def __init__(self, use_xyz=True, mode='TRAIN'):
super().__init__()
self.training_mode = (mode == 'TRAIN')
MODEL = importlib.import_module(cfg.RPN.BACKBONE)
self.backbone_net = MODEL.get_model(input_channels=int(
cfg.RPN.USE_INTENSITY),
use_xyz=use_xyz)
# classification branch
cls_layers = []
pre_channel = cfg.RPN.FP_MLPS[0][-1]
for k in range(0, cfg.RPN.CLS_FC.__len__()):
cls_layers.append(
pt_utils.Conv1d(pre_channel,
cfg.RPN.CLS_FC[k],
bn=cfg.RPN.USE_BN))
pre_channel = cfg.RPN.CLS_FC[k]
cls_layers.append(pt_utils.Conv1d(pre_channel, 1, activation=None))
if cfg.RPN.DP_RATIO >= 0:
cls_layers.insert(1, nn.Dropout(cfg.RPN.DP_RATIO))
self.rpn_cls_layer = nn.Sequential(*cls_layers)
# regression branch
per_loc_bin_num = int(cfg.RPN.LOC_SCOPE / cfg.RPN.LOC_BIN_SIZE) * 2
if cfg.RPN.LOC_XZ_FINE:
reg_channel = per_loc_bin_num * 4 + cfg.RPN.NUM_HEAD_BIN * 2 + 3
else:
reg_channel = per_loc_bin_num * 2 + cfg.RPN.NUM_HEAD_BIN * 2 + 3
reg_channel += 1 # reg y
reg_layers = []
pre_channel = cfg.RPN.FP_MLPS[0][-1]
for k in range(0, cfg.RPN.REG_FC.__len__()):
reg_layers.append(
pt_utils.Conv1d(pre_channel,
cfg.RPN.REG_FC[k],
bn=cfg.RPN.USE_BN))
pre_channel = cfg.RPN.REG_FC[k]
reg_layers.append(
pt_utils.Conv1d(pre_channel, reg_channel, activation=None))
if cfg.RPN.DP_RATIO >= 0:
reg_layers.insert(1, nn.Dropout(cfg.RPN.DP_RATIO))
self.rpn_reg_layer = nn.Sequential(*reg_layers)
if cfg.RPN.LOSS_CLS == 'DiceLoss':
self.rpn_cls_loss_func = loss_utils.DiceLoss(ignore_target=-1)
elif cfg.RPN.LOSS_CLS == 'SigmoidFocalLoss':
self.rpn_cls_loss_func = loss_utils.SigmoidFocalClassificationLoss(
alpha=cfg.RPN.FOCAL_ALPHA[0], gamma=cfg.RPN.FOCAL_GAMMA)
elif cfg.RPN.LOSS_CLS == 'BinaryCrossEntropy':
self.rpn_cls_loss_func = F.binary_cross_entropy
else:
raise NotImplementedError
self.proposal_layer = ProposalLayer(mode=mode)
self.init_weights()
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):
super().__init__()
iou_layer = []
pre_channel = 512
iou_layer.append(
pt_utils.Conv1d(pre_channel, pre_channel, bn=cfg.RCNN.USE_BN))
iou_layer.append(pt_utils.Conv1d(pre_channel, 1, activation=None))
if cfg.RCNN.DP_RATIO >= 0:
iou_layer.insert(1, nn.Dropout(cfg.RCNN.DP_RATIO))
self.iou_layer = nn.Sequential(*iou_layer)
self.proposal_target_layer = ProposalTargetLayer()
self.init_weights(weight_init='xavier')
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, num_classes, input_channels=0, use_xyz=True):
super().__init__()
self.SA_modules = nn.ModuleList()
channel_in = input_channels
if cfg.RCNN.USE_RPN_FEATURES:
self.rcnn_input_channel = 3 + int(cfg.RCNN.USE_INTENSITY) + int(cfg.RCNN.USE_MASK) + int(cfg.RCNN.USE_DEPTH)
self.xyz_up_layer = pt_utils.SharedMLP([self.rcnn_input_channel] + cfg.RCNN.XYZ_UP_LAYER,
bn=cfg.RCNN.USE_BN)
c_out = cfg.RCNN.XYZ_UP_LAYER[-1]
self.merge_down_layer = pt_utils.SharedMLP([c_out * 2, c_out], bn=cfg.RCNN.USE_BN)
for k in range(cfg.RCNN.SA_CONFIG.NPOINTS.__len__()):
mlps = [channel_in] + cfg.RCNN.SA_CONFIG.MLPS[k]
