def _init_layers(self):
self.relu = nn.ReLU(inplace=True)
self.cls_convs = nn.ModuleList()
self.reg_convs = nn.ModuleList()
for i in range(self.stacked_convs):
chn = self.in_channels if i == 0 else self.feat_channels
self.cls_convs.append(
ConvModule(
chn,
self.feat_channels,
3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg))
self.reg_convs.append(
ConvModule(
chn,
self.feat_channels,
3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg))
self.gfl_cls = nn.Conv2d(
self.feat_channels,
self.cls_out_channels,
3,
padding=1)
self.gfl_reg = nn.Conv2d(
self.feat_channels, 4 * (self.reg_max + 1), 3, padding=1)
self.scales = nn.ModuleList([Scale(1.0) for _ in self.anchor_strides])
def _init_layers(self):
self.cls_convs = nn.ModuleList()
self.reg_convs = nn.ModuleList()
for i in range(self.stacked_convs):
chn = self.in_channels if i == 0 else self.feat_channels
self.cls_convs.append(
ConvModule(
chn,
self.feat_channels,
3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
bias=self.norm_cfg is None))
self.reg_convs.append(
ConvModule(
chn,
self.feat_channels,
3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
bias=self.norm_cfg is None))
self.fcos_cls = nn.Conv2d(
self.feat_channels, self.cls_out_channels, 3, padding=1)
self.fcos_reg = nn.Conv2d(self.feat_channels, 4, 3, padding=1)
self.fcos_centerness = nn.Conv2d(self.feat_channels, 1, 3, padding=1)
self.scales = nn.ModuleList([Scale(1.0) for _ in self.strides])
def _init_layers(self):
"""Initialize each of the layers needed."""
self.cls_convs = nn.ModuleList()
self.energy_convs = None if not self.split_convs else nn.ModuleList()
self.reg_convs = nn.ModuleList()
# Create the stacked convolutions
for i in range(self.stacked_convs):
chn = self.in_channels if i == 0 else self.feat_channels
# Make the different convolution stacks
self.cls_convs.append(
ConvModule(chn,
self.feat_channels,
3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
bias=self.norm_cfg is None))
if self.split_convs:
self.energy_convs.append(
ConvModule(chn,
self.feat_channels,
3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
bias=self.norm_cfg is None))
self.reg_convs.append(
ConvModule(chn,
self.feat_channels,
3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
bias=self.norm_cfg is None))
# Classifier convolution
self.wfcos_cls = nn.Conv2d(self.feat_channels,
self.cls_out_channels,
3,
padding=1)
# Bounding box regression convolution
self.wfcos_reg = nn.Conv2d(self.feat_channels, 4, 3, padding=1)
# Energy map convolution
self.wfcos_energy = nn.Conv2d(self.feat_channels,
self.max_energy,
1,
padding=0)
# Scaling factor for the different heads
self.scales = nn.ModuleList([Scale(1.0) for _ in self.strides])
def _init_layers(self):
self.cls_convs = nn.ModuleList()
self.reg_convs = nn.ModuleList()
for i in range(self.stacked_convs-1):
chn = self.in_channels if i == 0 else self.feat_channels
self.cls_convs.append(
ConvModule(
chn,
self.feat_channels,
3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
bias=self.norm_cfg is None))
for i in range(self.stacked_convs):
chn = self.in_channels if i == 0 else self.feat_channels
self.reg_convs.append(
ConvModule(
chn,
self.feat_channels,
3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
bias=self.norm_cfg is None))
self.fcos_cls = nn.Conv2d(
self.feat_channels, self.cls_out_channels, 3, padding=1)
self.fcos_reg = nn.Conv2d(self.feat_channels, 4, 3, padding=1)
self.fcos_centerness = nn.Conv2d(self.feat_channels, 1, 3, padding=1)
self.scales = nn.ModuleList([Scale(1.0) for _ in self.strides])
self.nc = 32
###########instance##############
self.feat_align = FeatureAlign(self.feat_channels, self.feat_channels, 3, flag_norm=self.norm_cfg is not None)
self.sip_cof = nn.Conv2d(self.feat_channels, self.nc*4, 3, padding=1)
self.sip_mask_lat = nn.Conv2d(512, self.nc, 3, padding=1)
self.sip_mask_lat0 = nn.Conv2d(768, 512, 1, padding=0)
if self.rescoring_flag:
self.convs_scoring = []
channels = [1, 16, 16, 16, 32, 64, 128]
for i in range(6):
in_channels = channels[i]
out_channels = channels[i + 1]
stride = 2 if i == 0 else 2
padding = 0
self.convs_scoring.append(
ConvModule(
in_channels, out_channels,
3,
stride=stride,
padding=padding,
bias=True))
self.convs_scoring = nn.Sequential(*self.convs_scoring)
self.mask_scoring = nn.Conv2d(128, self.num_classes-1, 1)
for m in self.convs_scoring:
kaiming_init(m.conv)
normal_init(self.mask_scoring, std=0.001)
self.relu = nn.ReLU(inplace=True)
self.crop_cuda = CropSplit(2)
self.crop_gt_cuda = CropSplitGt(2)
self.init_weights()