def __init__(self,
output_shape,
num_class=2,
num_input_features=4,
vfe_class_name="VoxelFeatureExtractor",
vfe_num_filters=[32, 128],
with_distance=False,
middle_class_name="SparseMiddleExtractor",
middle_num_input_features=-1,
middle_num_filters_d1=[64],
middle_num_filters_d2=[64, 64],
rpn_class_name="RPN",
rpn_num_input_features=-1,
rpn_layer_nums=[3, 5, 5],
rpn_layer_strides=[2, 2, 2],
rpn_num_filters=[128, 128, 256],
rpn_upsample_strides=[1, 2, 4],
rpn_num_upsample_filters=[256, 256, 256],
use_norm=True,
use_groupnorm=False,
num_groups=32,
use_direction_classifier=True,
use_sigmoid_score=False,
encode_background_as_zeros=True,
use_rotate_nms=True,
multiclass_nms=False,
nms_score_thresholds=None,
nms_pre_max_sizes=None,
nms_post_max_sizes=None,
nms_iou_thresholds=None,
target_assigner=None,
cls_loss_weight=1.0,
loc_loss_weight=1.0,
pos_cls_weight=1.0,
neg_cls_weight=1.0,
direction_loss_weight=1.0,
loss_norm_type=LossNormType.NormByNumPositives,
encode_rad_error_by_sin=False,
loc_loss_ftor=None,
cls_loss_ftor=None,
measure_time=False,
voxel_generator=None,
post_center_range=None,
dir_offset=0.0,
sin_error_factor=1.0,
nms_class_agnostic=False,
num_direction_bins=2,
direction_limit_offset=0,
name='voxelnet'):
super().__init__()
self.name = name
self._sin_error_factor = sin_error_factor
self._num_class = num_class
self._use_rotate_nms = use_rotate_nms
self._multiclass_nms = multiclass_nms
self._nms_score_thresholds = nms_score_thresholds
self._nms_pre_max_sizes = nms_pre_max_sizes
self._nms_post_max_sizes = nms_post_max_sizes
self._nms_iou_thresholds = nms_iou_thresholds
self._use_sigmoid_score = use_sigmoid_score
self._encode_background_as_zeros = encode_background_as_zeros
self._use_direction_classifier = use_direction_classifier
self._num_input_features = num_input_features
self._box_coder = target_assigner.box_coder
self.target_assigner = target_assigner
self.voxel_generator = voxel_generator
self._pos_cls_weight = pos_cls_weight
self._neg_cls_weight = neg_cls_weight
self._encode_rad_error_by_sin = encode_rad_error_by_sin
self._loss_norm_type = loss_norm_type
self._dir_loss_ftor = WeightedSoftmaxClassificationLoss()
self._diff_loc_loss_ftor = WeightedSmoothL1LocalizationLoss()
self._dir_offset = dir_offset
self._loc_loss_ftor = loc_loss_ftor
self._cls_loss_ftor = cls_loss_ftor
self._direction_loss_weight = direction_loss_weight
self._cls_loss_weight = cls_loss_weight
self._loc_loss_weight = loc_loss_weight
self._post_center_range = post_center_range or []
self.measure_time = measure_time
self._nms_class_agnostic = nms_class_agnostic
self._num_direction_bins = num_direction_bins
self._dir_limit_offset = direction_limit_offset
self.voxel_feature_extractor = voxel_encoder.get_vfe_class(
vfe_class_name)(
num_input_features,
use_norm,
num_filters=vfe_num_filters,
with_distance=with_distance,
voxel_size=self.voxel_generator.voxel_size,
pc_range=self.voxel_generator.point_cloud_range,
)
self.middle_feature_extractor = middle.get_middle_class(
middle_class_name)(output_shape,
use_norm,
num_input_features=middle_num_input_features,
num_filters_down1=middle_num_filters_d1,
num_filters_down2=middle_num_filters_d2)
self.rpn = rpn.get_rpn_class(rpn_class_name)(
use_norm=True,
num_class=num_class,
layer_nums=rpn_layer_nums,
layer_strides=rpn_layer_strides,
num_filters=rpn_num_filters,
upsample_strides=rpn_upsample_strides,
num_upsample_filters=rpn_num_upsample_filters,
num_input_features=rpn_num_input_features,
num_anchor_per_loc=target_assigner.num_anchors_per_location,
encode_background_as_zeros=encode_background_as_zeros,
use_direction_classifier=use_direction_classifier,
use_groupnorm=use_groupnorm,
num_groups=num_groups,
box_code_size=target_assigner.box_coder.code_size,
num_direction_bins=self._num_direction_bins)
self.rpn_acc = metrics.Accuracy(
dim=-1, encode_background_as_zeros=encode_background_as_zeros)
self.rpn_precision = metrics.Precision(dim=-1)
self.rpn_recall = metrics.Recall(dim=-1)
self.rpn_metrics = metrics.PrecisionRecall(
dim=-1,
thresholds=[0.1, 0.3, 0.5, 0.7, 0.8, 0.9, 0.95],
use_sigmoid_score=use_sigmoid_score,
encode_background_as_zeros=encode_background_as_zeros)
self.rpn_cls_loss = metrics.Scalar()
self.rpn_loc_loss = metrics.Scalar()
