def __init__(self, input_channels=0, use_xyz=True, mode="TRAIN"):
super().__init__()
# 特征提取
# self.backbone_net = pointnet2_msg.get_model()
c_in = input_channels
self.SA_module1 = PointnetSAModuleMSG(npoint=8192, radii=[0.1, 0.5], nsamples=[16, 32], mlps=[[c_in, 16, 16, 32], [c_in, 32, 32, 64]], use_xyz=use_xyz, bn=True)
c_out_1 = 32 + 64
c_in = c_out_1
self.SA_module2 = PointnetSAModuleMSG(npoint=2048, radii=[0.5, 1.], nsamples=[16, 32], mlps=[[c_in, 64, 64, 128], [c_in, 64, 96, 128]], use_xyz=use_xyz, bn=True)
c_out_2 = 128 + 128
c_in = c_out_2
self.SA_module3 = PointnetSAModuleMSG(npoint=512, radii=[1.0, 2.0], nsamples=[16, 32], mlps=[[c_in, 128, 196, 256], [c_in, 128, 196, 256]], use_xyz=use_xyz, bn=True)
c_out_3 = 256 + 256
c_in = c_out_3
self.SA_module4 = PointnetSAModuleMSG(npoint=128, radii=[2.0, 4.0], nsamples=[16, 32], mlps=[[c_in, 256, 256, 512], [c_in, 256, 384, 512]], use_xyz=use_xyz, bn=True)
c_out_4 = 512 + 512
self.FP_module1 = PointnetFPModule(mlp=[c_out_4+c_out_3, 512, 512], bn=True)
self.FP_module2 = PointnetFPModule(mlp=[512+c_out_2, 512, 512], bn=True)
self.FP_module3 = PointnetFPModule(mlp=[512+c_out_1, 256, 256], bn=True)
self.FP_module4 = PointnetFPModule(mlp=[256+input_channels, 128, 128], bn=True)
self.ins_fc1 = pt_utils.Conv1d(128, 64, kernel_size=1, bn=True)
# self.ins_dp = nn.Dropout(0.1)
self.ins_fc2 = pt_utils.Conv1d(64, 5, kernel_size=1, bn=False, activation=None)
def __init__(self, input_channels=6, use_xyz=True):
super().__init__()
self.SA_modules = nn.ModuleList()
channel_in = input_channels
skip_channel_list = [input_channels]
for k in range(cfg.RPN.SA_CONFIG.NPOINTS.__len__()):
mlps = cfg.RPN.SA_CONFIG.MLPS[k].copy()
channel_out = 0
for idx in range(mlps.__len__()):
mlps[idx] = [channel_in] + mlps[idx]
channel_out += mlps[idx][-1]
self.SA_modules.append(
PointnetSAModuleMSG(npoint=cfg.RPN.SA_CONFIG.NPOINTS[k],
radii=cfg.RPN.SA_CONFIG.RADIUS[k],
nsamples=cfg.RPN.SA_CONFIG.NSAMPLE[k],
mlps=mlps,
use_xyz=use_xyz,
bn=cfg.RPN.USE_BN))
skip_channel_list.append(channel_out)
channel_in = channel_out
self.FP_modules = nn.ModuleList()
for k in range(cfg.RPN.FP_MLPS.__len__()):
pre_channel = cfg.RPN.FP_MLPS[k + 1][-1] if k + 1 < len(
cfg.RPN.FP_MLPS) else channel_out
self.FP_modules.append(
PointnetFPModule(mlp=[pre_channel + skip_channel_list[k]] +
cfg.RPN.FP_MLPS[k]))
def __init__(self, input_channels=0, use_xyz=True, mode="TRAIN"):
super().__init__()
# 特征提取
# self.backbone_net = pointnet2_msg.get_model()
npoints = cfg.NET.SA_NPOINTS
radiis = cfg.NET.RADIIS
nsamples = cfg.NET.NSAMPLES
mlps = cfg.NET.MLPS
# c_in = input_channels
# self.SA_module1 = PointnetSAModuleMSG(npoint=npoints[0], radii=radiis[0], nsamples=nsamples[0],
# mlps=[[c_in, *mlps[0][0]], [c_in, *mlps[0][1]], [c_in, *mlps[0][2]]], use_xyz=use_xyz, bn=True)
# c_out_1 = sum(mlps[0][:][-1])
# c_in = c_out_1
# self.SA_module2 = PointnetSAModuleMSG(npoint=npoints[1], radii=radiis[1], nsamples=nsamples[1],
# mlps=[[c_in, *mlps[1][0]], [c_in, *mlps[1][1]], [c_in, *mlps[1][2]]], use_xyz=use_xyz, bn=True)
# c_out_2 = sum(mlps[1][:][-1])
