_range: A float value corresponding to the range of random
translation in x, y, z directions. If None, no translation would happen.
points_within_box_margin: A margin to add to box radius when deciding which
points fall inside each box.
num_points_to_randomly_sample: Number of points to randomly sample. If None,
it will keep the original points and does not perform sampling.
crop_points_around_random_seed_point: If True, randomly samples a seed
point and crops the closest `points_pad_or_clip_size` points to the seed
point. The random seed point selection is based on the following
procedure. First an object box is randomly selected. Then a random point
from the random box is selected. Note that the random seed point could be
sampled from background as well.
crop_num_points: Number of points to crop.
crop_radius: The maximum distance of the cropped points from the randomly
sampled point. If None, it won't be used.
crop_num_background_points: Minimum number of background points in crop. If
None, it won't get applied.
make_objects_axis_aligned: If True, the objects will become axis aligned,
meaning that they will have identity rotation matrix.
min_num_points_in_objects: Remove objects that have less number of points
in them than this value.
fit_objects_to_instance_id_points: If True, it will fit objects to points
based on their instance ids.
voxel_density_threshold: Points that belong to a voxel with a density lower
than this will be removed.
voxel_density_grid_cell_size: Voxel grid size for removing noise based on
voxel density threshold.
Returns:
inputs: The inputs processed according to our configuration.
Raises:
ValueError: If input dictionary is missing any of the required keys.
"""
inputs = dict(inputs)
# Convert all float64 to float32 and all int64 to int32.
for key in sorted(inputs):
if isinstance(inputs[key], tf.Tensor):
if inputs[key].dtype == tf.float64:
inputs[key] = tf.cast(inputs[key], dtype=tf.float32)
if inputs[key].dtype == tf.int64:
if key == 'timestamp':
continue
else:
inputs[key] = tf.cast(inputs[key], dtype=tf.int32)
(view_image_inputs, view_indices_2d_inputs, mesh_inputs, object_inputs,
non_tensor_inputs) = split_inputs(
inputs=inputs,
input_field_mapping_fn=input_field_mapping_fn,
image_preprocess_fn_dic=image_preprocess_fn_dic,
images_points_correspondence_fn=images_points_correspondence_fn)
if standard_fields.InputDataFields.point_positions not in mesh_inputs:
raise ValueError('Key %s is missing' %
standard_fields.InputDataFields.point_positions)
# Randomly sample points (optional)
preprocessor_utils.randomly_sample_points(
mesh_inputs=mesh_inputs,
view_indices_2d_inputs=view_indices_2d_inputs,
target_num_points=num_points_to_randomly_sample)
# Remove low density points
if voxel_density_threshold is not None:
preprocessor_utils.remove_pointcloud_noise(
mesh_inputs=mesh_inputs,
view_indices_2d_inputs=view_indices_2d_inputs,
voxel_grid_cell_size=voxel_density_grid_cell_size,
voxel_density_threshold=voxel_density_threshold)
rotation_center = tf.convert_to_tensor(rotation_center, dtype=tf.float32)
# Remove objects that do not have 3d info.
_filter_valid_objects(inputs=object_inputs)
# Cast the objects_class to tf.int32.
_cast_objects_class(inputs=object_inputs)
# Remove objects that have less than a certain number of poitns
if min_num_points_in_objects > 0:
preprocessor_utils.remove_objects_by_num_points(
mesh_inputs=mesh_inputs,
object_inputs=object_inputs,
min_num_points_in_objects=min_num_points_in_objects)
# Set point box ids.
preprocessor_utils.set_point_instance_ids(
mesh_inputs=mesh_inputs,
object_inputs=object_inputs,
points_within_box_margin=points_within_box_margin)
# Process images.
preprocessor_utils.preprocess_images(
view_image_inputs=view_image_inputs,
view_indices_2d_inputs=view_indices_2d_inputs,
image_preprocess_fn_dic=image_preprocess_fn_dic,
is_training=is_training)
