def __init__(self,
in_channels,
num_classes=3,
extra_width=0.2,
seg_score_thr=0.3,
init_cfg=None,
loss_seg=dict(
type='FocalLoss',
use_sigmoid=True,
reduction='sum',
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_part=dict(
type='CrossEntropyLoss',
use_sigmoid=True,
loss_weight=1.0)):
super(PointwiseSemanticHead, self).__init__(init_cfg=init_cfg)
self.extra_width = extra_width
self.num_classes = num_classes
self.seg_score_thr = seg_score_thr
self.seg_cls_layer = nn.Linear(in_channels, 1, bias=True)
self.seg_reg_layer = nn.Linear(in_channels, 3, bias=True)
self.loss_seg = build_loss(loss_seg)
self.loss_part = build_loss(loss_part)
def __init__(self,
num_classes,
bbox_coder,
train_cfg=None,
test_cfg=None,
pred_layer_cfg=None,
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
dir_res_loss=None,
size_res_loss=None,
semantic_loss=None):
super(BRBboxHead, self).__init__()
self.num_classes = num_classes
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.dir_res_loss = build_loss(dir_res_loss)
self.size_res_loss = build_loss(size_res_loss)
self.semantic_loss = build_loss(semantic_loss)
self.bbox_coder = build_bbox_coder(bbox_coder)
# Bbox classification and regression
self.conv_pred = BaseConvBboxHead(
**pred_layer_cfg,
num_cls_out_channels=self._get_cls_out_channels(),
num_reg_out_channels=self._get_reg_out_channels())
def __init__(self,
in_channels=[128],
tasks=None,
train_cfg=None,
test_cfg=None,
bbox_coder=None,
common_heads=dict(),
loss_cls=dict(type='GaussianFocalLoss', reduction='mean'),
loss_bbox=dict(type='L1Loss',
reduction='none',
loss_weight=0.25),
separate_head=dict(type='SeparateHead',
init_bias=-2.19,
final_kernel=3),
share_conv_channel=64,
num_heatmap_convs=2,
conv_cfg=dict(type='Conv2d'),
norm_cfg=dict(type='BN2d'),
bias='auto',
norm_bbox=True):
super(CenterHead, self).__init__()
num_classes = [len(t['class_names']) for t in tasks]
self.class_names = [t['class_names'] for t in tasks]
# Feng Xiang code
# code begin
# num_attr = [len(t['attr_names']) for t in tasks]
# self.attr_names = [t['attr_names'] for t in tasks]
# code end
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.in_channels = in_channels
self.num_classes = num_classes
self.norm_bbox = norm_bbox
self.loss_cls = build_loss(loss_cls)
self.loss_bbox = build_loss(loss_bbox)
self.bbox_coder = build_bbox_coder(bbox_coder)
self.num_anchor_per_locs = [n for n in num_classes]
self.fp16_enabled = False
# a shared convolution
self.shared_conv = ConvModule(in_channels,
share_conv_channel,
kernel_size=3,
padding=1,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
bias=bias)
self.task_heads = nn.ModuleList()
for num_cls in num_classes:
heads = copy.deepcopy(common_heads)
heads.update(dict(heatmap=(num_cls, num_heatmap_convs)))
separate_head.update(in_channels=share_conv_channel,
heads=heads,
num_cls=num_cls)
self.task_heads.append(builder.build_head(separate_head))
def __init__(self,
num_classes,
bbox_coder,
train_cfg=None,
test_cfg=None,
vote_module_cfg=None,
vote_aggregation_cfg=None,
pred_layer_cfg=None,
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
objectness_loss=None,
center_loss=None,
center_loss_mse=None,
dir_class_loss=None,
dir_res_loss=None,
size_class_loss=None,
size_res_loss=None,
semantic_loss=None,
iou_loss=None):
super(VoteHead, self).__init__()
self.num_classes = num_classes
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.gt_per_seed = vote_module_cfg['gt_per_seed']
self.num_proposal = vote_aggregation_cfg['num_point']
