def _init_layers(self):
"""Initialize layers of the head."""
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))
assert self.num_anchors == 1, 'anchor free version'
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_generator.strides])
def _init_layers(self):
"""Initialize layers of the head."""
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.retina_cls = nn.Conv2d(
self.feat_channels,
self.num_anchors * self.cls_out_channels,
3,
padding=1)
self.retina_reg = nn.Conv2d(
self.feat_channels, self.num_anchors * 4, 3, padding=1)
def _make_layers(self, out_channels, in_channels=256, feat_channels=256):
"""Initialize conv sequential for CornerHead."""
return nn.Sequential(
ConvModule(in_channels, feat_channels, 3, padding=1),
ConvModule(feat_channels,
out_channels,
1,
norm_cfg=None,
act_cfg=None))
def __init__(self,
downsample_times=5,
num_stacks=2,
stage_channels=(256, 256, 384, 384, 384, 512),
stage_blocks=(2, 2, 2, 2, 2, 4),
feat_channel=256,
norm_cfg=dict(type='BN', requires_grad=True)):
super(HourglassNet, self).__init__()
self.num_stacks = num_stacks
assert self.num_stacks >= 1
assert len(stage_channels) == len(stage_blocks)
assert len(stage_channels) > downsample_times
cur_channel = stage_channels[0]
self.stem = nn.Sequential(
ConvModule(3, 128, 7, padding=3, stride=2, norm_cfg=norm_cfg),
ResLayer(BasicBlock, 128, 256, 1, stride=2, norm_cfg=norm_cfg))
self.hourglass_modules = nn.ModuleList([
HourglassModule(downsample_times, stage_channels, stage_blocks)
for _ in range(num_stacks)
])
self.inters = ResLayer(
BasicBlock,
cur_channel,
cur_channel,
num_stacks - 1,
norm_cfg=norm_cfg)
self.conv1x1s = nn.ModuleList([
ConvModule(
cur_channel, cur_channel, 1, norm_cfg=norm_cfg, act_cfg=None)
for _ in range(num_stacks - 1)
])
self.out_convs = nn.ModuleList([
ConvModule(
cur_channel, feat_channel, 3, padding=1, norm_cfg=norm_cfg)
for _ in range(num_stacks)
])
self.remap_convs = nn.ModuleList([
ConvModule(
feat_channel, cur_channel, 1, norm_cfg=norm_cfg, act_cfg=None)
for _ in range(num_stacks - 1)
])
self.relu = nn.ReLU(inplace=True)
def _init_layers(self):
"""Initialize layers of the head."""
self.relu = nn.ReLU(inplace=True)
self.cls_convs = nn.ModuleList()
self.reg_convs = nn.ModuleList()
# 常规4层卷积堆叠
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.num_points表示9个语义点
# 如果use_grid_points，则表示学习delta xywh模式
pts_out_dim = 4 if self.use_grid_points else 2 * self.num_points
# 分类分支的dcn
self.reppoints_cls_conv = DeformConv2d(self.feat_channels,
self.point_feat_channels,
self.dcn_kernel, 1,
self.dcn_pad)
# 分类分支输出
self.reppoints_cls_out = nn.Conv2d(self.point_feat_channels,
self.cls_out_channels, 1, 1, 0)
# 第一次回归
self.reppoints_pts_init_conv = nn.Conv2d(self.feat_channels,
self.point_feat_channels, 3,
1, 1)
# 第一次回归的点位置输出，每个位置都要输出pts_out_dim
self.reppoints_pts_init_out = nn.Conv2d(self.point_feat_channels,
pts_out_dim, 1, 1, 0)
# 点回归分支的dcn
self.reppoints_pts_refine_conv = DeformConv2d(self.feat_channels,
self.point_feat_channels,
self.dcn_kernel, 1,
self.dcn_pad)
# 最终回归点输出
self.reppoints_pts_refine_out = nn.Conv2d(self.point_feat_channels,
pts_out_dim, 1, 1, 0)
def __init__(self,
in_channels,
num_levels,
refine_level=2,
refine_type=None,
conv_cfg=None,
norm_cfg=None):
super(BFP, self).__init__()
assert refine_type in [None, 'conv', 'non_local']
self.in_channels = in_channels
self.num_levels = num_levels
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.refine_level = refine_level
self.refine_type = refine_type
assert 0 <= self.refine_level < self.num_levels
if self.refine_type == 'conv':
self.refine = ConvModule(self.in_channels,
self.in_channels,
3,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg)
elif self.refine_type == 'non_local':
self.refine = NonLocal2d(self.in_channels,
reduction=1,
use_scale=False,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg)
def __init__(self,
depth=53,
out_indices=(3, 4, 5),
frozen_stages=-1,
conv_cfg=None,
norm_cfg=dict(type='BN', requires_grad=True),
act_cfg=dict(type='LeakyReLU', negative_slope=0.1),
norm_eval=True):
super(Darknet, self).__init__()
if depth not in self.arch_settings:
raise KeyError(f'invalid depth {depth} for darknet')
self.depth = depth
self.out_indices = out_indices