# Randomly transform points and boxes.
_randomly_transform_points_boxes(
mesh_inputs=mesh_inputs,
object_inputs=object_inputs,
x_min_degree_rotation=x_min_degree_rotation,
x_max_degree_rotation=x_max_degree_rotation,
y_min_degree_rotation=y_min_degree_rotation,
y_max_degree_rotation=y_max_degree_rotation,
z_min_degree_rotation=z_min_degree_rotation,
z_max_degree_rotation=z_max_degree_rotation,
rotation_center=rotation_center,
min_scale_ratio=min_scale_ratio,
max_scale_ratio=max_scale_ratio,
translation_range=translation_range)
# Randomly crop points around a random seed point.
if crop_points_around_random_seed_point:
preprocessor_utils.crop_points_around_random_seed_point(
mesh_inputs=mesh_inputs,
view_indices_2d_inputs=view_indices_2d_inputs,
num_closest_points=crop_num_points,
max_distance=crop_radius,
num_background_points=crop_num_background_points)
if fit_objects_to_instance_id_points:
preprocessor_utils.fit_objects_to_instance_id_points(
mesh_inputs=mesh_inputs, object_inputs=object_inputs)
if make_objects_axis_aligned:
preprocessor_utils.make_objects_axis_aligned(object_inputs=object_inputs)
# Putting back the dictionaries together
inputs = mesh_inputs.copy()
inputs.update(object_inputs)
inputs.update(non_tensor_inputs)
for key in sorted(view_image_inputs):
inputs[('%s/features' % key)] = view_image_inputs[key]
for key in sorted(view_indices_2d_inputs):
inputs[('%s/indices_2d' % key)] = view_indices_2d_inputs[key]
# Transfer object properties to points, and randomly rotate the points around
# y axis at training time.
_transfer_object_properties_to_points(inputs=inputs)
# Pad or clip points and their properties.
_pad_or_clip_point_properties(
inputs=inputs, pad_or_clip_size=points_pad_or_clip_size)
# Create features that do not exist
preprocessor_utils.add_point_offsets(
inputs=inputs, voxel_grid_cell_size=voxel_grid_cell_size)
preprocessor_utils.add_point_offset_bins(
inputs=inputs,
voxel_grid_cell_size=voxel_grid_cell_size,
num_bins_x=num_offset_bins_x,
num_bins_y=num_offset_bins_y,
num_bins_z=num_offset_bins_z)
# Voxelize point features
preprocessor_utils.voxelize_point_features(
inputs=inputs,
voxels_pad_or_clip_size=voxels_pad_or_clip_size,
voxel_grid_cell_size=voxel_grid_cell_size,
point_feature_keys=point_feature_keys,
point_to_voxel_segment_func=point_to_voxel_segment_func)
# Voxelizing the semantic labels
preprocessor_utils.voxelize_semantic_labels(
inputs=inputs,
voxels_pad_or_clip_size=voxels_pad_or_clip_size,
voxel_grid_cell_size=voxel_grid_cell_size)
# Voxelizing the instance labels
preprocessor_utils.voxelize_instance_labels(
inputs=inputs,
voxels_pad_or_clip_size=voxels_pad_or_clip_size,
voxel_grid_cell_size=voxel_grid_cell_size)
# Voxelize the object properties
preprocessor_utils.voxelize_object_properties(
inputs=inputs,
voxels_pad_or_clip_size=voxels_pad_or_clip_size,
voxel_grid_cell_size=voxel_grid_cell_size)
# Filter preinputs by output_keys if it is not None.
if output_keys is not None:
for key in list(inputs):
if key not in output_keys:
inputs.pop(key, None)
return inputs
def preprocess(inputs,
output_keys=None,
is_training=False,
using_sequence_dataset=False,
num_frame_to_load=1,
transform_points_fn=None,
image_preprocess_fn_dic=None,
images_points_correspondence_fn=None,
compute_semantic_labels_fn=None,
compute_motion_labels_fn=None,
view_names=(),
points_key='points',
colors_key='colors',
normals_key='normals',
intensities_key='intensities',
elongations_key='elongations',
semantic_labels_key='semantic_labels',
motion_labels_key='motion_labels',
spin_coords_key=None,
points_in_image_frame_key=None,
num_points_to_randomly_sample=None,
x_min_degree_rotation=None,
x_max_degree_rotation=None,
y_min_degree_rotation=None,
y_max_degree_rotation=None,
z_min_degree_rotation=None,
z_max_degree_rotation=None,
points_pad_or_clip_size=None,
voxels_pad_or_clip_size=None,
voxel_grid_cell_size=(0.1, 0.1, 0.1),
num_offset_bins_x=4,
num_offset_bins_y=4,
num_offset_bins_z=4,
point_feature_keys=('point_offsets', ),
point_to_voxel_segment_func=tf.math.unsorted_segment_mean,
x_random_crop_size=None,
y_random_crop_size=None,
min_scale_ratio=None,
max_scale_ratio=None,
semantic_labels_offset=0,
ignore_labels=(),
remove_unlabeled_images_and_points=False,
labeled_view_name=None,
only_keep_first_return_lidar_points=False):
"""Preprocesses a dictionary of `Tensor` inputs.