self.objectness_loss = build_loss(objectness_loss)
self.dir_res_loss = build_loss(dir_res_loss)
self.dir_class_loss = build_loss(dir_class_loss)
self.size_res_loss = build_loss(size_res_loss)
if size_class_loss is not None:
self.size_class_loss = build_loss(size_class_loss)
if semantic_loss is not None:
self.semantic_loss = build_loss(semantic_loss)
if iou_loss is not None:
self.iou_loss = build_loss(iou_loss)
else:
self.iou_loss = None
if center_loss is not None:
self.center_loss = build_loss(center_loss)
if center_loss_mse is not None:
self.center_loss_mse = build_loss(center_loss_mse)
self.bbox_coder = build_bbox_coder(bbox_coder)
self.num_sizes = self.bbox_coder.num_sizes
self.num_dir_bins = self.bbox_coder.num_dir_bins
self.vote_module = VoteModule(**vote_module_cfg)
self.vote_aggregation = build_sa_module(vote_aggregation_cfg)
self.fp16_enabled = False
# Bbox classification and regression
self.conv_pred = BaseConvBboxHead(
**pred_layer_cfg,
num_cls_out_channels=self._get_cls_out_channels(),
num_reg_out_channels=self._get_reg_out_channels())
def __init__(
self,
img_backbone=None,
pts_backbone=None,
num_classes=None,
prelogits_dim=None,
class_weights=None,
pretrained=None,
contrast_criterion=None,
max_pts=1024, # max_pts_per_group
groups=1, # number of groups per sample
lambda_contrast=0.1,
img_fcs=(64, 64, 16),
pts_fcs=(16, 16, 16),
train_cfg=None,
test_cfg=None):
super(SegFusionContra, self).__init__()
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if pts_backbone:
self.pts_backbone = builder.build_backbone(pts_backbone)
self.init_weights(pretrained=pretrained)
self.seg_head = nn.Linear(prelogits_dim, num_classes)
self.class_weights = torch.tensor(class_weights)
if contrast_criterion:
self.contrast_criterion = builder.build_loss(contrast_criterion)
self.max_pts = max_pts
self.groups = groups
self.lambda_contrast = lambda_contrast
self.img_fc = build_mlp(img_fcs)
self.pts_fc = build_mlp(pts_fcs)
def __init__(self,
in_channels,
vote_per_seed=1,
gt_per_seed=3,
conv_channels=(16, 16),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
norm_feats=True,
vote_loss=None):
super().__init__()
self.in_channels = in_channels
self.vote_per_seed = vote_per_seed
self.gt_per_seed = gt_per_seed
self.norm_feats = norm_feats
self.vote_loss = build_loss(vote_loss)
prev_channels = in_channels
vote_conv_list = list()
for k in range(len(conv_channels)):
vote_conv_list.append(
ConvModule(prev_channels,
conv_channels[k],
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
bias=True,
inplace=True))
prev_channels = conv_channels[k]
self.vote_conv = nn.Sequential(*vote_conv_list)
# conv_out predicts coordinate and residual features
out_channel = (3 + in_channels) * self.vote_per_seed
self.conv_out = nn.Conv1d(prev_channels, out_channel, 1)
def __init__(self,
img_backbone=None,
pts_backbone=None,
num_classes=None,
prelogits_dim=None,
class_weights=None,
pretrained=None,
contrast_criterion=None,
max_pts=1024,
lambda_contrast=0.1,
train_cfg=None,
test_cfg=None):
super(SegFusionV2, self).__init__()
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if pts_backbone:
self.pts_backbone = builder.build_backbone(pts_backbone)
self.init_weights(pretrained=pretrained)
self.seg_head = nn.Linear(prelogits_dim, num_classes)
self.class_weights = torch.tensor(class_weights)
if contrast_criterion:
self.contrast_criterion = builder.build_loss(contrast_criterion)
self.max_pts = max_pts
self.lambda_contrast = lambda_contrast
self.g1 = nn.Sequential(nn.Linear(64, 64), nn.ReLU(inplace=True),