self.rpn_total_loss = metrics.Scalar()
self.register_buffer("global_step", torch.LongTensor(1).zero_())
self._time_dict = {}
self._time_total_dict = {}
self._time_count_dict = {}
def __init__(self,
output_shape,
num_class=2,
num_input_features=4,
vfe_class_name="VoxelFeatureExtractor",
vfe_num_filters=[32, 128],
with_distance=False,
middle_class_name="SparseMiddleExtractor",
middle_num_input_features=-1,
middle_num_filters_d1=[64],
middle_num_filters_d2=[64, 64],
rpn_class_name="RPN",
rpn_num_input_features=-1,
rpn_layer_nums=[3, 5, 5],
rpn_layer_strides=[2, 2, 2],
rpn_num_filters=[128, 128, 256],
rpn_upsample_strides=[1, 2, 4],
rpn_num_upsample_filters=[256, 256, 256],
use_norm=True,
use_groupnorm=False,
num_groups=32,
use_direction_classifier=True,
use_sigmoid_score=False,
encode_background_as_zeros=True,
use_rotate_nms=True,
multiclass_nms=False,
nms_score_threshold=0.5,
nms_pre_max_size=1000,
nms_post_max_size=20,
nms_iou_threshold=0.1,
target_assigner=None,
cls_loss_weight=1.0,
loc_loss_weight=1.0,
pos_cls_weight=1.0,
neg_cls_weight=1.0,
direction_loss_weight=1.0,
loss_norm_type=LossNormType.NormByNumPositives,
encode_rad_error_by_sin=False,
loc_loss_ftor=None,
cls_loss_ftor=None,
measure_time=False,
voxel_generator=None,
post_center_range=None,
name='voxelnet'):
super().__init__()
self.name = name
self._num_class = num_class
self._use_rotate_nms = use_rotate_nms
self._multiclass_nms = multiclass_nms
self._nms_score_threshold = nms_score_threshold
self._nms_pre_max_size = nms_pre_max_size
self._nms_post_max_size = nms_post_max_size
self._nms_iou_threshold = nms_iou_threshold
self._use_sigmoid_score = use_sigmoid_score
self._encode_background_as_zeros = encode_background_as_zeros
self._use_direction_classifier = use_direction_classifier
self._num_input_features = num_input_features
self._box_coder = target_assigner.box_coder
self.target_assigner = target_assigner
self.voxel_generator = voxel_generator
self._pos_cls_weight = pos_cls_weight
self._neg_cls_weight = neg_cls_weight
self._encode_rad_error_by_sin = encode_rad_error_by_sin
self._loss_norm_type = loss_norm_type
self._dir_loss_ftor = WeightedSoftmaxClassificationLoss()
self._diff_loc_loss_ftor = WeightedSmoothL1LocalizationLoss()
self._loc_loss_ftor = loc_loss_ftor
self._cls_loss_ftor = cls_loss_ftor
self._direction_loss_weight = direction_loss_weight
self._cls_loss_weight = cls_loss_weight
self._loc_loss_weight = loc_loss_weight
self._post_center_range = post_center_range or []
self.measure_time = measure_time
vfe_class_dict = {
"VoxelFeatureExtractor": voxel_encoder.VoxelFeatureExtractor,
"VoxelFeatureExtractorV2": voxel_encoder.VoxelFeatureExtractorV2,
"VoxelFeatureExtractorV3": voxel_encoder.VoxelFeatureExtractorV3,
"SimpleVoxel": voxel_encoder.SimpleVoxel,
"PillarFeatureNet": pointpillars.PillarFeatureNet,
}
vfe_class = vfe_class_dict[vfe_class_name]
self.voxel_feature_extractor = vfe_class(
num_input_features,
use_norm,
num_filters=vfe_num_filters,
with_distance=with_distance,
voxel_size=self.voxel_generator.voxel_size,
pc_range=self.voxel_generator.point_cloud_range,
)
mid_class_dict = {
"SparseMiddleExtractor": middle.SparseMiddleExtractor,
"SpMiddleD4HD": middle.SpMiddleD4HD,
"SpMiddleD8HD": middle.SpMiddleD8HD,
"SpMiddleFHD": middle.SpMiddleFHD,
"SpMiddleFHDV2": middle.SpMiddleFHDV2,
"SpMiddleFHDLarge": middle.SpMiddleFHDLarge,
"SpMiddleResNetFHD": middle.SpMiddleResNetFHD,
"SpMiddleD4HDLite": middle.SpMiddleD4HDLite,
"SpMiddleFHDLite": middle.SpMiddleFHDLite,
"SpMiddle2K": middle.SpMiddle2K,
"SpMiddleFHDPeople": middle.SpMiddleFHDPeople,
"SpMiddle2KPeople": middle.SpMiddle2KPeople,
"SpMiddleHDLite": middle.SpMiddleHDLite,
"PointPillarsScatter": pointpillars.PointPillarsScatter,
}
mid_class = mid_class_dict[middle_class_name]
self.middle_feature_extractor = mid_class(
output_shape,
use_norm,
num_input_features=middle_num_input_features,
num_filters_down1=middle_num_filters_d1,
num_filters_down2=middle_num_filters_d2)
rpn_class_dict = {
"RPN": rpn.RPN,
"RPNV2": rpn.RPNV2,
"ResNetRPN": rpn.ResNetRPN,
}
rpn_class = rpn_class_dict[rpn_class_name]
self.rpn = rpn_class(
use_norm=True,
num_class=num_class,
layer_nums=rpn_layer_nums,
layer_strides=rpn_layer_strides,
num_filters=rpn_num_filters,
upsample_strides=rpn_upsample_strides,