If is_training=True, it will randomly rotate the points around the z axis,
and will randomly flip the points with respect to x and/or y axis.
Note that the preprocessor function does not correct normal vectors if they
exist in the inputs.
Note that the preprocessing effects all values of `inputs` that are `Tensors`.
Args:
inputs: A dictionary of inputs. Each value must be a `Tensor`.
output_keys: Either None, or a list of strings containing the keys in the
dictionary that is returned by the preprocess function.
is_training: Whether we're training or testing.
using_sequence_dataset: if true, the inputs will contain scene and multiple
frames data.
num_frame_to_load: If greater than 1, load multiframe point cloud point
positions and its correspondence.
transform_points_fn: Fn to transform other frames to a specific frame's
coordinate.
image_preprocess_fn_dic: Image preprocessing function. Maps view names to
their image preprocessing functions. Set it to None, if there are no
images to preprocess or you are not interested in preprocesing images.
images_points_correspondence_fn: The function that computes correspondence
between images and points.
compute_semantic_labels_fn: If not None, semantic labels will be computed
using this function.
compute_motion_labels_fn: If not None, motion labels will be computed using
this function.
view_names: Names corresponding to 2d views of the scene.
points_key: The key used for `points` in the inputs.
colors_key: The key used for `colors` in the inputs.
normals_key: The key used for 'normals' in the inputs.
intensities_key: The key used for 'intensities' in the inputs.
elongations_key: The key used for 'elongations' in the inputs.
semantic_labels_key: The key used for 'semantic_labels' in the inputs.
motion_labels_key: The key used for 'motion_labels' in the inputs.
spin_coords_key: The key used for 'spin_coords' in the inputs. In Waymo
data, spin_coords is a [num_points, 3] tensor that contains scan_index,
shot_index, return_index. In Waymo data, return_index of the first return
points is 0.
points_in_image_frame_key: A string that identifies the tensor that contains
the points_in_image_frame tensor. If None, it won't be used.
num_points_to_randomly_sample: Number of points to randomly sample. If None,
it will keep the original points and does not perform sampling.
x_min_degree_rotation: Min degree of rotation around the x axis.
x_max_degree_rotation: Max degree of ratation around the x axis.
y_min_degree_rotation: Min degree of rotation around the y axis.
y_max_degree_rotation: Max degree of ratation around the y axis.
z_min_degree_rotation: Min degree of rotation around the z axis.
z_max_degree_rotation: Max degree of ratation around the z axis.
points_pad_or_clip_size: Number of target points to pad or clip to. If None,
it will not perform the point padding.
voxels_pad_or_clip_size: Number of target voxels to pad or clip to. If None,
it will not perform the voxel padding.
voxel_grid_cell_size: A three dimensional tuple determining the voxel grid
size.
num_offset_bins_x: Number of bins for point offsets in x direction.
num_offset_bins_y: Number of bins for point offsets in y direction.
num_offset_bins_z: Number of bins for point offsets in z direction.
point_feature_keys: The keys used to form the voxel features.
point_to_voxel_segment_func: The function used to aggregate the features
of the points that fall in the same voxel.
x_random_crop_size: Size of the random crop in x dimension. If None, random
crop will not take place on x dimension.
y_random_crop_size: Size of the random crop in y dimension. If None, random
crop will not take place on y dimension.
min_scale_ratio: Minimum scale ratio. Used for scaling point cloud.
max_scale_ratio: Maximum scale ratio. Used for scaling point cloud.
semantic_labels_offset: An integer offset that will be added to labels.
ignore_labels: A tuple containing labels that should be ignored when
computing the loss and metrics.
remove_unlabeled_images_and_points: If True, removes the images that are not
labeled and also removes the points that are associated with those images.
labeled_view_name: The name of the view that is labeled, otherwise None.
only_keep_first_return_lidar_points: If True, we only keep the first return
lidar points.