nn.Linear(64, 16))
self.g2 = nn.Sequential(nn.Linear(16, 16), nn.ReLU(inplace=True),
nn.Linear(16, 16))
def __init__(self,
pts_voxel_layer=None,
pts_voxel_encoder=None,
pts_middle_encoder=None,
img_backbone=None,
img_seg_head=None,
pts_backbone=None,
pts_neck=None,
pts_bbox_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None,
pts_fc=[],
contrast_criterion=None,
max_pts=4096,
lambda_contrast=0.1):
super(FusionContrastV2, self).__init__()
if img_backbone:
self.img_backbone = builder.build_backbone(img_backbone)
if img_seg_head:
self.img_seg_head = builder.build_head(img_seg_head)
if pts_voxel_layer:
self.pts_voxel_layer = Voxelization(**pts_voxel_layer)
if pts_voxel_encoder:
self.pts_voxel_encoder = builder.build_voxel_encoder(
pts_voxel_encoder)
if pts_middle_encoder:
self.pts_middle_encoder = builder.build_middle_encoder(
pts_middle_encoder)
if pts_backbone:
self.pts_backbone = builder.build_backbone(pts_backbone)
if pts_neck:
self.pts_neck = builder.build_neck(pts_neck)
if pts_bbox_head:
pts_train_cfg = train_cfg.pts if train_cfg else None
pts_bbox_head.update(train_cfg=pts_train_cfg)
pts_test_cfg = test_cfg.pts if test_cfg else None
pts_bbox_head.update(test_cfg=pts_test_cfg)
self.pts_bbox_head = builder.build_head(pts_bbox_head)
if contrast_criterion:
self.contrast_criterion = builder.build_loss(contrast_criterion)
self.max_pts = max_pts
self.lambda_contrast = lambda_contrast
fc_layers = []
for i, (in_c, out_c) in enumerate(zip(pts_fc[:-1], pts_fc[1:])):
fc_layers.append(nn.Linear(in_c, out_c))
if i == len(pts_fc) - 2:
break
fc_layers.append(nn.ReLU(inplace=True))
self.fc_layers = nn.Sequential(*fc_layers)
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.init_weights(pretrained=pretrained)
def __init__(self,
num_classes,
bbox_coder,
in_channels=256,
train_cfg=None,
test_cfg=None,
vote_module_cfg=None,
vote_aggregation_cfg=None,
prop_reasoning_cfg=None,
pred_layer_cfg=None,
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
act_cfg=dict(type='ReLU'),
objectness_loss=None,
center_loss=None,
dir_class_loss=None,
dir_res_loss=None,
size_res_loss=None,
corner_loss=None,
vote_loss=None):
super(SSD3DHead_ProRe, self).__init__(
num_classes,
bbox_coder,
train_cfg=train_cfg,
test_cfg=test_cfg,
vote_module_cfg=vote_module_cfg,
vote_aggregation_cfg=vote_aggregation_cfg,
pred_layer_cfg=pred_layer_cfg,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
objectness_loss=objectness_loss,
center_loss=center_loss,
dir_class_loss=dir_class_loss,
dir_res_loss=dir_res_loss,
size_class_loss=None,
size_res_loss=size_res_loss,
semantic_loss=None)
self.prop_reason = ProRe(**prop_reasoning_cfg)
self.corner_loss = build_loss(corner_loss)
self.vote_loss = build_loss(vote_loss)
self.num_candidates = vote_module_cfg['num_points']
def __init__(self,
in_channels,
vote_per_seed=1,
gt_per_seed=3,
num_points=-1,
conv_channels=(16, 16),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
act_cfg=dict(type='ReLU'),
norm_feats=True,
with_res_feat=True,
vote_xyz_range=None,
vote_loss=None):
super().__init__()
self.in_channels = in_channels
self.vote_per_seed = vote_per_seed
self.gt_per_seed = gt_per_seed
self.num_points = num_points
self.norm_feats = norm_feats
self.with_res_feat = with_res_feat
assert vote_xyz_range is None or is_tuple_of(vote_xyz_range, float)
self.vote_xyz_range = vote_xyz_range
if vote_loss is not None:
self.vote_loss = build_loss(vote_loss)
prev_channels = in_channels
vote_conv_list = list()
for k in range(len(conv_channels)):
vote_conv_list.append(