num_upsample_filters=rpn_num_upsample_filters,
num_input_features=rpn_num_input_features,
num_anchor_per_loc=target_assigner.num_anchors_per_location,
encode_background_as_zeros=encode_background_as_zeros,
use_direction_classifier=use_direction_classifier,
use_groupnorm=use_groupnorm,
num_groups=num_groups,
box_code_size=target_assigner.box_coder.code_size)
self.rpn_acc = metrics.Accuracy(
dim=-1, encode_background_as_zeros=encode_background_as_zeros)
self.rpn_precision = metrics.Precision(dim=-1)
self.rpn_recall = metrics.Recall(dim=-1)
self.rpn_metrics = metrics.PrecisionRecall(
dim=-1,
thresholds=[0.1, 0.3, 0.5, 0.7, 0.8, 0.9, 0.95],
use_sigmoid_score=use_sigmoid_score,
encode_background_as_zeros=encode_background_as_zeros)
self.rpn_cls_loss = metrics.Scalar()
self.rpn_loc_loss = metrics.Scalar()
self.rpn_total_loss = metrics.Scalar()
self.register_buffer("global_step", torch.LongTensor(1).zero_())
self._time_dict = {}
self._time_total_dict = {}
self._time_count_dict = {}
def __init__(self,
output_shape,
num_class=2,
num_input_features=4,
vfe_class_name="VoxelFeatureExtractor",
vfe_num_filters=[32, 128],
with_distance=False,
middle_class_name="SparseMiddleExtractor",
middle_num_filters_d1=[64],
middle_num_filters_d2=[64, 64],
rpn_class_name="RPN",
rpn_layer_nums=[3, 5, 5],
rpn_layer_strides=[2, 2, 2],
rpn_num_filters=[128, 128, 256],
rpn_upsample_strides=[1, 2, 4],
rpn_num_upsample_filters=[256, 256, 256],
use_norm=True,
use_groupnorm=False,
num_groups=32,
use_sparse_rpn=False,
use_direction_classifier=True,
use_sigmoid_score=False,
encode_background_as_zeros=True,
use_rotate_nms=True,
multiclass_nms=False,
nms_score_threshold=0.5,
nms_pre_max_size=1000,
nms_post_max_size=20,
nms_iou_threshold=0.1,
target_assigner=None,
use_bev=False,
lidar_only=False,
cls_loss_weight=1.0,
loc_loss_weight=1.0,
pos_cls_weight=1.0,
neg_cls_weight=1.0,
direction_loss_weight=1.0,
loss_norm_type=LossNormType.NormByNumPositives,
encode_rad_error_by_sin=False,
loc_loss_ftor=None,
cls_loss_ftor=None,
name='voxelnet'):
super().__init__()
self.name = name
self._num_class = num_class
self._use_rotate_nms = use_rotate_nms
self._multiclass_nms = multiclass_nms
self._nms_score_threshold = nms_score_threshold
self._nms_pre_max_size = nms_pre_max_size
self._nms_post_max_size = nms_post_max_size
self._nms_iou_threshold = nms_iou_threshold
self._use_sigmoid_score = use_sigmoid_score
self._encode_background_as_zeros = encode_background_as_zeros
self._use_sparse_rpn = use_sparse_rpn
self._use_direction_classifier = use_direction_classifier
self._use_bev = use_bev
self._total_forward_time = 0.0
self._total_postprocess_time = 0.0
self._total_inference_count = 0
self._num_input_features = num_input_features
self._box_coder = target_assigner.box_coder
self._lidar_only = lidar_only
self.target_assigner = target_assigner
self._pos_cls_weight = pos_cls_weight
self._neg_cls_weight = neg_cls_weight
self._encode_rad_error_by_sin = encode_rad_error_by_sin
self._loss_norm_type = loss_norm_type
self._dir_loss_ftor = WeightedSoftmaxClassificationLoss()
self._loc_loss_ftor = loc_loss_ftor
self._cls_loss_ftor = cls_loss_ftor
self._direction_loss_weight = direction_loss_weight
self._cls_loss_weight = cls_loss_weight
self._loc_loss_weight = loc_loss_weight
vfe_class_dict = {
"VoxelFeatureExtractor": VoxelFeatureExtractor,
"VoxelFeatureExtractorV2": VoxelFeatureExtractorV2,
}
vfe_class = vfe_class_dict[vfe_class_name]
self.voxel_feature_extractor = vfe_class(num_input_features,
use_norm,
num_filters=vfe_num_filters,
with_distance=with_distance)
mid_class_dict = {
"MiddleExtractor": MiddleExtractor,
"SparseMiddleExtractor": SparseMiddleExtractor,
}
mid_class = mid_class_dict[middle_class_name]
self.middle_feature_extractor = mid_class(
output_shape,
use_norm,
num_input_features=vfe_num_filters[-1],
num_filters_down1=middle_num_filters_d1,
num_filters_down2=middle_num_filters_d2)
if len(middle_num_filters_d2) == 0:
if len(middle_num_filters_d1) == 0:
num_rpn_input_filters = vfe_num_filters[-1]
else:
num_rpn_input_filters = middle_num_filters_d1[-1]
else:
num_rpn_input_filters = middle_num_filters_d2[-1]
rpn_class_dict = {
"RPN": RPN,
}
rpn_class = rpn_class_dict[rpn_class_name]
self.rpn = rpn_class(