Returns:
The mean subtracted points with an optional rotation applied.
Raises:
ValueError: if `inputs` doesn't contain the points_key.
ValueError: if `points_in_image_frame` does not have rank 3.
"""
inputs = dict(inputs)
if using_sequence_dataset:
all_frame_inputs = inputs
scene = all_frame_inputs['scene']
frame1 = all_frame_inputs['frame1']
frame_start_index = all_frame_inputs['frame_start_index']
inputs = dict(
all_frame_inputs['frame0']
) # so that the following processing code can be unchanged.
# Initializing empty dictionary for mesh, image, indices_2d and non tensor
# inputs.
non_tensor_inputs = {}
view_image_inputs = {}
view_indices_2d_inputs = {}
mesh_inputs = {}
if image_preprocess_fn_dic is None:
image_preprocess_fn_dic = {}
# Convert all float64 to float32 and all int64 to int32.
for key in sorted(inputs):
if isinstance(inputs[key], tf.Tensor):
if inputs[key].dtype == tf.float64:
inputs[key] = tf.cast(inputs[key], dtype=tf.float32)
if inputs[key].dtype == tf.int64:
inputs[key] = tf.cast(inputs[key], dtype=tf.int32)
if points_key in inputs:
inputs[standard_fields.InputDataFields.
point_positions] = inputs[points_key]
if colors_key is not None and colors_key in inputs:
inputs[
standard_fields.InputDataFields.point_colors] = inputs[colors_key]
if normals_key is not None and normals_key in inputs:
inputs[standard_fields.InputDataFields.
point_normals] = inputs[normals_key]
if intensities_key is not None and intensities_key in inputs:
inputs[standard_fields.InputDataFields.
point_intensities] = inputs[intensities_key]
if elongations_key is not None and elongations_key in inputs:
inputs[standard_fields.InputDataFields.
point_elongations] = inputs[elongations_key]
if semantic_labels_key is not None and semantic_labels_key in inputs:
inputs[standard_fields.InputDataFields.
object_class_points] = inputs[semantic_labels_key]
if motion_labels_key is not None and motion_labels_key in inputs:
inputs[standard_fields.InputDataFields.
object_flow_points] = inputs[motion_labels_key]
if spin_coords_key is not None and spin_coords_key in inputs:
inputs[standard_fields.InputDataFields.
point_spin_coordinates] = inputs[spin_coords_key]
# 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 and intensities_key is not None:
inputs[standard_fields.InputDataFields.
point_intensities] = fn_outputs['points_intensity']
if 'points_elongation' in fn_outputs and elongations_key is not None:
inputs[standard_fields.InputDataFields.
point_elongations] = fn_outputs['points_elongation']
if 'points_label' in fn_outputs and semantic_labels_key is not None:
inputs[standard_fields.InputDataFields.
object_class_points] = fn_outputs['points_label']
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']
else:
if points_in_image_frame_key is not None:
inputs['rgb_view/features'] = inputs['image']
inputs['rgb_view/indices_2d'] = inputs[points_in_image_frame_key]
if len(inputs['rgb_view/indices_2d'].shape) != 3:
raise ValueError('`points_in_image_frame` should have rank 3.')
frame0 = inputs.copy()
if num_frame_to_load > 1:
point_positions_list = [
frame0[standard_fields.InputDataFields.point_positions]
]
if view_indices_2d_inputs:
view_indices_2d_list = [view_indices_2d_inputs[view_names[0]]]
frame_source_list = [
tf.zeros([
tf.shape(
frame0[standard_fields.InputDataFields.point_positions])[0]
], tf.int32)
]
for i in range(1, num_frame_to_load):
target_frame_key = 'frame' + str(i)
if images_points_correspondence_fn is not None:
frame_i = images_points_correspondence_fn(
all_frame_inputs[target_frame_key])
else:
raise ValueError(
'images_points_correspondence_fn is needed for loading multi-frame pointclouds.'