npoint = cfg.RCNN.SA_CONFIG.NPOINTS[k] if cfg.RCNN.SA_CONFIG.NPOINTS[k] != -1 else None
self.SA_modules.append(
PointnetSAModule(
npoint=npoint,
radius=cfg.RCNN.SA_CONFIG.RADIUS[k],
nsample=cfg.RCNN.SA_CONFIG.NSAMPLE[k],
mlp=mlps,
use_xyz=use_xyz,
bn=cfg.RCNN.USE_BN
)
)
channel_in = mlps[-1]
# classification layer
cls_channel = 1 if num_classes == 2 else num_classes
cls_layers = []
pre_channel = channel_in
for k in range(0, cfg.RCNN.CLS_FC.__len__()):
cls_layers.append(pt_utils.Conv1d(pre_channel, cfg.RCNN.CLS_FC[k], bn=cfg.RCNN.USE_BN))
pre_channel = cfg.RCNN.CLS_FC[k]
cls_layers.append(pt_utils.Conv1d(pre_channel, cls_channel, activation=None))
if cfg.RCNN.DP_RATIO >= 0:
cls_layers.insert(1, nn.Dropout(cfg.RCNN.DP_RATIO))
self.cls_layer = nn.Sequential(*cls_layers)
if cfg.RCNN.LOSS_CLS == 'SigmoidFocalLoss':
self.cls_loss_func = loss_utils.SigmoidFocalClassificationLoss(alpha=cfg.RCNN.FOCAL_ALPHA[0],
gamma=cfg.RCNN.FOCAL_GAMMA)
elif cfg.RCNN.LOSS_CLS == 'BinaryCrossEntropy':
self.cls_loss_func = F.binary_cross_entropy
elif cfg.RCNN.LOSS_CLS == 'CrossEntropy':
cls_weight = torch.from_numpy(cfg.RCNN.CLS_WEIGHT).float()
self.cls_loss_func = nn.CrossEntropyLoss(ignore_index=-1, reduce=False, weight=cls_weight)
else:
raise NotImplementedError
if cfg.USE_IOU_BRANCH:
iou_branch = []
iou_branch.append(pt_utils.Conv1d(channel_in, cfg.RCNN.REG_FC[0], bn=cfg.RCNN.USE_BN))
iou_branch.append(pt_utils.Conv1d(cfg.RCNN.REG_FC[0], cfg.RCNN.REG_FC[1], bn=cfg.RCNN.USE_BN))
iou_branch.append(pt_utils.Conv1d(cfg.RCNN.REG_FC[1], 1, activation=None))
if cfg.RCNN.DP_RATIO >= 0:
iou_branch.insert(1, nn.Dropout(cfg.RCNN.DP_RATIO))
self.iou_branch = nn.Sequential(*iou_branch)
#pass
# regression layer
per_loc_bin_num = int(cfg.RCNN.LOC_SCOPE / cfg.RCNN.LOC_BIN_SIZE) * 2
loc_y_bin_num = int(cfg.RCNN.LOC_Y_SCOPE / cfg.RCNN.LOC_Y_BIN_SIZE) * 2
reg_channel = per_loc_bin_num * 4 + cfg.RCNN.NUM_HEAD_BIN * 2 + 3
reg_channel += (1 if not cfg.RCNN.LOC_Y_BY_BIN else loc_y_bin_num * 2)
reg_layers = []
pre_channel = channel_in
for k in range(0, cfg.RCNN.REG_FC.__len__()):
reg_layers.append(pt_utils.Conv1d(pre_channel, cfg.RCNN.REG_FC[k], bn=cfg.RCNN.USE_BN))
pre_channel = cfg.RCNN.REG_FC[k]
reg_layers.append(pt_utils.Conv1d(pre_channel, reg_channel, activation=None))
if cfg.RCNN.DP_RATIO >= 0:
reg_layers.insert(1, nn.Dropout(cfg.RCNN.DP_RATIO))
self.reg_layer = nn.Sequential(*reg_layers)
self.proposal_target_layer = ProposalTargetLayer()
self.init_weights(weight_init='xavier')
def __init__(self,
num_classes,
num_point=512,
input_channels=0,
use_xyz=True):
super().__init__()
self.SA_modules = nn.ModuleList()
self.ATT_modules = nn.ModuleList()
channel_in = input_channels
self.MEAN_SIZE = torch.from_numpy(cfg.CLS_MEAN_SIZE[0]).cuda()
#todo use statics feature num
#self.rcnn_input_channel = 3 + int(cfg.RCNN.USE_INTENSITY) + int(cfg.RCNN.USE_MASK) + int(cfg.RCNN.USE_DEPTH)
self.rcnn_input_channel = 5
self.input_tansformer = Transformer(num_point, 3)
self.xyz_up_layer = pt_utils.SharedMLP([3] + cfg.RCNN.XYZ_UP_LAYER,