ConvModule(
prev_channels,
conv_channels[k],
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
bias=True,
inplace=True))
prev_channels = conv_channels[k]
self.vote_conv = nn.Sequential(*vote_conv_list)
# conv_out predicts coordinate and residual features
if with_res_feat:
out_channel = (3 + in_channels) * self.vote_per_seed
else:
out_channel = 3 * self.vote_per_seed
self.conv_out = nn.Conv1d(prev_channels, out_channel, 1)
def __init__(self,
model,
cfg,
batch_processor=None,
optimizer=None,
work_dir=None,
logger=None,
meta=None,
max_iters=None,
max_epochs=None):
super(ContrastRunnerV0,
self).__init__(model, batch_processor, optimizer, work_dir,
logger, meta, max_iters, max_epochs)
self.lambda_contrast = cfg.lambda_contrast
self.max_pts = cfg.max_pts
self.contrast_criterion = build_loss(cfg.contrast_criterion)
def __init__(self,
num_classes,
seg_in_channels,
part_in_channels,
seg_conv_channels=None,
part_conv_channels=None,
merge_conv_channels=None,
down_conv_channels=None,
shared_fc_channels=None,
cls_channels=None,
reg_channels=None,
dropout_ratio=0.1,
roi_feat_size=14,
with_corner_loss=True,
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d', eps=1e-3, momentum=0.01),
loss_bbox=dict(type='SmoothL1Loss',
beta=1.0 / 9.0,
loss_weight=2.0),
loss_cls=dict(type='CrossEntropyLoss',
use_sigmoid=True,
reduction='none',
loss_weight=1.0)):
super(PartA2BboxHead, self).__init__()
self.num_classes = num_classes
self.with_corner_loss = with_corner_loss
self.bbox_coder = build_bbox_coder(bbox_coder)
self.loss_bbox = build_loss(loss_bbox)
self.loss_cls = build_loss(loss_cls)
self.use_sigmoid_cls = loss_cls.get('use_sigmoid', False)
assert down_conv_channels[-1] == shared_fc_channels[0]
# init layers
part_channel_last = part_in_channels
part_conv = []
for i, channel in enumerate(part_conv_channels):
part_conv.append(
make_sparse_convmodule(part_channel_last,
channel,
3,
padding=1,
norm_cfg=norm_cfg,
indice_key=f'rcnn_part{i}',
conv_type='SubMConv3d'))
part_channel_last = channel
self.part_conv = spconv.SparseSequential(*part_conv)
seg_channel_last = seg_in_channels
seg_conv = []
for i, channel in enumerate(seg_conv_channels):
seg_conv.append(
make_sparse_convmodule(seg_channel_last,
channel,
3,
padding=1,
norm_cfg=norm_cfg,
indice_key=f'rcnn_seg{i}',
conv_type='SubMConv3d'))
seg_channel_last = channel
self.seg_conv = spconv.SparseSequential(*seg_conv)
self.conv_down = spconv.SparseSequential()
merge_conv_channel_last = part_channel_last + seg_channel_last
merge_conv = []
for i, channel in enumerate(merge_conv_channels):
merge_conv.append(
make_sparse_convmodule(merge_conv_channel_last,
channel,
3,
padding=1,
norm_cfg=norm_cfg,
indice_key='rcnn_down0'))
merge_conv_channel_last = channel
down_conv_channel_last = merge_conv_channel_last
conv_down = []
for i, channel in enumerate(down_conv_channels):
conv_down.append(
make_sparse_convmodule(down_conv_channel_last,
channel,
3,
padding=1,
norm_cfg=norm_cfg,
indice_key='rcnn_down1'))
down_conv_channel_last = channel
self.conv_down.add_module('merge_conv',
spconv.SparseSequential(*merge_conv))
self.conv_down.add_module(
'max_pool3d', spconv.SparseMaxPool3d(kernel_size=2, stride=2))
self.conv_down.add_module('down_conv',
spconv.SparseSequential(*conv_down))
shared_fc_list = []
pool_size = roi_feat_size // 2
pre_channel = shared_fc_channels[0] * pool_size**3
for k in range(1, len(shared_fc_channels)):
shared_fc_list.append(
ConvModule(pre_channel,
shared_fc_channels[k],
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