)
transformed_point_positions = transform_points_fn(
scene, frame_i['points_position'], frame_start_index,
i + frame_start_index)
point_positions_list.append(transformed_point_positions)
if view_indices_2d_inputs:
view_indices_2d_list.append(
frame_i['view_indices_2d'][view_names[0]])
frame_source_list.append(
tf.ones([tf.shape(transformed_point_positions)[0]], tf.int32) *
i)
# add multi-frame info to override inputs and view_indices_2d_inputs
inputs[standard_fields.InputDataFields.
point_frame_index] = tf.expand_dims(tf.concat(frame_source_list,
axis=0),
axis=1)
inputs[standard_fields.InputDataFields.point_positions] = tf.concat(
point_positions_list, axis=0)
if view_indices_2d_inputs:
view_indices_2d_inputs[view_names[0]] = tf.concat(
view_indices_2d_list, axis=1)
# Validate inputs.
if standard_fields.InputDataFields.point_positions not in inputs:
raise ValueError('`inputs` must contain a point_positions')
if inputs[
standard_fields.InputDataFields.point_positions].shape.ndims != 2:
raise ValueError('points must be of rank 2.')
if inputs[standard_fields.InputDataFields.point_positions].shape[1] != 3:
raise ValueError('point should be 3 dimensional.')
# Remove normal nans.
if standard_fields.InputDataFields.point_normals in inputs:
inputs[standard_fields.InputDataFields.point_normals] = tf.where(
tf.math.is_nan(
inputs[standard_fields.InputDataFields.point_normals]),
tf.zeros_like(
inputs[standard_fields.InputDataFields.point_normals]),
inputs[standard_fields.InputDataFields.point_normals])
# Compute semantic labels if compute_semantic_labels_fn is not None
# An example is when the ground-truth contains 3d object boxes and not per
# point labels. This would be a function that infers point labels from boxes.
if compute_semantic_labels_fn is not None:
inputs[standard_fields.InputDataFields.
object_class_points] = compute_semantic_labels_fn(
inputs=frame0,
points_key=standard_fields.InputDataFields.point_positions)
if compute_motion_labels_fn is not None:
inputs[standard_fields.InputDataFields.
object_flow_points] = compute_motion_labels_fn(
scene=scene,
frame0=frame0,
frame1=frame1,
frame_start_index=frame_start_index,
points_key=standard_fields.InputDataFields.point_positions)
# Splitting inputs to {view_image_inputs,
# view_indices_2d_inputs,
# mesh_inputs,
# non_tensor_inputs}
mesh_keys = []
for key in [
standard_fields.InputDataFields.point_positions,
standard_fields.InputDataFields.point_colors,
standard_fields.InputDataFields.point_normals,
standard_fields.InputDataFields.point_intensities,
standard_fields.InputDataFields.point_elongations,
standard_fields.InputDataFields.object_class_points,
standard_fields.InputDataFields.point_spin_coordinates,
standard_fields.InputDataFields.object_flow_points,
standard_fields.InputDataFields.point_frame_index,
]:
if key is not None and key in inputs:
mesh_keys.append(key)
view_image_names = [('%s/features' % key) for key in view_names]
view_indices_2d_names = [('%s/indices_2d' % key) for key in view_names]
# Additional key collecting
for k, v in six.iteritems(inputs):
if k in view_image_names:
view_image_inputs[k] = v
elif k in view_indices_2d_names:
view_indices_2d_inputs[k] = v
elif k in mesh_keys:
if num_frame_to_load > 1:
pad_size = tf.shape(
inputs[standard_fields.InputDataFields.
point_positions])[0] - tf.shape(v)[0]
if k == standard_fields.InputDataFields.object_class_points:
pad_value = -1
else:
pad_value = 0
v = tf.pad(v, [[0, pad_size], [0, 0]],
constant_values=pad_value)
mesh_inputs[k] = v
else:
non_tensor_inputs[k] = v
# Remove points that are not in the lidar first return (optional)
if only_keep_first_return_lidar_points:
_remove_second_return_lidar_points(
mesh_inputs=mesh_inputs,
view_indices_2d_inputs=view_indices_2d_inputs)
# Randomly sample points
preprocessor_utils.randomly_sample_points(
mesh_inputs=mesh_inputs,
view_indices_2d_inputs=view_indices_2d_inputs,
target_num_points=num_points_to_randomly_sample)