use_norm=True,
num_class=num_class,
layer_nums=rpn_layer_nums,
layer_strides=rpn_layer_strides,
num_filters=rpn_num_filters,
upsample_strides=rpn_upsample_strides,
num_upsample_filters=rpn_num_upsample_filters,
num_input_filters=num_rpn_input_filters * 2,
num_anchor_per_loc=target_assigner.num_anchors_per_location,
encode_background_as_zeros=encode_background_as_zeros,
use_direction_classifier=use_direction_classifier,
use_bev=use_bev,
use_groupnorm=use_groupnorm,
num_groups=num_groups,
box_code_size=target_assigner.box_coder.code_size)
self.rpn_acc = metrics.Accuracy(
dim=-1, encode_background_as_zeros=encode_background_as_zeros)
self.rpn_precision = metrics.Precision(dim=-1)
self.rpn_recall = metrics.Recall(dim=-1)
self.rpn_metrics = metrics.PrecisionRecall(
dim=-1,
thresholds=[0.1, 0.3, 0.5, 0.7, 0.8, 0.9, 0.95],
use_sigmoid_score=use_sigmoid_score,
encode_background_as_zeros=encode_background_as_zeros)
self.rpn_cls_loss = metrics.Scalar()
self.rpn_loc_loss = metrics.Scalar()
self.rpn_total_loss = metrics.Scalar()
self.register_buffer("global_step", torch.LongTensor(1).zero_())
def __init__(
self,
output_shape,
num_class=2,
num_input_features=4,
vfe_class_name="VoxelFeatureExtractor",
vfe_num_filters=[32, 128],
with_distance=False,
middle_class_name="SparseMiddleExtractor",
middle_num_input_features=-1,
middle_num_filters_d1=[64],
middle_num_filters_d2=[64, 64],
rpn_class_name="RPN",
rpn_num_input_features=-1,
rpn_layer_nums=[3, 5, 5],
rpn_layer_strides=[2, 2, 2],
rpn_num_filters=[128, 128, 256],
rpn_upsample_strides=[1, 2, 4],
rpn_num_upsample_filters=[256, 256, 256],
use_norm=True,
use_groupnorm=False,
num_groups=32,
use_sparse_rpn=False,
use_voxel_classifier=False,
use_direction_classifier=True,
use_sigmoid_score=False,
encode_background_as_zeros=True,
use_rotate_nms=True,
multiclass_nms=False,
nms_score_threshold=0.5,
nms_pre_max_size=1000,
nms_post_max_size=20,
nms_iou_threshold=0.1,
target_assigner=None,
use_bev=False,
use_rc_net=False,
lidar_only=False,
cls_loss_weight=1.0,
loc_loss_weight=1.0,
pos_cls_weight=1.0,
neg_cls_weight=1.0,
direction_loss_weight=1.0,
loss_norm_type=LossNormType.NormByNumPositives,
encode_rad_error_by_sin=False,
loc_loss_ftor=None,
cls_loss_ftor=None,
measure_time=False,
name='voxelnet',
use_iou_branch=False,
iou_dict=None,
iou_loss_weight=1.0,
iou_loss_ftor=None,
use_iou_param_partaa=False,
):
super().__init__()
self.name = name
self._num_class = num_class
self._use_rotate_nms = use_rotate_nms
self._multiclass_nms = multiclass_nms
self._nms_score_threshold = nms_score_threshold
self._nms_pre_max_size = nms_pre_max_size
self._nms_post_max_size = nms_post_max_size
self._nms_iou_threshold = nms_iou_threshold
self._use_sigmoid_score = use_sigmoid_score
self._encode_background_as_zeros = encode_background_as_zeros
self._use_sparse_rpn = use_sparse_rpn
self._use_direction_classifier = use_direction_classifier
self._use_bev = use_bev
self._num_input_features = num_input_features
self._box_coder = target_assigner.box_coder
self._lidar_only = lidar_only
self.target_assigner = target_assigner
self._pos_cls_weight = pos_cls_weight
self._neg_cls_weight = neg_cls_weight
self._encode_rad_error_by_sin = encode_rad_error_by_sin
self._loss_norm_type = loss_norm_type
self._dir_loss_ftor = WeightedSoftmaxClassificationLoss()
self._loc_loss_ftor = loc_loss_ftor
self._cls_loss_ftor = cls_loss_ftor
self._direction_loss_weight = direction_loss_weight
self._cls_loss_weight = cls_loss_weight
self._loc_loss_weight = loc_loss_weight
self.measure_time = measure_time
vfe_class_dict = {
"VoxelFeatureExtractor": voxel_encoder.VoxelFeatureExtractor,
"VoxelFeatureExtractorV2": voxel_encoder.VoxelFeatureExtractorV2,
"VoxelFeatureExtractorV3": voxel_encoder.VoxelFeatureExtractorV3,
"SimpleVoxel": voxel_encoder.SimpleVoxel
}
vfe_class = vfe_class_dict[vfe_class_name]
self.voxel_feature_extractor = vfe_class(num_input_features,
use_norm,
num_filters=vfe_num_filters,
with_distance=with_distance)
if len(middle_num_filters_d2) == 0:
if len(middle_num_filters_d1) == 0:
num_rpn_input_filters = vfe_num_filters[-1]
else:
num_rpn_input_filters = middle_num_filters_d1[-1]
else:
num_rpn_input_filters = middle_num_filters_d2[-1]
if use_sparse_rpn: # don't use this. just for fun.