bn=cfg.RCNN.USE_BN)
#self.feature_tansformer = Transformer(num_point, cfg.RCNN.XYZ_UP_LAYER[-1])
self.feature_up_layer = pt_utils.SharedMLP(
[self.rcnn_input_channel - 3] + cfg.RCNN.XYZ_UP_LAYER,
bn=cfg.RCNN.USE_BN)
c_out = cfg.RCNN.XYZ_UP_LAYER[-1]
self.merge_down_layer = pt_utils.SharedMLP([c_out * 2, c_out],
bn=cfg.RCNN.USE_BN)
for k in range(cfg.RCNN.SA_CONFIG.NPOINTS.__len__()):
if cfg.ATTENTION:
self.ATT_modules.append(
pt_utils.SharedMLP([channel_in],
bn=cfg.RCNN.USE_BN,
activation=nn.ReLU(inplace=True)))
mlps = [channel_in] + cfg.RCNN.SA_CONFIG.MLPS[k]
npoint = cfg.RCNN.SA_CONFIG.NPOINTS[
k] if cfg.RCNN.SA_CONFIG.NPOINTS[k] != -1 else None
self.SA_modules.append(
PointnetSAModule(npoint=npoint,
radius=cfg.RCNN.SA_CONFIG.RADIUS[k],
nsample=cfg.RCNN.SA_CONFIG.NSAMPLE[k],
mlp=mlps,
use_xyz=use_xyz,
bn=cfg.RCNN.USE_BN))
channel_in = mlps[-1]
# class SharedMLP(nn.Sequential):
#
# def __init__(
# self,
# args: List[int],
# *,
# bn: bool = False,
# activation=nn.ReLU(inplace=True),
# preact: bool = False,
# first: bool = False,
# name: str = "",
# instance_norm: bool = False,
# ):
# classification layer
cls_channel = 1 if num_classes == 2 else num_classes
cls_layers = []
pre_channel = channel_in
for k in range(0, cfg.RCNN.CLS_FC.__len__()):
cls_layers.append(
pt_utils.Conv1d(pre_channel,
cfg.RCNN.CLS_FC[k],
bn=cfg.RCNN.USE_BN))
pre_channel = cfg.RCNN.CLS_FC[k]
cls_layers.append(
pt_utils.Conv1d(pre_channel, cls_channel, activation=None))
if cfg.RCNN.DP_RATIO >= 0:
cls_layers.insert(1, nn.Dropout(cfg.RCNN.DP_RATIO))
self.cls_layer = nn.Sequential(*cls_layers)
if cfg.RCNN.LOSS_CLS == 'SigmoidFocalLoss':
self.cls_loss_func = loss_utils.SigmoidFocalClassificationLoss(
alpha=cfg.RCNN.FOCAL_ALPHA[0], gamma=cfg.RCNN.FOCAL_GAMMA)
elif cfg.RCNN.LOSS_CLS == 'BinaryCrossEntropy':
self.cls_loss_func = F.binary_cross_entropy
elif cfg.RCNN.LOSS_CLS == 'CrossEntropy':
cls_weight = torch.from_numpy(cfg.RCNN.CLS_WEIGHT).float()
self.cls_loss_func = nn.CrossEntropyLoss(ignore_index=-1,
reduce=False,
weight=cls_weight)
else:
raise NotImplementedError
# regression layer
per_loc_bin_num = int(cfg.RCNN.LOC_SCOPE / cfg.RCNN.LOC_BIN_SIZE) * 2
loc_y_bin_num = int(cfg.RCNN.LOC_Y_SCOPE / cfg.RCNN.LOC_Y_BIN_SIZE) * 2
reg_channel = per_loc_bin_num * 4 + cfg.RCNN.NUM_HEAD_BIN * 2 + 3
reg_channel += (1 if not cfg.RCNN.LOC_Y_BY_BIN else loc_y_bin_num * 2)
reg_layers = []
pre_channel = channel_in
for k in range(0, cfg.RCNN.REG_FC.__len__()):
reg_layers.append(
pt_utils.Conv1d(pre_channel,
cfg.RCNN.REG_FC[k],
bn=cfg.RCNN.USE_BN))
pre_channel = cfg.RCNN.REG_FC[k]
reg_layers.append(
pt_utils.Conv1d(pre_channel, reg_channel, activation=None))
if cfg.RCNN.DP_RATIO >= 0:
reg_layers.insert(1, nn.Dropout(cfg.RCNN.DP_RATIO))
self.reg_layer = nn.Sequential(*reg_layers)
# IOU estimation
# IOU layer
if cfg.IOUN.ENABLED:
self.cascade = cfg.CASCADE
self.can_xyz_up_layer = nn.ModuleList()
self.can_feature_up_layer = nn.ModuleList()
self.can_merge_down_layer = nn.ModuleList()