inplace=True))
pre_channel = shared_fc_channels[k]
if k != len(shared_fc_channels) - 1 and dropout_ratio > 0:
shared_fc_list.append(nn.Dropout(dropout_ratio))
self.shared_fc = nn.Sequential(*shared_fc_list)
# Classification layer
channel_in = shared_fc_channels[-1]
cls_channel = 1
cls_layers = []
pre_channel = channel_in
for k in range(0, len(cls_channels)):
cls_layers.append(
ConvModule(pre_channel,
cls_channels[k],
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
inplace=True))
pre_channel = cls_channels[k]
cls_layers.append(
ConvModule(pre_channel,
cls_channel,
1,
padding=0,
conv_cfg=conv_cfg,
act_cfg=None))
if dropout_ratio >= 0:
cls_layers.insert(1, nn.Dropout(dropout_ratio))
self.conv_cls = nn.Sequential(*cls_layers)
# Regression layer
reg_layers = []
pre_channel = channel_in
for k in range(0, len(reg_channels)):
reg_layers.append(
ConvModule(pre_channel,
reg_channels[k],
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
inplace=True))
pre_channel = reg_channels[k]
reg_layers.append(
ConvModule(pre_channel,
self.bbox_coder.code_size,
1,
padding=0,
conv_cfg=conv_cfg,
act_cfg=None))
if dropout_ratio >= 0:
reg_layers.insert(1, nn.Dropout(dropout_ratio))
self.conv_reg = nn.Sequential(*reg_layers)
self.init_weights()
def __init__(self,
num_dims,
num_classes,
primitive_mode,
train_cfg=None,
test_cfg=None,
vote_module_cfg=None,
vote_aggregation_cfg=None,
feat_channels=(128, 128),
upper_thresh=100.0,
surface_thresh=0.5,
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
objectness_loss=None,
center_loss=None,
semantic_reg_loss=None,
semantic_cls_loss=None,
init_cfg=None):
super(PrimitiveHead, self).__init__(init_cfg=init_cfg)
assert primitive_mode in ['z', 'xy', 'line']
# The dimension of primitive semantic information.
self.num_dims = num_dims
self.num_classes = num_classes
self.primitive_mode = primitive_mode
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.gt_per_seed = vote_module_cfg['gt_per_seed']
self.num_proposal = vote_aggregation_cfg['num_point']
self.upper_thresh = upper_thresh
self.surface_thresh = surface_thresh
self.objectness_loss = build_loss(objectness_loss)
self.center_loss = build_loss(center_loss)
self.semantic_reg_loss = build_loss(semantic_reg_loss)
self.semantic_cls_loss = build_loss(semantic_cls_loss)
assert vote_aggregation_cfg['mlp_channels'][0] == vote_module_cfg[
'in_channels']
# Primitive existence flag prediction
self.flag_conv = ConvModule(
vote_module_cfg['conv_channels'][-1],
vote_module_cfg['conv_channels'][-1] // 2,
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
bias=True,
inplace=True)
self.flag_pred = torch.nn.Conv1d(
vote_module_cfg['conv_channels'][-1] // 2, 2, 1)
self.vote_module = VoteModule(**vote_module_cfg)
self.vote_aggregation = build_sa_module(vote_aggregation_cfg)
prev_channel = vote_aggregation_cfg['mlp_channels'][-1]
conv_pred_list = list()
for k in range(len(feat_channels)):
conv_pred_list.append(
ConvModule(
prev_channel,
feat_channels[k],
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
bias=True,
inplace=True))
prev_channel = feat_channels[k]
self.conv_pred = nn.Sequential(*conv_pred_list)
conv_out_channel = 3 + num_dims + num_classes
self.conv_pred.add_module('conv_out',
nn.Conv1d(prev_channel, conv_out_channel, 1))
def __init__(self,
num_classes,
suface_matching_cfg,
line_matching_cfg,
bbox_coder,
train_cfg=None,
test_cfg=None,
gt_per_seed=1,
num_proposal=256,
feat_channels=(128, 128),
primitive_feat_refine_streams=2,
primitive_refine_channels=[128, 128, 128],