# Add weights if it does not exist in inputs. The weight of the points with
# label in `ignore_labels` is set to 0. This helps the loss and metrics to
# ignore those labels.
use_weights = (
standard_fields.InputDataFields.object_class_points in mesh_inputs
or standard_fields.InputDataFields.object_flow_points in mesh_inputs)
if use_weights:
if num_frame_to_load > 1:
num_valid_points_frame0 = tf.shape(
frame0[standard_fields.InputDataFields.point_positions])[0]
num_additional_frame_points = tf.shape(
mesh_inputs[standard_fields.InputDataFields.
object_class_points])[0] - num_valid_points_frame0
weights = tf.concat([
tf.ones([num_valid_points_frame0, 1], tf.float32),
tf.zeros([num_additional_frame_points, 1], tf.float32)
],
axis=0)
else:
weights = tf.ones_like(mesh_inputs[
standard_fields.InputDataFields.object_class_points],
dtype=tf.float32)
if standard_fields.InputDataFields.object_class_points in mesh_inputs:
mesh_inputs[
standard_fields.InputDataFields.object_class_points] = tf.cast(
mesh_inputs[
standard_fields.InputDataFields.object_class_points],
dtype=tf.int32)
for ignore_label in ignore_labels:
weights *= tf.cast(tf.not_equal(
mesh_inputs[
standard_fields.InputDataFields.object_class_points],
ignore_label),
dtype=tf.float32)
mesh_inputs[
standard_fields.InputDataFields.point_loss_weights] = weights
mesh_inputs[standard_fields.InputDataFields.
object_class_points] += semantic_labels_offset
# We normalize the intensities and elongations to be in a smaller range.
if standard_fields.InputDataFields.point_intensities in mesh_inputs:
mesh_inputs[standard_fields.InputDataFields.
point_intensities] = change_intensity_range(
intensities=mesh_inputs[
standard_fields.InputDataFields.point_intensities])
if standard_fields.InputDataFields.point_elongations in mesh_inputs:
mesh_inputs[
standard_fields.InputDataFields.point_elongations] = (tf.cast(
mesh_inputs[standard_fields.InputDataFields.point_elongations],
dtype=tf.float32) * 2.0 / 255.0) - 1.0
# Random scale the points.
if min_scale_ratio is not None and max_scale_ratio is not None:
scale_ratio = tf.random.uniform([],
minval=min_scale_ratio,
maxval=max_scale_ratio,
dtype=tf.float32)
mesh_inputs[
standard_fields.InputDataFields.point_positions] *= scale_ratio
if standard_fields.InputDataFields.object_flow_points in mesh_inputs:
mesh_inputs[standard_fields.InputDataFields.
object_flow_points] *= scale_ratio
# Random crop the points.
randomly_crop_points(mesh_inputs=mesh_inputs,
view_indices_2d_inputs=view_indices_2d_inputs,
x_random_crop_size=x_random_crop_size,
y_random_crop_size=y_random_crop_size)
# If training, pick the best labeled image and points that project to it.
# In many datasets, only one image is labeled anyways.
if remove_unlabeled_images_and_points:
pick_labeled_image(mesh_inputs=mesh_inputs,
view_image_inputs=view_image_inputs,
view_indices_2d_inputs=view_indices_2d_inputs,
view_name=labeled_view_name)
# Process images.
preprocessor_utils.preprocess_images(
view_image_inputs=view_image_inputs,
view_indices_2d_inputs=view_indices_2d_inputs,
image_preprocess_fn_dic=image_preprocess_fn_dic,
is_training=is_training)
# Record the original points.
original_points = mesh_inputs[
standard_fields.InputDataFields.point_positions]
if standard_fields.InputDataFields.point_colors in mesh_inputs:
original_colors = mesh_inputs[
standard_fields.InputDataFields.point_colors]
if standard_fields.InputDataFields.point_normals in mesh_inputs:
original_normals = mesh_inputs[
standard_fields.InputDataFields.point_normals]