self.frozen_stages = frozen_stages
self.layers, self.channels = self.arch_settings[depth]
cfg = dict(conv_cfg=conv_cfg, norm_cfg=norm_cfg, act_cfg=act_cfg)
self.conv1 = ConvModule(3, 32, 3, padding=1, **cfg)
self.cr_blocks = ['conv1']
for i, n_layers in enumerate(self.layers):
layer_name = f'conv_res_block{i + 1}'
in_c, out_c = self.channels[i]
self.add_module(
layer_name,
self.make_conv_res_block(in_c, out_c, n_layers, **cfg))
self.cr_blocks.append(layer_name)
self.norm_eval = norm_eval
def __init__(self,
num_scales,
in_channels,
out_channels,
conv_cfg=None,
norm_cfg=dict(type='BN', requires_grad=True),
act_cfg=dict(type='LeakyReLU', negative_slope=0.1)):
super(YOLOV3Neck, self).__init__()
assert (num_scales == len(in_channels) == len(out_channels))
self.num_scales = num_scales
self.in_channels = in_channels
self.out_channels = out_channels
# shortcut
cfg = dict(conv_cfg=conv_cfg, norm_cfg=norm_cfg, act_cfg=act_cfg)
# To support arbitrary scales, the code looks awful, but it works.
# Better solution is welcomed.
self.detect1 = DetectionBlock(in_channels[0], out_channels[0], **cfg)
for i in range(1, self.num_scales):
in_c, out_c = self.in_channels[i], self.out_channels[i]
self.add_module(f'conv{i}', ConvModule(in_c, out_c, 1, **cfg))
# in_c + out_c : High-lvl feats will be cat with low-lvl feats
self.add_module(f'detect{i+1}',
DetectionBlock(in_c + out_c, out_c, **cfg))
def _init_layers(self):
"""Initialize layers of the head."""
super(FCOSHead, self)._init_cls_convs()
super(FCOSHead, self)._init_reg_convs()
self.relu = nn.ReLU(inplace=True)
self.vfnet_reg_conv = ConvModule(self.feat_channels,
self.feat_channels,
3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
bias=self.conv_bias)
self.vfnet_reg = nn.Conv2d(self.feat_channels, 4, 3, padding=1)
self.scales = nn.ModuleList([Scale(1.0) for _ in self.strides])
self.vfnet_reg_refine_dconv = DeformConv2d(self.feat_channels,
self.feat_channels,
self.dcn_kernel,
1,
padding=self.dcn_pad)
self.vfnet_reg_refine = nn.Conv2d(self.feat_channels, 4, 3, padding=1)
self.scales_refine = nn.ModuleList([Scale(1.0) for _ in self.strides])
self.vfnet_cls_dconv = DeformConv2d(self.feat_channels,
self.feat_channels,
self.dcn_kernel,
1,
padding=self.dcn_pad)
self.vfnet_cls = nn.Conv2d(self.feat_channels,
self.cls_out_channels,
3,
padding=1)
def _init_layers(self):
"""Initialize layers of the head."""
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.conv_loc = nn.Conv2d(self.feat_channels, 1, 1)
self.conv_shape = nn.Conv2d(self.feat_channels, self.num_anchors * 2,
1)
self.feature_adaption_cls = FeatureAdaption(
self.feat_channels,
self.feat_channels,
kernel_size=3,
deform_groups=self.deform_groups)
self.feature_adaption_reg = FeatureAdaption(
self.feat_channels,
self.feat_channels,
kernel_size=3,
deform_groups=self.deform_groups)
self.retina_cls = MaskedConv2d(
self.feat_channels,
self.num_anchors * self.cls_out_channels,
3,
padding=1)
self.retina_reg = MaskedConv2d(
self.feat_channels, self.num_anchors * 4, 3, padding=1)
def __init__(self,
in_channels,
conv_cfg=None,
norm_cfg=dict(type='BN', requires_grad=True),
act_cfg=dict(type='LeakyReLU', negative_slope=0.1)):
super(ResBlock, self).__init__()
assert in_channels % 2 == 0 # ensure the in_channels is even
half_in_channels = in_channels // 2
# shortcut
cfg = dict(conv_cfg=conv_cfg, norm_cfg=norm_cfg, act_cfg=act_cfg)
self.conv1 = ConvModule(in_channels, half_in_channels, 1, **cfg)
self.conv2 = ConvModule(half_in_channels,
in_channels,
3,
padding=1,
**cfg)
def __init__(self,
in_channels,
out_channels,
conv_cfg=None,
norm_cfg=dict(type='BN', requires_grad=True),
act_cfg=dict(type='LeakyReLU', negative_slope=0.1)):
super(DetectionBlock, self).__init__()
double_out_channels = out_channels * 2
# shortcut
cfg = dict(conv_cfg=conv_cfg, norm_cfg=norm_cfg, act_cfg=act_cfg)
self.conv1 = ConvModule(in_channels, out_channels, 1, **cfg)
self.conv2 = ConvModule(
out_channels, double_out_channels, 3, padding=1, **cfg)
self.conv3 = ConvModule(double_out_channels, out_channels, 1, **cfg)
self.conv4 = ConvModule(
out_channels, double_out_channels, 3, padding=1, **cfg)
self.conv5 = ConvModule(double_out_channels, out_channels, 1, **cfg)
def _init_layers(self):
"""Initialize layers of the head."""
