def __init__(self,
*,
npoint: int,
radii: List[float],
nsamples: List[int],
mlps: List[List[int]],
bn: bool = True,
use_xyz: bool = True):
super().__init__()
assert len(radii) == len(nsamples) == len(mlps)
self.npoint = npoint
self.groupers = nn.ModuleList()
self.mlps = nn.ModuleList()
for i in range(len(radii)):
radius = radii[i]
nsample = nsamples[i]
self.groupers.append(
pointnet2_utils.QueryAndGroup(radius, nsample, use_xyz=use_xyz)
if npoint is not None else pointnet2_utils.GroupAll(use_xyz))
mlp_spec = mlps[i]
if use_xyz:
mlp_spec[0] += 3
self.mlps.append(pt_utils.SharedMLP(mlp_spec, bn=bn))
def __init__(self,
radii,
nsamples,
mlps,
bn=True,
use_xyz=True,
vote=False):
# type: (PointnetSAModuleMSG, int, list[float], list[int], list[list[int]], bool, bool) -> None
super(PointnetSAModuleMSG, self).__init__()
# 继承了_PointnetSAModuleBase中定义的操作方法
assert len(radii) == len(nsamples) == len(mlps)
self.groupers = nn.ModuleList()
self.mlps = nn.ModuleList()
for i in range(len(radii)):
radius = radii[i] # 多尺度就在于球查询有多种半径
nsample = nsamples[i]
if vote is False:
self.groupers.append(
pointnet2_utils.QueryAndGroup(radius,
nsample,
use_xyz=use_xyz))
# self.add_module(str(len(self)), module)
else: # 如果要霍夫投票，就要计算得分
self.groupers.append(
pointnet2_utils.QueryAndGroup_score(radius,
nsample,
use_xyz=use_xyz))
mlp_spec = mlps[i]
if use_xyz: # 如果要使用坐标信息，则MLP的输入要加三个
mlp_spec[0] += 3
self.mlps.append(pt_utils.SharedMLP(mlp_spec, bn=bn))
def __init__(self,
radii,
nsamples,
mlps,
bn=True,
use_xyz=True,
vote=False):
# type: (PointnetSAModuleMSG, int, List[float], List[int], List[List[int]], bool, bool) -> None
super(PointnetSAModuleMSG, self).__init__()
assert len(radii) == len(nsamples) == len(mlps)
self.groupers = nn.ModuleList()
self.mlps = nn.ModuleList()
for i in range(len(radii)):
radius = radii[i]
nsample = nsamples[i]
if vote is False:
self.groupers.append(
pointnet2_utils.QueryAndGroup(radius,
nsample,
use_xyz=use_xyz))
else:
self.groupers.append(
pointnet2_utils.QueryAndGroup_score(radius,
nsample,
use_xyz=use_xyz))
mlp_spec = mlps[i]
if use_xyz:
mlp_spec[0] += 3
self.mlps.append(pt_utils.SharedMLP(mlp_spec, bn=bn))
def __init__(self, npoint, radius, nsample, c_in, c_out, first_layer, mlp):
super(RSSAModule2, self).__init__()
self.npoint = npoint
self.radius = radius
self.nsample = nsample
# self.group_all = group_all
self.mlp_convs = nn.ModuleList()
self.mlp_bns = nn.ModuleList()
self.queryandgroup = pointutils.QueryAndGroup(radius, nsample)
self.first_layer = first_layer
# RS
c_in = c_in + 3
if first_layer:
self.mapping_func1 = nn.Conv2d(in_channels=10,
out_channels=math.floor(c_out / 2),
kernel_size=(1, 1),
stride=(1, 1),
bias=True)
self.bn_mapping = nn.BatchNorm2d(math.floor(c_out / 2))
self.mapping_func2 = nn.Conv2d(in_channels=math.floor(c_out / 2),
out_channels=16,
kernel_size=(1, 1),
stride=(1, 1),
bias=True)
self.xyz_raising = nn.Conv2d(in_channels=c_in,
out_channels=16,
kernel_size=(1, 1),
stride=(1, 1),
bias=True)
self.bn_xyz_raising = nn.BatchNorm2d(16)
self.bn_rsconv = nn.BatchNorm2d(16)
# self.cr_mapping = nn.Conv1d(in_channels=16, out_channels=c_out, kernel_size=1, stride=1, bias=True)
# self.bn_channel_raising = nn.BatchNorm1d(c_out)
else:
self.mapping_func1 = nn.Conv2d(in_channels=10,
out_channels=math.floor(c_out / 4),
kernel_size=(1, 1),
stride=(1, 1),
bias=True)
self.bn_mapping = nn.BatchNorm2d(math.floor(c_out / 4))
self.mapping_func2 = nn.Conv2d(in_channels=math.floor(c_out / 4),
out_channels=c_in,
kernel_size=(1, 1),
stride=(1, 1),
bias=True)
self.bn_rsconv = nn.BatchNorm2d(c_in)
# self.cr_mapping = nn.Conv1d(in_channels=c_in, out_channels=c_out, kernel_size=1, stride=1, bias=True)
# self.bn_channel_raising = nn.BatchNorm1d(c_out)
last_channel = c_in if not first_layer else 16
for out_channel in mlp:
self.mlp_convs.append(
nn.Conv2d(last_channel, out_channel, 1, bias=False))
self.mlp_bns.append(nn.BatchNorm2d(out_channel))
last_channel = out_channel
def __init__(self, npoint, radius, nsample, in_channel, mlp, group_all):
super(SAModule, self).__init__()
self.npoint = npoint
self.radius = radius
self.nsample = nsample
self.group_all = group_all
self.mlp_convs = nn.ModuleList()
self.mlp_bns = nn.ModuleList()
last_channel = in_channel + 3 # TODO：
for out_channel in mlp:
self.mlp_convs.append(
nn.Conv2d(last_channel, out_channel, 1, bias=False))
self.mlp_bns.append(nn.BatchNorm2d(out_channel))
last_channel = out_channel
if group_all:
self.queryandgroup = pointutils.GroupAll()
else:
self.queryandgroup = pointutils.QueryAndGroup(radius, nsample)