# Update feature visibility count.
if 'feature_visibility_count' in mesh_inputs:
mesh_inputs['feature_visibility_count'] = tf.maximum(
mesh_inputs['feature_visibility_count'], 1)
mesh_inputs['features'] /= tf.cast(
mesh_inputs['feature_visibility_count'], dtype=tf.float32)
# Subtract mean from points.
mean_points = tf.reduce_mean(
mesh_inputs[standard_fields.InputDataFields.point_positions], axis=0)
mesh_inputs[
standard_fields.InputDataFields.point_positions] -= tf.expand_dims(
mean_points, axis=0)
# Rotate points randomly.
if standard_fields.InputDataFields.point_normals in mesh_inputs:
normals = mesh_inputs[standard_fields.InputDataFields.point_normals]
else:
normals = None
if standard_fields.InputDataFields.object_flow_points in mesh_inputs:
motions = mesh_inputs[
standard_fields.InputDataFields.object_flow_points]
else:
motions = None
(mesh_inputs[standard_fields.InputDataFields.point_positions],
rotated_normals, rotated_motions) = rotate_randomly(
points=mesh_inputs[standard_fields.InputDataFields.point_positions],
normals=normals,
motions=motions,
x_min_degree_rotation=x_min_degree_rotation,
x_max_degree_rotation=x_max_degree_rotation,
y_min_degree_rotation=y_min_degree_rotation,
y_max_degree_rotation=y_max_degree_rotation,
z_min_degree_rotation=z_min_degree_rotation,
z_max_degree_rotation=z_max_degree_rotation)
# Random flipping in x and y directions.
(mesh_inputs[standard_fields.InputDataFields.point_positions],
flipped_normals,
flipped_motions) = flip_randomly_points_and_normals_motions(
points=mesh_inputs[standard_fields.InputDataFields.point_positions],
normals=rotated_normals,
motions=rotated_motions,
is_training=is_training)
if standard_fields.InputDataFields.point_normals in mesh_inputs:
mesh_inputs[
standard_fields.InputDataFields.point_normals] = flipped_normals
if standard_fields.InputDataFields.object_flow_points in mesh_inputs:
mesh_inputs[standard_fields.InputDataFields.
object_flow_points] = flipped_motions
# Normalize RGB to [-1.0, 1.0].
if standard_fields.InputDataFields.point_colors in mesh_inputs:
mesh_inputs[standard_fields.InputDataFields.point_colors] = tf.cast(
mesh_inputs[standard_fields.InputDataFields.point_colors],
dtype=tf.float32)
mesh_inputs[standard_fields.InputDataFields.point_colors] *= (2.0 /
255.0)
mesh_inputs[standard_fields.InputDataFields.point_colors] -= 1.0
# Add original points to mesh inputs.
mesh_inputs[standard_fields.InputDataFields.
point_positions_original] = original_points
if standard_fields.InputDataFields.point_colors in mesh_inputs:
mesh_inputs[standard_fields.InputDataFields.
point_colors_original] = original_colors
if standard_fields.InputDataFields.point_normals in mesh_inputs:
mesh_inputs[standard_fields.InputDataFields.
point_normals_original] = original_normals
# Pad or clip the point tensors.
pad_or_clip(mesh_inputs=mesh_inputs,
view_indices_2d_inputs=view_indices_2d_inputs,
pad_or_clip_size=points_pad_or_clip_size)
if num_frame_to_load > 1:
# Note: num_valid_points is the sum of 'num_points_per_fram' for now.
# num_points_per_frame is each frame's valid num of points.
# TODO(huangrui): if random sampling is called earlier, the count here
# is not guaranteed to be in order. need sorting.
if num_points_to_randomly_sample is not None:
raise ValueError(
'randomly sample is not compatible with padding multi frame point clouds yet!'