upper_thresh=100.0,
surface_thresh=0.5,
line_thresh=0.5,
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
objectness_loss=None,
center_loss=None,
dir_class_loss=None,
dir_res_loss=None,
size_class_loss=None,
size_res_loss=None,
semantic_loss=None,
cues_objectness_loss=None,
cues_semantic_loss=None,
proposal_objectness_loss=None,
primitive_center_loss=None):
super(H3DBboxHead, self).__init__()
self.num_classes = num_classes
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.gt_per_seed = gt_per_seed
self.num_proposal = num_proposal
self.with_angle = bbox_coder['with_rot']
self.upper_thresh = upper_thresh
self.surface_thresh = surface_thresh
self.line_thresh = line_thresh
self.objectness_loss = build_loss(objectness_loss)
self.center_loss = build_loss(center_loss)
self.dir_class_loss = build_loss(dir_class_loss)
self.dir_res_loss = build_loss(dir_res_loss)
self.size_class_loss = build_loss(size_class_loss)
self.size_res_loss = build_loss(size_res_loss)
self.semantic_loss = build_loss(semantic_loss)
self.bbox_coder = build_bbox_coder(bbox_coder)
self.num_sizes = self.bbox_coder.num_sizes
self.num_dir_bins = self.bbox_coder.num_dir_bins
self.cues_objectness_loss = build_loss(cues_objectness_loss)
self.cues_semantic_loss = build_loss(cues_semantic_loss)
self.proposal_objectness_loss = build_loss(proposal_objectness_loss)
self.primitive_center_loss = build_loss(primitive_center_loss)
assert suface_matching_cfg['mlp_channels'][-1] == \
line_matching_cfg['mlp_channels'][-1]
# surface center matching
self.surface_center_matcher = build_sa_module(suface_matching_cfg)
# line center matching
self.line_center_matcher = build_sa_module(line_matching_cfg)
# Compute the matching scores
matching_feat_dims = suface_matching_cfg['mlp_channels'][-1]
self.matching_conv = ConvModule(matching_feat_dims,
matching_feat_dims,
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
bias=True,
inplace=True)
self.matching_pred = nn.Conv1d(matching_feat_dims, 2, 1)
# Compute the semantic matching scores
self.semantic_matching_conv = ConvModule(matching_feat_dims,
matching_feat_dims,
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
bias=True,
inplace=True)
self.semantic_matching_pred = nn.Conv1d(matching_feat_dims, 2, 1)
# Surface feature aggregation
self.surface_feats_aggregation = list()
for k in range(primitive_feat_refine_streams):
self.surface_feats_aggregation.append(
ConvModule(matching_feat_dims,
matching_feat_dims,
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
bias=True,
inplace=True))
self.surface_feats_aggregation = nn.Sequential(
*self.surface_feats_aggregation)
# Line feature aggregation
self.line_feats_aggregation = list()
for k in range(primitive_feat_refine_streams):
self.line_feats_aggregation.append(
ConvModule(matching_feat_dims,
matching_feat_dims,
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
bias=True,
inplace=True))
self.line_feats_aggregation = nn.Sequential(
*self.line_feats_aggregation)
# surface center(6) + line center(12)
prev_channel = 18 * matching_feat_dims
self.bbox_pred = nn.ModuleList()
for k in range(len(primitive_refine_channels)):
self.bbox_pred.append(
ConvModule(prev_channel,
primitive_refine_channels[k],
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
bias=True,
inplace=False))
prev_channel = primitive_refine_channels[k]
# Final object detection
# Objectness scores (2), center residual (3),
# heading class+residual (num_heading_bin*2), size class +
# residual(num_size_cluster*4)
conv_out_channel = (2 + 3 + bbox_coder['num_dir_bins'] * 2 +
