def test_postprocess_with_nms(self):
num_voxels = 10000
outputs = {
standard_fields.DetectionResultFields.object_semantic_voxels:
tf.random.uniform([num_voxels, 10],
minval=-1.0,
maxval=1.0,
dtype=tf.float32),
standard_fields.DetectionResultFields.instance_embedding_voxels:
tf.random.uniform([num_voxels, 64],
minval=-1.0,
maxval=1.0,
dtype=tf.float32)
}
postprocessor.postprocess(
outputs=outputs,
num_furthest_voxel_samples=200,
sampler_score_vs_distance_coef=0.5,
embedding_similarity_strategy='distance',
apply_nms=True,
nms_score_threshold=0.1)
num_instances = outputs[standard_fields.DetectionResultFields
.instance_segments_voxel_mask].shape[0]
self.assertAllEqual(
outputs[standard_fields.DetectionResultFields
.instance_segments_voxel_mask].shape,
np.array([num_instances, num_voxels]))
self.assertAllEqual(
outputs[standard_fields.DetectionResultFields.objects_class].shape,
np.array([num_instances, 1]))
self.assertAllEqual(
outputs[standard_fields.DetectionResultFields.objects_score].shape,
np.array([num_instances, 1]))
def postprocess(inputs, outputs, is_training, num_furthest_voxel_samples,
sampler_score_vs_distance_coef, embedding_similarity_strategy,
embedding_similarity_threshold, score_threshold, apply_nms,
nms_iou_threshold):
"""Post-processor function.
Args:
inputs: A dictionary containing input tensors.
outputs: A dictionary containing predicted tensors.
is_training: If during training stage or not.
num_furthest_voxel_samples: Number of voxels to be sampled using furthest
voxel sampling in the postprocessor.
sampler_score_vs_distance_coef: The coefficient that balances the weight
between furthest voxel sampling and highest score sampling in the
postprocessor.
embedding_similarity_strategy: Embedding similarity strategy.
embedding_similarity_threshold: Similarity threshold used to decide if two
point embedding vectors belong to the same instance.
score_threshold: Instance score threshold used throughout postprocessing.
apply_nms: If True, it will apply non-maximum suppression to the final
predictions.
nms_iou_threshold: Intersection over union threshold used in non-maximum
suppression.
"""
if not is_training:
# Squeeze output voxel properties.
for key in standard_fields.get_output_voxel_fields():
if key in outputs and outputs[key] is not None:
outputs[key] = tf.squeeze(outputs[key], axis=0)
# Squeeze output point properties.
for key in standard_fields.get_output_point_fields():
if key in outputs and outputs[key] is not None:
outputs[key] = tf.squeeze(outputs[key], axis=0)
# Squeeze output object properties.
for key in standard_fields.get_output_object_fields():
if key in outputs and outputs[key] is not None:
outputs[key] = tf.squeeze(outputs[key], axis=0)
# Mask the valid voxels
mask_valid_voxels(inputs=inputs, outputs=outputs)
# Mask the valid points
mask_valid_points(inputs=inputs, outputs=outputs)
# NMS
postprocessor.postprocess(
outputs=outputs,
num_furthest_voxel_samples=num_furthest_voxel_samples,
sampler_score_vs_distance_coef=sampler_score_vs_distance_coef,
embedding_similarity_strategy=embedding_similarity_strategy,
embedding_similarity_threshold=embedding_similarity_threshold,
apply_nms=apply_nms,
nms_score_threshold=score_threshold,
nms_iou_threshold=nms_iou_threshold)
# Add instance segment point masks at eval time
if standard_fields.InputDataFields.points_to_voxel_mapping in inputs:
instance_segments_point_mask = (
voxel_utils.sparse_voxel_grid_to_pointcloud(
voxel_features=tf.expand_dims(tf.transpose(
outputs[standard_fields.DetectionResultFields.
instance_segments_voxel_mask]),
axis=0),
segment_ids=inputs[standard_fields.InputDataFields.
points_to_voxel_mapping],
num_valid_voxels=inputs[
standard_fields.InputDataFields.num_valid_voxels],
num_valid_points=inputs[
standard_fields.InputDataFields.num_valid_points]))
outputs[standard_fields.DetectionResultFields.
instance_segments_point_mask] = tf.transpose(
tf.squeeze(instance_segments_point_mask, axis=0))