def CreateDecoderMetrics(self):
"""Decoder metrics for WaymoOpenDataset."""
p = self.params
waymo_metric_p = p.ap_metric.Copy().Set(
cls=waymo_ap_metric.WaymoAPMetrics)
waymo_metrics = waymo_metric_p.Instantiate()
class_names = waymo_metrics.metadata.ClassNames()
# TODO(bencaine,vrv): There's some code smell with this ap_metrics params
# usage. We create local copies of the params to then instantiate them.
# Failing to do this risks users editing the params after construction of
# the object, making each object method call have the potential for side
# effects.
# Create a new dictionary with copies of the params converted to objects
# so we can then add these to the decoder metrics.
extra_ap_metrics = {}
for k, metric_p in p.extra_ap_metrics.items():
extra_ap_metrics[k] = metric_p.Instantiate()
waymo_metric_bev_p = waymo_metric_p.Copy()
waymo_metric_bev_p.box_type = '2d'
waymo_metrics_bev = waymo_metric_bev_p.Instantiate()
# Convert the list of class names to a dictionary mapping class_id -> name.
class_id_to_name = dict(enumerate(class_names))
# TODO(vrv): This uses the same top down transform as for KITTI;
# re-visit these settings since detections can happen all around
# the car.
top_down_transform = transform_util.MakeCarToImageTransform(
pixels_per_meter=32.,
image_ref_x=512.,
image_ref_y=1408.,
flip_axes=True)
decoder_metrics = py_utils.NestedMap({
'top_down_visualization':
(detection_3d_metrics.TopDownVisualizationMetric(
top_down_transform,
image_height=1536,
image_width=1024,
class_id_to_name=class_id_to_name)),
'num_samples_in_batch':
metrics.AverageMetric(),
'waymo_metrics':
waymo_metrics,
'waymo_metrics_bev':
waymo_metrics_bev,
})
self._update_metrics_class_keys = [
'waymo_metrics_bev', 'waymo_metrics'
]
for k, metric in extra_ap_metrics.items():
decoder_metrics[k] = metric
self._update_metrics_class_keys.append(k)
decoder_metrics.mesh = detection_3d_metrics.WorldViewer()
return decoder_metrics
def CreateDecoderMetrics(self):
"""Decoder metrics for WaymoOpenDataset."""
p = self.params
waymo_metric_p = p.ap_metric.Copy().Set(
cls=waymo_ap_metric.WaymoAPMetrics)
waymo_metrics = waymo_metric_p.Instantiate()
class_names = waymo_metrics.metadata.ClassNames()
for k, v in p.extra_ap_metrics.items():
p.extra_ap_metrics[k] = v.Instantiate()
waymo_metric_bev_p = waymo_metric_p.Copy()
waymo_metric_bev_p.box_type = '2d'
waymo_metrics_bev = waymo_metric_bev_p.Instantiate()
# Convert the list of class names to a dictionary mapping class_id -> name.
class_id_to_name = dict(enumerate(class_names))
# TODO(vrv): This uses the same top down transform as for KITTI;
# re-visit these settings since detections can happen all around
# the car.
top_down_transform = transform_util.MakeCarToImageTransform(
pixels_per_meter=32.,
image_ref_x=512.,
image_ref_y=1408.,
flip_axes=True)
decoder_metrics = py_utils.NestedMap({
'top_down_visualization':
(detection_3d_metrics.TopDownVisualizationMetric(
top_down_transform,
image_height=1536,
image_width=1024,
class_id_to_name=class_id_to_name)),
'num_samples_in_batch':
metrics.AverageMetric(),
'waymo_metrics':
waymo_metrics,
'waymo_metrics_bev':
waymo_metrics_bev,
})
self._update_metrics_class_keys = [
'waymo_metrics_bev', 'waymo_metrics'
]
for k, v in p.extra_ap_metrics.items():
decoder_metrics[k] = v
self._update_metrics_class_keys.append(k)
decoder_metrics.mesh = detection_3d_metrics.WorldViewer()
return decoder_metrics
def testTopDownVisualizationMetric(self):
top_down_transform = transform_util.MakeCarToImageTransform(
pixels_per_meter=32.,
image_ref_x=512.,
image_ref_y=1408.,
flip_axes=True)
metric = detection_3d_metrics.TopDownVisualizationMetric(
top_down_transform)
batch_size = 4
num_preds = 10
num_gt = 12
num_points = 128
visualization_labels = np.random.randint(0, 2, (batch_size, num_preds))
predicted_bboxes = np.random.rand(batch_size, num_preds, 5)
visualization_weights = np.abs(np.random.rand(batch_size, num_preds))
labels = np.random.randint(0, 2, (batch_size, num_gt))
gt_bboxes_2d = np.random.rand(batch_size, num_gt, 5)
gt_bboxes_2d_weights = np.abs(np.random.rand(batch_size, num_gt))
difficulties = np.random.randint(0, 3, (batch_size, num_gt))
points_xyz = np.random.rand(batch_size, num_points, 3)
points_padding = np.random.randint(0, 2, (batch_size, num_points))
source_ids = np.full([batch_size], '012346')
metric.Update(
py_utils.NestedMap({
'visualization_labels': visualization_labels,
'predicted_bboxes': predicted_bboxes,
'visualization_weights': visualization_weights,
'labels': labels,
'gt_bboxes_2d': gt_bboxes_2d,
'gt_bboxes_2d_weights': gt_bboxes_2d_weights,
'points_xyz': points_xyz,
'points_padding': points_padding,
'difficulties': difficulties,
'source_ids': source_ids,
}))
_ = metric.Summary('test')
def CreateDecoderMetrics(self):
"""Decoder metrics for KITTI."""
p = self.params
kitti_metric_p = p.ap_metric.Copy().Set(
cls=kitti_ap_metric.KITTIAPMetrics)
apm = kitti_metric_p.Instantiate()
class_names = apm.metadata.ClassNames()
# Convert the list of class names to a dictionary mapping class_id -> name.
class_id_to_name = dict(enumerate(class_names))
top_down_transform = transform_util.MakeCarToImageTransform(
pixels_per_meter=32.,
image_ref_x=512.,
image_ref_y=1408.,
flip_axes=True)
decoder_metrics = py_utils.NestedMap({
'top_down_visualization':
(detection_3d_metrics.TopDownVisualizationMetric(
top_down_transform,
image_height=1536,
image_width=1024,
class_id_to_name=class_id_to_name)),
'num_samples_in_batch':
metrics.AverageMetric(),
'kitti_AP_v2':
apm,
})
decoder_metrics.mesh = detection_3d_metrics.WorldViewer()
if p.summarize_boxes_on_image:
decoder_metrics.camera_visualization = (
detection_3d_metrics.CameraVisualization(
bbox_score_threshold=p.
visualization_classification_threshold))
return decoder_metrics