self.sparse_rpn = rpn.SparseRPN(
output_shape,
# num_input_features=vfe_num_filters[-1],
num_filters_down1=middle_num_filters_d1,
num_filters_down2=middle_num_filters_d2,
use_norm=True,
num_class=num_class,
layer_nums=rpn_layer_nums,
layer_strides=rpn_layer_strides,
num_filters=rpn_num_filters,
upsample_strides=rpn_upsample_strides,
num_upsample_filters=rpn_num_upsample_filters,
num_input_features=num_rpn_input_filters * 2,
num_anchor_per_loc=target_assigner.num_anchors_per_location,
encode_background_as_zeros=encode_background_as_zeros,
use_direction_classifier=use_direction_classifier,
use_bev=use_bev,
use_groupnorm=use_groupnorm,
num_groups=num_groups,
box_code_size=target_assigner.box_coder.code_size)
else:
mid_class_dict = {
"SparseMiddleExtractor": middle.SparseMiddleExtractor,
"SpMiddleD4HD": middle.SpMiddleD4HD,
"SpMiddleD8HD": middle.SpMiddleD8HD,
"SpMiddleFHD": middle.SpMiddleFHD,
"SpMiddleFHDV2": middle.SpMiddleFHDV2,
"SpMiddleFHDLarge": middle.SpMiddleFHDLarge,
"SpMiddleResNetFHD": middle.SpMiddleResNetFHD,
"SpMiddleD4HDLite": middle.SpMiddleD4HDLite,
"SpMiddleFHDLite": middle.SpMiddleFHDLite,
"SpMiddle2K": middle.SpMiddle2K,
}
mid_class = mid_class_dict[middle_class_name]
self.middle_feature_extractor = mid_class(
output_shape,
use_norm,
num_input_features=middle_num_input_features,
num_filters_down1=middle_num_filters_d1,
num_filters_down2=middle_num_filters_d2)
rpn_class_dict = {
"RPN": rpn.RPN,
"RPNV2": rpn.RPNV2,
"RPN_FUSION": rpn.RPN_FUSION,
}
self.rpn_class_name = rpn_class_name
rpn_class = rpn_class_dict[self.rpn_class_name]
self.rpn = rpn_class(
use_norm=True,
num_class=num_class,
layer_nums=rpn_layer_nums,
layer_strides=rpn_layer_strides,
num_filters=rpn_num_filters,
upsample_strides=rpn_upsample_strides,
num_upsample_filters=rpn_num_upsample_filters,
num_input_features=rpn_num_input_features,
num_anchor_per_loc=target_assigner.num_anchors_per_location,
encode_background_as_zeros=encode_background_as_zeros,
use_direction_classifier=use_direction_classifier,
use_bev=use_bev,
use_groupnorm=use_groupnorm,
num_groups=num_groups,
box_code_size=target_assigner.box_coder.code_size)
self.rpn_acc = metrics.Accuracy(
dim=-1, encode_background_as_zeros=encode_background_as_zeros)
self.rpn_precision = metrics.Precision(dim=-1)
self.rpn_recall = metrics.Recall(dim=-1)
self.rpn_metrics = metrics.PrecisionRecall(
dim=-1,
thresholds=[0.1, 0.3, 0.5, 0.7, 0.8, 0.9, 0.95],
use_sigmoid_score=use_sigmoid_score,
encode_background_as_zeros=encode_background_as_zeros)
self.rpn_cls_loss = metrics.Scalar()
self.rpn_loc_loss = metrics.Scalar()
self.rpn_total_loss = metrics.Scalar()
self.register_buffer("global_step", torch.LongTensor(1).zero_())
self._time_dict = {}
self._time_total_dict = {}
self._time_count_dict = {}
def __init__(self,
output_shape,
num_class=2,
num_input_features=4,
voxelization_name="BV",
vfe_num_filters=[32, 128],
with_distance=False,
tdbn_name="tDBN_1",
tdbn_filters_d1=[64],
tdbn_filters_d2=[64, 64],
det_net_name="det_net",
det_net_layer_nums=[3, 5, 5],
det_net_layer_strides=[2, 2, 2],
det_net_num_filters=[128, 128, 256],
det_net_upsample_strides=[1, 2, 4],
det_net_num_upsample_filters=[256, 256, 256],
use_norm=True,
use_groupnorm=False,
num_groups=32,
use_direction_classifier=True,
use_sigmoid_score=False,
encode_background_as_zeros=True,
use_rotate_nms=True,
multiclass_nms=False,
nms_score_threshold=0.5,
nms_pre_max_size=1000,
nms_post_max_size=20,
nms_iou_threshold=0.1,
target_assigner=None,
lidar_only=False,
cls_loss_weight=1.0,
loc_loss_weight=1.0,
pos_cls_weight=1.0,
neg_cls_weight=1.0,
direction_loss_weight=1.0,
loss_norm_type=LossNormType.NormByNumPositives,
encode_rad_error_by_sin=False,
loc_loss_ftor=None,
cls_loss_ftor=None,
name='model_net'):
super().__init__()
self.name = name
self._num_class = num_class
self._use_rotate_nms = use_rotate_nms
self._multiclass_nms = multiclass_nms
self._nms_score_threshold = nms_score_threshold
self._nms_pre_max_size = nms_pre_max_size
self._nms_post_max_size = nms_post_max_size
self._nms_iou_threshold = nms_iou_threshold
self._use_sigmoid_score = use_sigmoid_score
self._encode_background_as_zeros = encode_background_as_zeros
self._use_direction_classifier = use_direction_classifier
self._total_forward_time = 0.0
self._total_postprocess_time = 0.0
self._total_inference_count = 0
self._num_input_features = num_input_features
self._box_coder = target_assigner.box_coder
self._lidar_only = lidar_only
self.target_assigner = target_assigner
self._pos_cls_weight = pos_cls_weight
