def __init__(self, num_layers, ndim, shape, kernel_size, stride, padding,
dilation):
super().__init__()
layers = [
spconv.SparseMaxPool3d(kernel_size, stride, padding, dilation)
]
for i in range(1, num_layers):
layers.append(
spconv.SparseMaxPool3d(kernel_size, stride, padding, dilation))
self.net = spconv.SparseSequential(*layers, )
self.shape = shape
def __init__(self,
output_shape,
use_norm=True,
num_input_features=128,
num_filters_down1=[64],
num_filters_down2=[64, 64],
name='SpMiddleFHDV2'):
super(SpMiddleFHDV2, self).__init__()
self.name = name
if use_norm:
BatchNorm2d = change_default_args(eps=1e-3,
momentum=0.01)(nn.BatchNorm2d)
BatchNorm1d = change_default_args(eps=1e-3,
momentum=0.01)(nn.BatchNorm1d)
Conv2d = change_default_args(bias=False)(nn.Conv2d)
SpConv3d = change_default_args(bias=False)(spconv.SparseConv3d)
SubMConv3d = change_default_args(bias=False)(spconv.SubMConv3d)
ConvTranspose2d = change_default_args(bias=False)(
nn.ConvTranspose2d)
else:
BatchNorm2d = Empty
BatchNorm1d = Empty
Conv2d = change_default_args(bias=True)(nn.Conv2d)
SpConv3d = change_default_args(bias=True)(spconv.SparseConv3d)
SubMConv3d = change_default_args(bias=True)(spconv.SubMConv3d)
ConvTranspose2d = change_default_args(bias=True)(
nn.ConvTranspose2d)
sparse_shape = np.array(output_shape[1:4]) + [1, 0, 0]
# sparse_shape[0] = 11
print(sparse_shape)
self.sparse_shape = sparse_shape
self.voxel_output_shape = output_shape
# input: # [1600, 1200, 41]
self.middle_conv = spconv.SparseSequential(
SubMConv3d(num_input_features, 16, 3, indice_key="subm0"),
BatchNorm1d(16),
nn.ReLU(),
SubMConv3d(16, 16, 3, indice_key="subm0"),
BatchNorm1d(16),
nn.ReLU(),
SpConv3d(16, 32, 3, 2,
padding=1), # [1600, 1200, 41] -> [800, 600, 21]
BatchNorm1d(32),
nn.ReLU(),
SubMConv3d(32, 32, 3, indice_key="subm1"),
BatchNorm1d(32),
nn.ReLU(),
SubMConv3d(32, 32, 3, indice_key="subm1"),
BatchNorm1d(32),
nn.ReLU(),
SpConv3d(32, 64, 3, 2,
padding=1), # [800, 600, 21] -> [400, 300, 11]
BatchNorm1d(64),
nn.ReLU(),
SubMConv3d(64, 64, 3, indice_key="subm2"),
BatchNorm1d(64),
nn.ReLU(),
SubMConv3d(64, 64, 3, indice_key="subm2"),
BatchNorm1d(64),
nn.ReLU(),
SubMConv3d(64, 64, 3, indice_key="subm2"),
BatchNorm1d(64),
nn.ReLU(),
SpConv3d(64, 64, 3, 2,
padding=[0, 1, 1]), # [400, 300, 11] -> [200, 150, 5]
BatchNorm1d(64),
nn.ReLU(),
SubMConv3d(64, 64, 3, indice_key="subm3"),
BatchNorm1d(64),
nn.ReLU(),
SubMConv3d(64, 64, 3, indice_key="subm3"),
BatchNorm1d(64),
nn.ReLU(),
SubMConv3d(64, 64, 3, indice_key="subm3"),
BatchNorm1d(64),
nn.ReLU(),
SpConv3d(64, 64, (3, 1, 1),
(2, 1, 1)), # [200, 150, 5] -> [200, 150, 2]
BatchNorm1d(64),
nn.ReLU(),
spconv.SparseMaxPool3d([2, 1, 1]),
)
self.max_batch_size = 6