self.SA_score_modules = nn.ModuleList()
self.ATT_score_modules = nn.ModuleList()
self.IOU_layer = nn.ModuleList()
self.ICL_layer = nn.ModuleList()
self.ref_layer = nn.ModuleList()
for i in range(self.cascade):
for p in self.parameters():
p.requires_grad = False
self.can_xyz_up_layer.append(
pt_utils.SharedMLP([3] + cfg.RCNN.XYZ_UP_LAYER,
bn=cfg.RCNN.USE_BN).cuda())
self.can_feature_up_layer.append(
pt_utils.SharedMLP([2] + cfg.RCNN.XYZ_UP_LAYER,
bn=cfg.RCNN.USE_BN).cuda())
c_out = cfg.RCNN.XYZ_UP_LAYER[-1]
self.can_merge_down_layer.append(
pt_utils.SharedMLP([c_out * 2, c_out], bn=cfg.RCNN.USE_BN))
iou_channel_in = input_channels
for k in range(cfg.IOUN.SA_CONFIG.NPOINTS.__len__()):
mlps = [iou_channel_in] + cfg.IOUN.SA_CONFIG.MLPS[k]
if cfg.ATTENTION:
self.ATT_score_modules.append(
pt_utils.SharedMLP(
[iou_channel_in],
bn=cfg.RCNN.USE_BN,
activation=nn.ELU(inplace=True)))
npoint = cfg.IOUN.SA_CONFIG.NPOINTS[
k] if cfg.IOUN.SA_CONFIG.NPOINTS[k] != -1 else None
self.SA_score_modules.append(
PointnetSAModule(npoint=npoint,
radius=cfg.IOUN.SA_CONFIG.RADIUS[k],
nsample=cfg.IOUN.SA_CONFIG.NSAMPLE[k],
mlp=mlps,
use_xyz=use_xyz,
bn=cfg.IOUN.USE_BN).cuda())
iou_channel_in = mlps[-1]
IOU_channel = 1
IOU_layers = []
pre_channel = iou_channel_in
for k in range(0, cfg.IOUN.CLS_FC.__len__()):
IOU_layers.append(
pt_utils.Conv1d(pre_channel,
cfg.IOUN.CLS_FC[k],
bn=cfg.IOUN.USE_BN))
pre_channel = cfg.IOUN.CLS_FC[k]
IOU_layers.append(
pt_utils.Conv1d(pre_channel, IOU_channel, activation=None))
if cfg.IOUN.DP_RATIO >= 0:
IOU_layers.insert(1, nn.Dropout(cfg.IOUN.DP_RATIO))
self.IOU_layer.append(nn.Sequential(*IOU_layers).cuda())
ICL_channel = 1
ICL_layers = []
pre_channel = iou_channel_in
for k in range(0, cfg.IOUN.CLS_FC.__len__()):
ICL_layers.append(
pt_utils.Conv1d(pre_channel,
cfg.IOUN.CLS_FC[k],
bn=cfg.IOUN.USE_BN))
pre_channel = cfg.IOUN.CLS_FC[k]
ICL_layers.append(
pt_utils.Conv1d(pre_channel, ICL_channel, activation=None))
if cfg.IOUN.DP_RATIO >= 0:
ICL_layers.insert(1, nn.Dropout(cfg.IOUN.DP_RATIO))
self.ICL_layer.append(nn.Sequential(*ICL_layers).cuda())
per_loc_bin_num = int(
cfg.IOUN.LOC_SCOPE / cfg.IOUN.LOC_BIN_SIZE) * 2
loc_y_bin_num = int(
cfg.IOUN.LOC_Y_SCOPE / cfg.IOUN.LOC_Y_BIN_SIZE) * 2
ref_channel = 7
ref_layers = []
pre_channel = iou_channel_in
for k in range(0, cfg.IOUN.REG_FC.__len__()):
ref_layers.append(
pt_utils.Conv1d(pre_channel,
cfg.IOUN.REG_FC[k],
bn=cfg.IOUN.USE_BN))
pre_channel = cfg.IOUN.REG_FC[k]
ref_layers.append(
pt_utils.Conv1d(pre_channel, ref_channel, activation=None))
if cfg.IOUN.DP_RATIO >= 0:
ref_layers.insert(1, nn.Dropout(cfg.IOUN.DP_RATIO))
self.ref_layer.append(nn.Sequential(*ref_layers).cuda())
self.init_weights(weight_init='xavier')
def __init__(self, use_xyz=True, mode='TRAIN'):
super().__init__()
self.training_mode = (mode == 'TRAIN')
MODEL = importlib.import_module(cfg.RPN.BACKBONE)
self.backbone_net = MODEL.get_model(input_channels=int(
cfg.RPN.USE_INTENSITY),
use_xyz=use_xyz)