self._neg_cls_weight = neg_cls_weight
self._encode_rad_error_by_sin = encode_rad_error_by_sin
self._loss_norm_type = loss_norm_type
self._dir_loss_ftor = WeightedSoftmaxClassificationLoss()
self._loc_loss_ftor = loc_loss_ftor
self._cls_loss_ftor = cls_loss_ftor
self._direction_loss_weight = direction_loss_weight
self._cls_loss_weight = cls_loss_weight
self._loc_loss_weight = loc_loss_weight
voxelization_class_dict = {
"VEF": voxelization.VoxelFeatureExtractor,
"BV": voxelization.BinaryVoxel,
}
voxelization_class = voxelization_class_dict[voxelization_name]
self.voxel_feature_extractor = voxelization_class(
num_input_features,
use_norm,
num_filters=vfe_num_filters,
with_distance=with_distance)
tdbn_class_dict = {
"tDBN_1": tDBN.tDBN_1,
"tDBN_2": tDBN.tDBN_2,
"tDBN_bv_1": tDBN.tDBN_bv_1,
"tDBN_bv_2": tDBN.tDBN_bv_2,
}
tdbn_class = tdbn_class_dict[tdbn_name]
self.tdbn_feature_extractor = tdbn_class(
output_shape,
use_norm,
num_filters_down1=tdbn_filters_d1,
num_filters_down2=tdbn_filters_d2)
det_net_class_dict = {
"det_net": det_net.det_net,
"det_net_2": det_net.det_net_2,
}
det_net_class = det_net_class_dict[det_net_name]
self.det_net = det_net_class(
use_norm=True,
num_class=num_class,
layer_nums=det_net_layer_nums,
layer_strides=det_net_layer_strides,
num_filters=det_net_num_filters,
upsample_strides=det_net_upsample_strides,
num_upsample_filters=det_net_num_upsample_filters,
num_anchor_per_loc=target_assigner.num_anchors_per_location,
encode_background_as_zeros=encode_background_as_zeros,
use_direction_classifier=use_direction_classifier,
use_groupnorm=use_groupnorm,
num_groups=num_groups,
box_code_size=target_assigner.box_coder.code_size)
self.det_net_acc = metrics.Accuracy(
dim=-1, encode_background_as_zeros=encode_background_as_zeros)
self.det_net_precision = metrics.Precision(dim=-1)
self.det_net_recall = metrics.Recall(dim=-1)
self.det_net_metrics = metrics.PrecisionRecall(
dim=-1,
thresholds=[0.1, 0.3, 0.5, 0.7, 0.8, 0.9, 0.95],
use_sigmoid_score=use_sigmoid_score,
encode_background_as_zeros=encode_background_as_zeros)
self.det_net_cls_loss = metrics.Scalar()
self.det_net_loc_loss = metrics.Scalar()
self.det_net_total_loss = metrics.Scalar()
self.register_buffer("global_step", torch.LongTensor(1).zero_())
def __init__(self,
output_shape,
num_class=2,
num_input_features=4,
vfe_class_name="VoxelFeatureExtractor",
vfe_num_filters=[32, 128],
with_distance=False,
middle_class_name="SparseMiddleExtractor",
middle_num_input_features=-1,
middle_num_filters_d1=[64],
middle_num_filters_d2=[64, 64],
rpn_class_name="RPN",
rpn_num_input_features=-1,
rpn_layer_nums=[3, 5, 5],
rpn_layer_strides=[2, 2, 2],
rpn_num_filters=[128, 128, 256],
rpn_upsample_strides=[1, 2, 4],
rpn_num_upsample_filters=[256, 256, 256],
use_norm=True,
use_groupnorm=False,
num_groups=32,
use_direction_classifier=True,
use_sigmoid_score=False,
encode_background_as_zeros=True,
use_rotate_nms=True,
multiclass_nms=False,
nms_score_thresholds=None,
nms_pre_max_sizes=None,
nms_post_max_sizes=None,
nms_iou_thresholds=None,
target_assigner=None,
cls_loss_weight=1.0,
loc_loss_weight=1.0,
pos_cls_weight=1.0,
neg_cls_weight=1.0,
direction_loss_weight=1.0,
loss_norm_type=LossNormType.NormByNumPositives,
encode_rad_error_by_sin=False,
loc_loss_ftor=None,
cls_loss_ftor=None,
measure_time=False,
voxel_generator=None,
post_center_range=None,
dir_offset=0.0,
sin_error_factor=1.0,
nms_class_agnostic=False,
num_direction_bins=2,
direction_limit_offset=0,
name='voxelnet'):
super().__init__()
self.name = name
self._sin_error_factor = sin_error_factor
self._num_class = num_class
self._use_rotate_nms = use_rotate_nms
self._multiclass_nms = multiclass_nms
self._nms_score_thresholds = nms_score_thresholds
self._nms_pre_max_sizes = nms_pre_max_sizes
self._nms_post_max_sizes = nms_post_max_sizes
self._nms_iou_thresholds = nms_iou_thresholds
self._use_sigmoid_score = use_sigmoid_score
self._encode_background_as_zeros = encode_background_as_zeros
self._use_direction_classifier = use_direction_classifier
self._num_input_features = num_input_features
self._box_coder = target_assigner.box_coder
self.target_assigner = target_assigner
self.voxel_generator = voxel_generator
self._pos_cls_weight = pos_cls_weight
self._neg_cls_weight = neg_cls_weight
self._encode_rad_error_by_sin = encode_rad_error_by_sin
self._loss_norm_type = loss_norm_type
self._dir_loss_ftor = WeightedSoftmaxClassificationLoss()
self._diff_loc_loss_ftor = WeightedSmoothL1LocalizationLoss()
self._dir_offset = dir_offset
self._loc_loss_ftor = loc_loss_ftor