)
_, _, mesh_inputs[standard_fields.InputDataFields.
num_valid_points_per_frame] = tf.unique_with_counts(
tf.reshape(
mesh_inputs[standard_fields.InputDataFields.
point_frame_index], [-1]))
if points_pad_or_clip_size is not None:
padded_points = tf.where_v2(
tf.greater(
points_pad_or_clip_size, mesh_inputs[
standard_fields.InputDataFields.num_valid_points]),
points_pad_or_clip_size -
mesh_inputs[standard_fields.InputDataFields.num_valid_points],
0)
# Correct the potential unique count error from optionally padded 0s point
# frame index.
mesh_inputs[
standard_fields.InputDataFields.
num_valid_points_per_frame] -= tf.pad(
tf.expand_dims(padded_points, 0), [[
0,
tf.shape(mesh_inputs[standard_fields.InputDataFields.
num_valid_points_per_frame])[0] -
1
]])
# Putting back the dictionaries together
processed_inputs = mesh_inputs.copy()
processed_inputs.update(non_tensor_inputs)
for key in sorted(view_image_inputs):
processed_inputs[('%s/features' % key)] = view_image_inputs[key]
for key in sorted(view_indices_2d_inputs):
processed_inputs[('%s/indices_2d' % key)] = view_indices_2d_inputs[key]
# Create features that do not exist
if 'point_offsets' in point_feature_keys:
preprocessor_utils.add_point_offsets(
inputs=processed_inputs, voxel_grid_cell_size=voxel_grid_cell_size)
if 'point_offset_bins' in point_feature_keys:
preprocessor_utils.add_point_offset_bins(
inputs=processed_inputs,
voxel_grid_cell_size=voxel_grid_cell_size,
num_bins_x=num_offset_bins_x,
num_bins_y=num_offset_bins_y,
num_bins_z=num_offset_bins_z)
# Voxelize point features
preprocessor_utils.voxelize_point_features(
inputs=processed_inputs,
voxels_pad_or_clip_size=voxels_pad_or_clip_size,
voxel_grid_cell_size=voxel_grid_cell_size,
point_feature_keys=point_feature_keys,
point_to_voxel_segment_func=point_to_voxel_segment_func,
num_frame_to_load=num_frame_to_load)
# Voxelize point / image correspondence indices
preprocessor_utils.voxelize_point_to_view_correspondences(
inputs=processed_inputs,
view_indices_2d_inputs=view_indices_2d_inputs,
voxels_pad_or_clip_size=voxels_pad_or_clip_size,
voxel_grid_cell_size=voxel_grid_cell_size)
# Voxelizing the semantic labels
preprocessor_utils.voxelize_semantic_labels(
inputs=processed_inputs,
voxels_pad_or_clip_size=voxels_pad_or_clip_size,
voxel_grid_cell_size=voxel_grid_cell_size)
# Voxelizing the loss weights
preprocessor_utils.voxelize_property_tensor(
inputs=processed_inputs,
point_tensor_key=standard_fields.InputDataFields.point_loss_weights,
corresponding_voxel_tensor_key=standard_fields.InputDataFields.
voxel_loss_weights,
voxels_pad_or_clip_size=voxels_pad_or_clip_size,
voxel_grid_cell_size=voxel_grid_cell_size,
segment_func=tf.math.unsorted_segment_max)
# Voxelizing the object flow
if standard_fields.InputDataFields.object_flow_points in processed_inputs:
preprocessor_utils.voxelize_property_tensor(
inputs=processed_inputs,
point_tensor_key=standard_fields.InputDataFields.
object_flow_points,
corresponding_voxel_tensor_key='object_flow_voxels_max',
voxels_pad_or_clip_size=voxels_pad_or_clip_size,
voxel_grid_cell_size=voxel_grid_cell_size,
segment_func=tf.math.unsorted_segment_max)
preprocessor_utils.voxelize_property_tensor(
inputs=processed_inputs,
point_tensor_key=standard_fields.InputDataFields.
object_flow_points,
corresponding_voxel_tensor_key='object_flow_voxels_min',
voxels_pad_or_clip_size=voxels_pad_or_clip_size,
voxel_grid_cell_size=voxel_grid_cell_size,
segment_func=tf.math.unsorted_segment_min)
processed_inputs[standard_fields.InputDataFields.
object_flow_voxels] = processed_inputs[
'object_flow_voxels_max'] + processed_inputs[
'object_flow_voxels_min']
if num_frame_to_load > 1:
mesh_inputs[
standard_fields.InputDataFields.num_valid_points] = mesh_inputs[
standard_fields.InputDataFields.num_valid_points_per_frame][0]
# Filter preprocessed_inputs by output_keys if it is not None.
if output_keys is not None:
processed_inputs = {
k: v
for k, v in six.iteritems(processed_inputs) if k in output_keys
}
return processed_inputs