# c_in = c_out_2
# self.SA_module3 = PointnetSAModuleMSG(npoint=npoints[2], radii=radiis[2], nsamples=nsamples[2],
# mlps=[[c_in, *mlps[2][0]], [c_in, *mlps[2][1]], [c_in, *mlps[2][2]]], use_xyz=use_xyz, bn=True)
# c_out_3 = sum(mlps[2][:][-1])
# c_in = c_out_3
# self.SA_module4 = PointnetSAModuleMSG(npoint=npoints[3], radii=radiis[3], nsamples=nsamples[3],
# mlps=[[c_in, *mlps[3][0]], [c_in, *mlps[3][1]], [c_in, *mlps[3][2]]], use_xyz=use_xyz, bn=True)
# c_out_4 = sum(mlps[3][:][-1])
c_in = input_channels
c_out = []
sa_module = []
for i in range(len(npoints)):
c_o = 0
for m in mlps[i]:
m[:] = [c_in, *m]
c_o += m[-1]
c_out.append(c_o)
sa_module.append(
PointnetSAModuleMSG(npoint=npoints[i],
radii=radiis[i],
nsamples=nsamples[i],
mlps=mlps[i],
use_xyz=use_xyz,
bn=True))
c_in = c_out[-1]
self.SA_module1 = sa_module[0]
self.SA_module2 = sa_module[1]
self.SA_module3 = sa_module[2]
self.SA_module4 = sa_module[3]
c_out_1, c_out_2, c_out_3, c_out_4 = c_out
self.FP_module1 = PointnetFPModule(mlp=[c_out_4 + c_out_3, 512, 512],
bn=True)
self.FP_module2 = PointnetFPModule(mlp=[512 + c_out_2, 512, 512],
bn=True)
self.FP_module3 = PointnetFPModule(mlp=[512 + c_out_1, 256, 256],
bn=True)
self.FP_module4 = PointnetFPModule(
mlp=[256 + input_channels, 128, 128], bn=True)
self.ins_fc1 = pt_utils.Conv1d(128, 64, kernel_size=1, bn=True)
# self.ins_dp = nn.Dropout(0.1)
self.ins_fc2 = pt_utils.Conv1d(64,
8,
kernel_size=1,
bn=False,
activation=None)
def __init__(self, input_channels=7):
super.__init__()
self.SA_module1 = PointnetSAModuleMSG(npoint=1024，radii=[0.1, 0.5], nsamples=[16, 32], mlps=[[16, 16, 32], [32, 32, 64]], use_xyz=use_xyz, bn=True)
self.SA_module2 = PointnetSAModuleMSG(npoint=256，radii=[0.5, 1.0], nsamples=[16, 32], mlps=[[64, 64, 128], [64, 96, 128]], use_xyz=use_xyz, bn=True)
self.SA_module3 = PointnetSAModuleMSG(npoint=64，radii=[1.0, 2.0], nsamples=[16, 32], mlps=[[128, 196, 256], [128, 196, 256]], use_xyz=use_xyz, bn=True)
self.SA_module4 = PointnetSAModuleMSG(npoint=16，radii=[2.0, 4.0], nsamples=[16, 32], mlps=[[256, 256, 512], [256, 384, 512]], use_xyz=use_xyz, bn=True)
# class Pointnet2MSG(nn.Module):
# def __init__(self, input_channels=6, use_xyz=True):
# super().__init__()
# self.SA_modules = nn.ModuleList()
# channel_in = input_channels
# skip_channel_list = [input_channels]
# for k in range(cfg.RPN.SA_CONFIG.NPOINTS.__len__()):
# mlps = cfg.RPN.SA_CONFIG.MLPS[k].copy()
# channel_out = 0
# for idx in range(mlps.__len__()):
# mlps[idx] = [channel_in] + mlps[idx]
# channel_out += mlps[idx][-1]
# self.SA_modules.append(
# PointnetSAModuleMSG(
# npoint=cfg.RPN.SA_CONFIG.NPOINTS[k],
# radii=cfg.RPN.SA_CONFIG.RADIUS[k],
# nsamples=cfg.RPN.SA_CONFIG.NSAMPLE[k],
# mlps=mlps,
# use_xyz=use_xyz,
# bn=cfg.RPN.USE_BN
# )
# )
# skip_channel_list.append(channel_out)
# channel_in = channel_out
# self.FP_modules = nn.ModuleList()
# for k in range(cfg.RPN.FP_MLPS.