self._cls_loss_ftor = cls_loss_ftor
self._direction_loss_weight = direction_loss_weight
self._cls_loss_weight = cls_loss_weight
self._loc_loss_weight = loc_loss_weight
self._post_center_range = post_center_range or []
self.measure_time = measure_time
self._nms_class_agnostic = nms_class_agnostic
self._num_direction_bins = num_direction_bins
self._dir_limit_offset = direction_limit_offset
self.voxel_feature_extractor = voxel_encoder.get_vfe_class(vfe_class_name)(
num_input_features,
use_norm,
num_filters=vfe_num_filters,
with_distance=with_distance,
voxel_size=self.voxel_generator.voxel_size,
pc_range=self.voxel_generator.point_cloud_range,
)
self.middle_feature_extractor = middle.get_middle_class(middle_class_name)(
output_shape,
use_norm,
num_input_features=middle_num_input_features,
num_filters_down1=middle_num_filters_d1,
num_filters_down2=middle_num_filters_d2)
self._rpn_layer_nums = rpn_layer_nums
self.rpn = rpn.get_rpn_class(rpn_class_name)(
use_norm=True,
num_class=num_class,
layer_nums=rpn_layer_nums,
layer_strides=rpn_layer_strides,
num_filters=rpn_num_filters,
upsample_strides=rpn_upsample_strides,
num_upsample_filters=rpn_num_upsample_filters,
num_input_features=rpn_num_input_features,
num_anchor_per_loc=target_assigner.num_anchors_per_location,
encode_background_as_zeros=encode_background_as_zeros,
use_direction_classifier=use_direction_classifier,
use_groupnorm=use_groupnorm,
num_groups=num_groups,
box_code_size=target_assigner.box_coder.code_size,
num_direction_bins=self._num_direction_bins)
self.rpn_acc = metrics.Accuracy(
dim=-1, encode_background_as_zeros=encode_background_as_zeros)
self.rpn_precision = metrics.Precision(dim=-1)
self.rpn_recall = metrics.Recall(dim=-1)
self.rpn_metrics = metrics.PrecisionRecall(
dim=-1,
thresholds=[0.1, 0.3, 0.5, 0.7, 0.8, 0.9, 0.95],
use_sigmoid_score=use_sigmoid_score,
encode_background_as_zeros=encode_background_as_zeros)
self.rpn_cls_loss = metrics.Scalar()
self.rpn_loc_loss = metrics.Scalar()
self.rpn_total_loss = metrics.Scalar()
self.register_buffer("global_step", torch.LongTensor(1).zero_())
self._time_dict = {
'PFE': [],
#'PillarGen': [],
#'PillarPrep': [],
#'PillarFeatureNet': [],
#'PillarScatter': [],
'RPN-stage-1': [],
'RPN-stage-2': [],
'RPN-stage-3': [],
'RPN-finalize': [],
'Predict': [],
'Pre-stage-1': [],
'Post-stage-1': [],
'End-to-end': [],}
self._cuda_event_dict = copy.deepcopy(self._time_dict)
self._det_num = 1
self._dump_scores = False
if self._dump_scores:
for i in range(1, len(rpn_layer_nums) + 1):
mypath = os.getenv('HOME') + "/scores_" + str(i)
if not os.path.exists(mypath):
os.makedirs(mypath)
#self._cuda_streams = []
#for i in range(4): # We are assuming 4 slices
# self._cuda_streams.append(torch.cuda.Stream())
self._num_class_with_bg = self._num_class
if not self._encode_background_as_zeros:
self._num_class_with_bg = self._num_class + 1
def __init__(self,
output_shape,
num_class=2,
num_input_features=4,
vfe_class_name="VoxelFeatureExtractor",
vfe_num_filters=[32, 128],
with_distance=False,
middle_class_name="MiddleExtractor",
middle_num_filters_d1=[64],
middle_num_filters_d2=[64, 64],
rpn_class_name="RPN",
rpn_layer_nums=[3, 5, 5],
rpn_layer_strides=[2, 2, 2],
rpn_num_filters=[128, 128, 256],
rpn_upsample_strides=[1, 2, 4],
rpn_num_upsample_filters=[256, 256, 256],
use_norm=True,
use_groupnorm=False,
num_groups=32,
use_sparse_rpn=False,
use_direction_classifier=True,
use_sigmoid_score=False,
encode_background_as_zeros=True,
use_rotate_nms=True,
multiclass_nms=False,
nms_score_threshold=0.5,
nms_pre_max_size=1000,
nms_post_max_size=20,
nms_iou_threshold=0.1,
target_assigner=None,
use_bev=False,
lidar_only=False,
cls_loss_weight=1.0,
loc_loss_weight=1.0,
pos_cls_weight=1.0,
neg_cls_weight=1.0,
direction_loss_weight=1.0,
loss_norm_type=LossNormType.NormByNumPositives,
encode_rad_error_by_sin=False,
loc_loss_ftor=None,
cls_loss_ftor=None,
voxel_size=(0.2, 0.2, 4),
pc_range=(0, -40, -3, 70.4, 40, 1),
name='voxelnet',
K=100,
hm_weight=1,
dim_weight=1,
rot_weight=1,
off_weight=1,
centernet_layers=50):
super().__init__()
self.name = name
self._num_class = num_class
self._use_rotate_nms = use_rotate_nms
self._multiclass_nms = multiclass_nms
self._nms_score_threshold = nms_score_threshold
self._nms_pre_max_size = nms_pre_max_size
self._nms_post_max_size = nms_post_max_size
self._nms_iou_threshold = nms_iou_threshold
self._use_sigmoid_score = use_sigmoid_score
self._encode_background_as_zeros = encode_background_as_zeros
self._use_sparse_rpn = use_sparse_rpn