# here Conv1d is almost the same as torch Conv1d
# for torch Conv1d see https://pytorch.org/docs/stable/nn.html#conv1d
# here we use the Conv1d so we can do two levels of batch calculation
# the first level is at the level of the scenes and the second is at the level of th points
# The input to both heads is a (B, C, N) shaped tensor.
# C is number of channels (i.e. the number of features each point has) (it is apparently 128)
# N is the number of points in one scene
# this way we regress the output values of all the points using a single run of a Conv1d layer
# Notice the output has the form: classification head (B,1,N) , regression head (B,9,N)
# since the kernel_size is 1 the output is a linear combination of channels just like a simple linear regression plus a bias
# in the case of the regression head, each of the 9 outputs has its own set of weights and biases.
# notice the output is the result of the regression/classification for all the points not just a single one.
# classification branch
cls_layers = []
pre_channel = cfg.RPN.FP_MLPS[0][-1] # = 128
for k in range(0, cfg.RPN.CLS_FC.__len__()):
# input is 128 output is also 128
cls_layers.append(
pt_utils.Conv1d(
pre_channel, cfg.RPN.CLS_FC[k],
bn=cfg.RPN.USE_BN)) # bn is batch normalization
pre_channel = cfg.RPN.CLS_FC[k]
cls_layers.append(pt_utils.Conv1d(pre_channel, 1, activation=None)
) # sigmoid is applied in the loss function not here
# this ends up being:
# 1st layer 128 inputs to 128 outputs
# 2nd layer 128 to 1
if cfg.RPN.DP_RATIO >= 0:
cls_layers.insert(1, nn.Dropout(cfg.RPN.DP_RATIO))
self.rpn_cls_layer = nn.Sequential(*cls_layers)
# it adds a dropout layer with ratio 0.5
# regression branch
# we will do a normal regression for all the 9 parameters (x,y,z, w,h,l , rx,ry,rz) of our bboxes
reg_channel = 9
reg_layers = []
pre_channel = cfg.RPN.FP_MLPS[0][-1] # = 128
for k in range(0, cfg.RPN.REG_FC.__len__()): # cfg.RPN.REG_FC = [128]
reg_layers.append(
pt_utils.Conv1d(pre_channel,
cfg.RPN.REG_FC[k],
bn=cfg.RPN.USE_BN))
pre_channel = cfg.RPN.REG_FC[k]
reg_layers.append(
pt_utils.Conv1d(pre_channel, reg_channel, activation=None))
#if you use binning and classification the activation of this last layer is applied in the loss instead
# see /lib/utils/loss_utils.py "get_reg_loss" it uses BinaryCrossEntropy which applies a softmax (I need to change this !)
if cfg.RPN.DP_RATIO >= 0:
reg_layers.insert(1, nn.Dropout(cfg.RPN.DP_RATIO))
self.rpn_reg_layer = nn.Sequential(*reg_layers)
# this ends up being:
# 1st layer 128 inputs to 128 outputs
# 2nd layer 128 to 9 outputs
# it adds a dropout layer with ratio 0.5
if cfg.RPN.LOSS_CLS == 'DiceLoss':
self.rpn_cls_loss_func = loss_utils.DiceLoss(ignore_target=-1)
elif cfg.RPN.LOSS_CLS == 'SigmoidFocalLoss':
self.rpn_cls_loss_func = loss_utils.SigmoidFocalClassificationLoss(
alpha=cfg.RPN.FOCAL_ALPHA[0], gamma=cfg.RPN.FOCAL_GAMMA)
elif cfg.RPN.LOSS_CLS == 'BinaryCrossEntropy':
self.rpn_cls_loss_func = F.binary_cross_entropy
else:
raise NotImplementedError
# proposal layer is only used in RCNN and not in RPN
self.proposal_layer = ProposalLayer(mode=mode)
self.init_weights()