bbox_coder['num_sizes'] * 4 + self.num_classes)
self.bbox_pred.append(nn.Conv1d(prev_channel, conv_out_channel, 1))
def __init__(self,
num_classes,
in_channels,
bbox_coder,
num_decoder_layers,
transformerlayers,
decoder_self_posembeds=dict(type='ConvBNPositionalEncoding',
input_channel=6,
num_pos_feats=288),
decoder_cross_posembeds=dict(type='ConvBNPositionalEncoding',
input_channel=3,
num_pos_feats=288),
train_cfg=None,
test_cfg=None,
num_proposal=128,
pred_layer_cfg=None,
size_cls_agnostic=True,
gt_per_seed=3,
sampling_objectness_loss=None,
objectness_loss=None,
center_loss=None,
dir_class_loss=None,
dir_res_loss=None,
size_class_loss=None,
size_res_loss=None,
size_reg_loss=None,
semantic_loss=None,
init_cfg=None):
super(GroupFree3DHead, self).__init__(init_cfg=init_cfg)
self.num_classes = num_classes
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.num_proposal = num_proposal
self.in_channels = in_channels
self.num_decoder_layers = num_decoder_layers
self.size_cls_agnostic = size_cls_agnostic
self.gt_per_seed = gt_per_seed
# Transformer decoder layers
if isinstance(transformerlayers, ConfigDict):
transformerlayers = [
copy.deepcopy(transformerlayers)
for _ in range(num_decoder_layers)
]
else:
assert isinstance(transformerlayers, list) and \
len(transformerlayers) == num_decoder_layers
self.decoder_layers = nn.ModuleList()
for i in range(self.num_decoder_layers):
self.decoder_layers.append(
build_transformer_layer(transformerlayers[i]))
self.embed_dims = self.decoder_layers[0].embed_dims
assert self.embed_dims == decoder_self_posembeds['num_pos_feats']
assert self.embed_dims == decoder_cross_posembeds['num_pos_feats']
# bbox_coder
self.bbox_coder = build_bbox_coder(bbox_coder)
self.num_sizes = self.bbox_coder.num_sizes
self.num_dir_bins = self.bbox_coder.num_dir_bins
# Initial object candidate sampling
self.gsample_module = GeneralSamplingModule()
self.fps_module = Points_Sampler([self.num_proposal])
self.points_obj_cls = PointsObjClsModule(self.in_channels)
self.fp16_enabled = False
# initial candidate prediction
self.conv_pred = BaseConvBboxHead(
**pred_layer_cfg,
num_cls_out_channels=self._get_cls_out_channels(),
num_reg_out_channels=self._get_reg_out_channels())
# query proj and key proj
self.decoder_query_proj = nn.Conv1d(self.embed_dims,
self.embed_dims,
kernel_size=1)
self.decoder_key_proj = nn.Conv1d(self.embed_dims,
self.embed_dims,
kernel_size=1)
# query position embed
self.decoder_self_posembeds = nn.ModuleList()
for _ in range(self.num_decoder_layers):
self.decoder_self_posembeds.append(
build_positional_encoding(decoder_self_posembeds))
# key position embed
self.decoder_cross_posembeds = nn.ModuleList()
for _ in range(self.num_decoder_layers):
self.decoder_cross_posembeds.append(
build_positional_encoding(decoder_cross_posembeds))
# Prediction Head
self.prediction_heads = nn.ModuleList()
for i in range(self.num_decoder_layers):
self.prediction_heads.append(
BaseConvBboxHead(
**pred_layer_cfg,
num_cls_out_channels=self._get_cls_out_channels(),
num_reg_out_channels=self._get_reg_out_channels()))
self.sampling_objectness_loss = build_loss(sampling_objectness_loss)
self.objectness_loss = build_loss(objectness_loss)
self.center_loss = build_loss(center_loss)
self.dir_res_loss = build_loss(dir_res_loss)
self.dir_class_loss = build_loss(dir_class_loss)
self.semantic_loss = build_loss(semantic_loss)
if self.size_cls_agnostic:
self.size_reg_loss = build_loss(size_reg_loss)
else:
self.size_res_loss = build_loss(size_res_loss)