self._use_direction_classifier = use_direction_classifier
self._use_bev = use_bev
self._total_forward_time = 0.0
self._total_postprocess_time = 0.0
self._total_inference_count = 0
self._num_input_features = num_input_features
self._box_coder = target_assigner.box_coder
self._lidar_only = lidar_only
self.K = K
self.hm_weight = hm_weight
self.dim_weight = dim_weight
self.rot_weight = rot_weight
self.off_weight = off_weight
self.centernet_layers = centernet_layers
self.pc_range = pc_range
vfe_class_dict = {
"VoxelFeatureExtractor": VoxelFeatureExtractor,
"VoxelFeatureExtractorV2": VoxelFeatureExtractorV2,
"PillarFeatureNet": PillarFeatureNet
}
vfe_class = vfe_class_dict[vfe_class_name]
if vfe_class_name == "PillarFeatureNet":
self.voxel_feature_extractor = vfe_class(
num_input_features,
use_norm,
num_filters=vfe_num_filters,
with_distance=with_distance,
voxel_size=voxel_size,
pc_range=pc_range)
else:
self.voxel_feature_extractor = vfe_class(
num_input_features,
use_norm,
num_filters=vfe_num_filters,
with_distance=with_distance)
print("middle_class_name", middle_class_name)
if middle_class_name == "PointPillarsScatter":
self.middle_feature_extractor = PointPillarsScatter(
output_shape=output_shape,
num_input_features=vfe_num_filters[-1])
else:
mid_class_dict = {
"MiddleExtractor": MiddleExtractor
# "SparseMiddleExtractor": SparseMiddleExtractor,
}
mid_class = mid_class_dict[middle_class_name]
self.middle_feature_extractor = mid_class(
output_shape,
use_norm,
num_input_features=vfe_num_filters[-1],
num_filters_down1=middle_num_filters_d1,
num_filters_down2=middle_num_filters_d2)
#======================= New detection heads ==========================
heads = {'hm': self._num_class, 'rot': 8, 'dim': 3, 'reg': 2}
self.centernet = get_pose_net(num_layers=self.centernet_layers,
heads=heads)
#=======================================================================
self.rpn_acc = metrics.Accuracy(
dim=-1, encode_background_as_zeros=encode_background_as_zeros)
self.rpn_precision = metrics.Precision(dim=-1)
self.rpn_recall = metrics.Recall(dim=-1)
self.rpn_metrics = metrics.PrecisionRecall(
dim=-1,
thresholds=[0.1, 0.3, 0.5, 0.7, 0.8, 0.9, 0.95],
use_sigmoid_score=use_sigmoid_score,
encode_background_as_zeros=encode_background_as_zeros)
self.hm_loss = metrics.Scalar()
self.dim_loss = metrics.Scalar()
self.rot_loss = metrics.Scalar()
self.total_loss = metrics.Scalar()
self.register_buffer("global_step", torch.LongTensor(1).zero_())
def __init__(self, target_assigner, nms_score_thresholds,
nms_iou_thresholds, nms_pre_max_sizes, nms_post_max_sizes,
loc_loss_ftor, cls_loss_ftor, loc_loss_weight,
cls_loss_weight):
super().__init__()
self.name = "pointpillars_loss"
self.measure_time = False
encode_background_as_zeros = True
use_sigmoid_score = True
self._num_class = 4
self._encode_rad_error_by_sin = True
self._encode_background_as_zeros = encode_background_as_zeros
self._sin_error_factor = 1.0
self._num_direction_bins = 2
self._dir_offset = 0
self._dir_limit_offset = 1
self._direction_loss_weight = 0.2
self._use_direction_classifier = True
self.target_assigner = target_assigner
self._box_coder = target_assigner.box_coder
self._pos_cls_weight = 1.0
self._neg_cls_weight = 1.0
self._loss_norm_type = LossNormType.NormByNumPositives
self._loc_loss_ftor = loc_loss_ftor
self._cls_loss_ftor = cls_loss_ftor
self._loc_loss_weight = loc_loss_weight
self._cls_loss_weight = cls_loss_weight
self._dir_loss_ftor = WeightedSoftmaxClassificationLoss()
self._diff_loc_loss_ftor = WeightedSmoothL1LocalizationLoss()
# postprocess
self._post_center_range = [-40, -80, -5, 40, 40, 5]
self._use_sigmoid_score = True
self._use_rotate_nms = False
self._multiclass_nms = False
self._nms_class_agnostic = False
self._nms_score_thresholds = nms_score_thresholds
self._nms_iou_thresholds = nms_iou_thresholds
self._nms_pre_max_sizes = nms_pre_max_sizes
self._nms_post_max_sizes = nms_post_max_sizes
self.rpn_acc = metrics.Accuracy(
dim=-1, encode_background_as_zeros=encode_background_as_zeros)
self.rpn_precision = metrics.Precision(dim=-1)
self.rpn_recall = metrics.Recall(dim=-1)
self.rpn_metrics = metrics.PrecisionRecall(
dim=-1,
thresholds=[0.1, 0.3, 0.5, 0.7, 0.8, 0.9, 0.95],
use_sigmoid_score=use_sigmoid_score,
encode_background_as_zeros=encode_background_as_zeros)
self.rpn_cls_loss = metrics.Scalar()
self.rpn_loc_loss = metrics.Scalar()
self.rpn_total_loss = metrics.Scalar()
self.register_buffer("global_step", torch.LongTensor(1).zero_())
self._time_dict = {}
self._time_total_dict = {}
self._time_count_dict = {}