self.grid = torch.full([self.max_batch_size, *sparse_shape],
-1,
dtype=torch.int32).cuda()
def __init__(
self,
num_point_features, #16
rcnn_cfg, #
**kwargs):
super().__init__(rcnn_target_config=rcnn_cfg.TARGET_CONFIG)
self.SA_modules = nn.ModuleList()
block = self.post_act_block
self.conv_part = spconv.SparseSequential(
block(4, 64, 3, padding=1, indice_key='rcnn_subm1'),
block(64, 64, 3, padding=1, indice_key='rcnn_subm1_1'),
)
self.conv_rpn = spconv.SparseSequential(
block(num_point_features,
64,
3,
padding=1,
indice_key='rcnn_subm2'),
block(64, 64, 3, padding=1, indice_key='rcnn_subm1_2'),
)
self.conv_down = spconv.SparseSequential(
# [14, 14, 14] -> [7, 7, 7]
block(128, 128, 3, padding=1, indice_key='rcnn_subm2'),
block(128, 128, 3, padding=1, indice_key='rcnn_subm2'),
spconv.SparseMaxPool3d(kernel_size=2, stride=2),
block(128, 128, 3, padding=1, indice_key='rcnn_subm3'),
block(128,
rcnn_cfg.SHARED_FC[0],
3,
padding=1,
indice_key='rcnn_subm3'),
)
#首先生成share全连接层,生成三层网络，每一层是1维卷积，
#大概的结构就是1.conv1d->bn->relu->dropout-(512*7*7*7,)->()
# 2.conv1d->bn->relu->dropout-
# 3.conv1d->bn->relu
shared_fc_list = []
pool_size = rcnn_cfg.ROI_AWARE_POOL_SIZE // 2
pre_channel = rcnn_cfg.SHARED_FC[
0] * pool_size * pool_size * pool_size #512*7*7
for k in range(1, rcnn_cfg.SHARED_FC.__len__()):
shared_fc_list.append(
pt_utils.Conv1d(pre_channel, rcnn_cfg.SHARED_FC[k], bn=True))
pre_channel = rcnn_cfg.SHARED_FC[k]
if k != rcnn_cfg.SHARED_FC.__len__() - 1 and rcnn_cfg.DP_RATIO > 0:
shared_fc_list.append(nn.Dropout(rcnn_cfg.DP_RATIO))
self.shared_fc_layer = nn.Sequential(*shared_fc_list)
#share fc layer这一层包含有三层一维度卷积，每一层卷积大概的结构是conv1d->bn->relu->dropout(0.3)
#(256*7*7*7,512)->(512,512)-> (512,512)这是三个卷积层的通道数变化
#生成分类层
#cls_layer包含三层一维卷积，大概的结构是
# (0)conv->bn->relu->dropout(0.3),(512,256)
# (1)conv->bn->relu (256,256)
# (2) conv (256,1)
channel_in = rcnn_cfg.SHARED_FC[-1]
# Classification layer
cls_channel = 1
cls_layers = []
pre_channel = channel_in
for k in range(0, rcnn_cfg.CLS_FC.__len__()):
cls_layers.append(
pt_utils.Conv1d(pre_channel, rcnn_cfg.CLS_FC[k], bn=True))
pre_channel = rcnn_cfg.CLS_FC[k]
cls_layers.append(
pt_utils.Conv1d(pre_channel, cls_channel, activation=None))
if rcnn_cfg.DP_RATIO >= 0:
cls_layers.insert(1, nn.Dropout(rcnn_cfg.DP_RATIO))
self.cls_layer = nn.Sequential(*cls_layers)
#生成回归层
#回归层大概就是
#（0）conv1d->bn->relu (512,256)
#(1)dropout(0.3)
#(2)conv1d->bn->relu (256,256)
# (3)conv1d (256,7)
reg_layers = []
pre_channel = channel_in
for k in range(0, rcnn_cfg.REG_FC.__len__()):
reg_layers.append(
pt_utils.Conv1d(pre_channel, rcnn_cfg.REG_FC[k], bn=True))
pre_channel = rcnn_cfg.REG_FC[k]
reg_layers.append(
pt_utils.Conv1d(pre_channel,
self.box_coder.code_size,
activation=None))
if rcnn_cfg.DP_RATIO >= 0:
reg_layers.insert(1, nn.Dropout(rcnn_cfg.DP_RATIO))
self.reg_layer = nn.Sequential(*reg_layers)
#池化层ROI_AWARE_POOL_SIZE=14
self.roiaware_pool3d_layer = roiaware_pool3d_utils.RoIAwarePool3d(
out_size=rcnn_cfg.ROI_AWARE_POOL_SIZE, max_pts_each_voxel=128)
self.init_weights(weight_init='xavier')
def __init__(self, num_point_features, rcnn_cfg, **kwargs):
super().__init__(rcnn_target_config=cfg.MODEL.RCNN.TARGET_CONFIG)
self.SA_modules = nn.ModuleList()
block = self.post_act_block
self.conv_part = spconv.SparseSequential(
block(4, 64, 3, padding=1, indice_key='rcnn_subm1'),
block(64, 64, 3, padding=1, indice_key='rcnn_subm1_1'),
)
self.conv_rpn = spconv.SparseSequential(
block(num_point_features, 64, 3, padding=1, indice_key='rcnn_subm2'),
block(64, 64, 3, padding=1, indice_key='rcnn_subm1_2'),
)
self.conv_down = spconv.SparseSequential(
# [14, 14, 14] -> [7, 7, 7]
block(128, 128, 3, padding=1, indice_key='rcnn_subm2'),
block(128, 128, 3, padding=1, indice_key='rcnn_subm2'),
spconv.SparseMaxPool3d(kernel_size=2, stride=2),
block(128, 128, 3, padding=1, indice_key='rcnn_subm3'),
block(128, rcnn_cfg.SHARED_FC[0], 3, padding=1, indice_key='rcnn_subm3'),
)
shared_fc_list = []
pool_size = rcnn_cfg.ROI_AWARE_POOL_SIZE // 2
pre_channel = rcnn_cfg.SHARED_FC[0] * pool_size * pool_size * pool_size
for k in range(1, rcnn_cfg.SHARED_FC.__len__()):
shared_fc_list.append(pt_utils.Conv1d(pre_channel, rcnn_cfg.SHARED_FC[k], bn=True))
pre_channel = rcnn_cfg.SHARED_FC[k]
if k != rcnn_cfg.SHARED_FC.__len__() - 1 and rcnn_cfg.DP_RATIO > 0:
shared_fc_list.append(nn.Dropout(rcnn_cfg.DP_RATIO))
self.shared_fc_layer = nn.Sequential(*shared_fc_list)
channel_in = rcnn_cfg.SHARED_FC[-1]
# Classification layer
cls_channel = 1
cls_layers = []
pre_channel = channel_in
for k in range(0, rcnn_cfg.CLS_FC.__len__()):
cls_layers.append(pt_utils.Conv1d(pre_channel, rcnn_cfg.CLS_FC[k], bn=True))
pre_channel = rcnn_cfg.CLS_FC[k]
cls_layers.append(pt_utils.Conv1d(pre_channel, cls_channel, activation=None))
if rcnn_cfg.DP_RATIO >= 0:
cls_layers.insert(1, nn.Dropout(rcnn_cfg.DP_RATIO))
self.cls_layer = nn.Sequential(*cls_layers)
# Regression layer
reg_layers = []
pre_channel = channel_in
for k in range(0, rcnn_cfg.REG_FC.__len__()):
reg_layers.append(pt_utils.Conv1d(pre_channel, rcnn_cfg.REG_FC[k], bn=True))
pre_channel = rcnn_cfg.REG_FC[k]
reg_layers.append(pt_utils.Conv1d(pre_channel, self.box_coder.code_size, activation=None))
if rcnn_cfg.DP_RATIO >= 0:
reg_layers.insert(1, nn.Dropout(rcnn_cfg.DP_RATIO))
self.reg_layer = nn.Sequential(*reg_layers)
self.roiaware_pool3d_layer = roiaware_pool3d_utils.RoIAwarePool3d(
out_size=rcnn_cfg.ROI_AWARE_POOL_SIZE, max_pts_each_voxel=128
)
self.init_weights(weight_init='xavier')