self.size_class_loss = build_loss(size_class_loss)
def __init__(self,
num_classes,
bbox_coder,
train_cfg=None,
test_cfg=None,
vote_moudule_cfg=None,
vote_aggregation_cfg=None,
feat_channels=(128, 128),
conv_cfg=dict(type='Conv1d'),
norm_cfg=dict(type='BN1d'),
objectness_loss=None,
center_loss=None,
dir_class_loss=None,
dir_res_loss=None,
size_class_loss=None,
size_res_loss=None,
semantic_loss=None):
super(VoteHead, self).__init__()
self.num_classes = num_classes
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.gt_per_seed = vote_moudule_cfg['gt_per_seed']
self.num_proposal = vote_aggregation_cfg['num_point']
self.objectness_loss = build_loss(objectness_loss)
self.center_loss = build_loss(center_loss)
self.dir_class_loss = build_loss(dir_class_loss)
self.dir_res_loss = build_loss(dir_res_loss)
self.size_class_loss = build_loss(size_class_loss)
self.size_res_loss = build_loss(size_res_loss)
self.semantic_loss = build_loss(semantic_loss)
assert vote_aggregation_cfg['mlp_channels'][0] == vote_moudule_cfg[
'in_channels']
self.bbox_coder = build_bbox_coder(bbox_coder)
self.num_sizes = self.bbox_coder.num_sizes
self.num_dir_bins = self.bbox_coder.num_dir_bins
self.vote_module = VoteModule(**vote_moudule_cfg)
self.vote_aggregation = PointSAModule(**vote_aggregation_cfg)
prev_channel = vote_aggregation_cfg['mlp_channels'][-1]
conv_pred_list = list()
for k in range(len(feat_channels)):
conv_pred_list.append(
ConvModule(prev_channel,
feat_channels[k],
1,
padding=0,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
bias=True,
inplace=True))
prev_channel = feat_channels[k]
self.conv_pred = nn.Sequential(*conv_pred_list)
# Objectness scores (2), center residual (3),
# heading class+residual (num_dir_bins*2),
# size class+residual(num_sizes*4)
conv_out_channel = (2 + 3 + self.num_dir_bins * 2 +
self.num_sizes * 4 + num_classes)
self.conv_pred.add_module('conv_out',
nn.Conv1d(prev_channel, conv_out_channel, 1))
def __init__(self,
in_channels=[128],
tasks=None,
train_cfg=None,
test_cfg=None,
bbox_coder=None,
common_heads=dict(),
loss_cls=dict(type='GaussianFocalLoss', reduction='mean'),
loss_bbox=dict(type='L1Loss',
reduction='none',
loss_weight=0.25),
seperate_head=dict(type='SeparateHead',
init_bias=-2.19,
final_kernel=3),
feature_channel=64,
num_heatmap_convs=2,
conv_cfg=dict(type='Conv2d'),
norm_cfg=dict(type='BN2d'),
bias='auto',
norm_bbox=True,
pred_mode=['voxel'],
num_head_convs=2,
num_classes=17,
ignore_label=0,
grid_size=[480, 360, 32]):
super(SelectivesegHead, self).__init__()
self.class_names = [t['class_names'] for t in tasks]
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.in_channels = in_channels
self.num_classes = num_classes
self.norm_bbox = norm_bbox
self.loss_cls = build_loss(loss_cls)
self.loss_bbox = build_loss(loss_bbox)
self.bbox_coder = build_bbox_coder(bbox_coder)
self.fp16_enabled = False
self.pred_mode = pred_mode
assert ('voxel' in self.pred_mode) or ('point' in self.pred_mode) or (
'pillar' in self.pred_mode)
self.ignore_label = ignore_label
self.grid_size = grid_size
semantic_conv = []
for i in range(num_head_convs):
if i > 0:
in_channels = feature_channel
conv = ConvModule(in_channels,
feature_channel,
kernel_size=1,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
bias=False)
semantic_conv.append(conv)
self.semantic_conv = nn.Sequential(*semantic_conv)
self.semantic_cls = nn.Conv1d(feature_channel, self.num_classes, 1)
self.semantic_CE_loss = torch.nn.CrossEntropyLoss(
ignore_index=ignore_label)