__len__()):
# pre_channel = cfg.RPN.FP_MLPS[k + 1][-1] if k + 1 < len(cfg.RPN.FP_MLPS) else channel_out
# self.FP_modules.append(
# PointnetFPModule(mlp=[pre_channel + skip_channel_list[k]] + cfg.RPN.FP_MLPS[k])
# )
# def _break_up_pc(self, pc):
# xyz = pc[..., 0:3].contiguous()
# features = (
# pc[..., 3:].transpose(1, 2).contiguous()
# if pc.size(-1) > 3 else None
# )
# return xyz, features
# def forward(self, pointcloud: torch.cuda.FloatTensor):
# xyz, features = self._break_up_pc(pointcloud)
# l_xyz, l_features = [xyz], [features]
# for i in range(len(self.SA_modules)):
# li_xyz, li_features = self.SA_modules[i](l_xyz[i], l_features[i])
# l_xyz.append(li_xyz)
# l_features.append(li_features)
# for i in range(-1, -(len(self.FP_modules) + 1), -1):
# l_features[i - 1] = self.FP_modules[i](
# l_xyz[i - 1], l_xyz[i], l_features[i - 1], l_features[i]
# )
# return l_xyz[0], l_features[0]
def __init__(self, input_channels=6, use_xyz=True):
super().__init__()
self.SA_modules = nn.ModuleList()
channel_in = input_channels
skip_channel_list = [input_channels]
for k in range(cfg.RPN.SA_CONFIG.NPOINTS.__len__()):
mlps = cfg.RPN.SA_CONFIG.MLPS[k].copy()
channel_out = 0
for idx in range(mlps.__len__()):
mlps[idx] = [channel_in] + mlps[idx]
channel_out += mlps[idx][-1]
self.SA_modules.append(
PointnetSAModuleMSG(npoint=cfg.RPN.SA_CONFIG.NPOINTS[k],
radii=cfg.RPN.SA_CONFIG.RADIUS[k],
nsamples=cfg.RPN.SA_CONFIG.NSAMPLE[k],
mlps=mlps,
use_xyz=use_xyz,
bn=cfg.RPN.USE_BN))
skip_channel_list.append(channel_out)
channel_in = channel_out
##################
if cfg.LI_FUSION.ENABLED:
self.Img_Block = nn.ModuleList()
self.Fusion_Conv = nn.ModuleList()
self.DeConv = nn.ModuleList()
for i in range(len(cfg.LI_FUSION.IMG_CHANNELS) - 1):
self.Img_Block.append(
BasicBlock(cfg.LI_FUSION.IMG_CHANNELS[i],
cfg.LI_FUSION.IMG_CHANNELS[i + 1],
stride=1))
if cfg.LI_FUSION.ADD_Image_Attention:
self.Fusion_Conv.append(
Atten_Fusion_Conv(cfg.LI_FUSION.IMG_CHANNELS[i + 1],
cfg.LI_FUSION.POINT_CHANNELS[i],
cfg.LI_FUSION.POINT_CHANNELS[i]))
else:
self.Fusion_Conv.append(
Fusion_Conv(
cfg.LI_FUSION.IMG_CHANNELS[i + 1] +
cfg.LI_FUSION.POINT_CHANNELS[i],
cfg.LI_FUSION.POINT_CHANNELS[i]))
self.DeConv.append(
nn.ConvTranspose2d(
cfg.LI_FUSION.IMG_CHANNELS[i + 1],
cfg.LI_FUSION.DeConv_Reduce[i],
kernel_size=cfg.LI_FUSION.DeConv_Kernels[i],
stride=cfg.LI_FUSION.DeConv_Kernels[i]))
self.image_fusion_conv = nn.Conv2d(
sum(cfg.LI_FUSION.DeConv_Reduce),
cfg.LI_FUSION.IMG_FEATURES_CHANNEL // 4,
kernel_size=1)
self.image_fusion_bn = torch.nn.BatchNorm2d(
cfg.LI_FUSION.IMG_FEATURES_CHANNEL // 4)
if cfg.LI_FUSION.ADD_Image_Attention:
self.final_fusion_img_point = Atten_Fusion_Conv(
cfg.LI_FUSION.IMG_FEATURES_CHANNEL // 4,
cfg.LI_FUSION.IMG_FEATURES_CHANNEL,
cfg.LI_FUSION.IMG_FEATURES_CHANNEL)
else:
self.final_fusion_img_point = Fusion_Conv(
cfg.LI_FUSION.IMG_FEATURES_CHANNEL +
cfg.LI_FUSION.IMG_FEATURES_CHANNEL // 4,
cfg.LI_FUSION.IMG_FEATURES_CHANNEL)
self.FP_modules = nn.ModuleList()
for k in range(cfg.RPN.FP_MLPS.__len__()):
pre_channel = cfg.RPN.FP_MLPS[k + 1][-1] if k + 1 < len(
cfg.RPN.FP_MLPS) else channel_out
self.FP_modules.append(
PointnetFPModule(mlp=[pre_channel + skip_channel_list[k]] +
cfg.RPN.FP_MLPS[k]))