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))
pts_out_dim = 4 if self.use_grid_points else 2 * self.num_points
self.reppoints_cls_conv = DeformConv2d(self.feat_channels,
self.point_feat_channels,
self.dcn_kernel, 1,
self.dcn_pad)
self.reppoints_cls_out = nn.Conv2d(self.point_feat_channels,
self.cls_out_channels, 1, 1, 0)
self.reppoints_pts_init_conv = nn.Conv2d(self.feat_channels,
self.point_feat_channels, 3,
1, 1)
self.reppoints_pts_init_out = nn.Conv2d(self.point_feat_channels,
pts_out_dim, 1, 1, 0)
self.reppoints_pts_refine_conv = DeformConv2d(self.feat_channels,
self.point_feat_channels,
self.dcn_kernel, 1,
self.dcn_pad)
self.reppoints_pts_refine_out = nn.Conv2d(self.point_feat_channels,
pts_out_dim, 1, 1, 0)
def __init__(self,
in_channels,
directions,
feat_channels=128,
out_channels=128,
norm_cfg=dict(type='BN', requires_grad=True)):
super(BiCornerPool, self).__init__()
self.direction1_conv = ConvModule(in_channels,
feat_channels,
3,
padding=1,
norm_cfg=norm_cfg)
self.direction2_conv = ConvModule(in_channels,
feat_channels,
3,
padding=1,
norm_cfg=norm_cfg)
self.aftpool_conv = ConvModule(feat_channels,
out_channels,
3,
padding=1,
norm_cfg=norm_cfg,
act_cfg=None)
self.conv1 = ConvModule(in_channels,
out_channels,
1,
norm_cfg=norm_cfg,
act_cfg=None)
self.conv2 = ConvModule(in_channels,
out_channels,
3,
padding=1,
norm_cfg=norm_cfg)
self.direction1_pool = CornerPool(directions[0])
self.direction2_pool = CornerPool(directions[1])
self.relu = nn.ReLU(inplace=True)
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.retina_cls = nn.Conv2d(self.feat_channels,
self.cls_out_channels,
3,
padding=1)
# 分别精细回归4条边和gt bbox的4条边距离，每条边距离回归分成self.side_num个桶
self.retina_bbox_reg = nn.Conv2d(self.feat_channels,
self.side_num * 4,
3,
padding=1)
# 先采用分类做法判断落在哪个桶，然后利用retina_bbox_reg进行精细数值回归
self.retina_bbox_cls = nn.Conv2d(self.feat_channels,
self.side_num * 4,
3,
padding=1)
def _init_layers(self):
self.convs_bridge = nn.ModuleList()
self.convs_pred = nn.ModuleList()
for i in range(self.num_levels):
conv_bridge = ConvModule(self.in_channels[i],
self.out_channels[i],
3,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
conv_pred = nn.Conv2d(self.out_channels[i],
self.num_anchors * self.num_attrib, 1)
self.convs_bridge.append(conv_bridge)
self.convs_pred.append(conv_pred)
def _init_reg_convs(self):
"""Initialize bbox regression conv layers of the head."""
self.reg_convs = nn.ModuleList()
for i in range(self.stacked_convs):
chn = self.in_channels if i == 0 else self.feat_channels
if self.dcn_on_last_conv and i == self.stacked_convs - 1:
conv_cfg = dict(type='DCNv2')
else:
conv_cfg = self.conv_cfg
self.reg_convs.append(
ConvModule(chn,
self.feat_channels,
3,
stride=1,
padding=1,
conv_cfg=conv_cfg,
norm_cfg=self.norm_cfg,
bias=self.conv_bias))
def make_conv_res_block(in_channels,
out_channels,
res_repeat,
conv_cfg=None,
norm_cfg=dict(type='BN', requires_grad=True),
act_cfg=dict(type='LeakyReLU',
negative_slope=0.1)):
"""In Darknet backbone, ConvLayer is usually followed by ResBlock. This
function will make that. The Conv layers always have 3x3 filters with
stride=2. The number of the filters in Conv layer is the same as the
out channels of the ResBlock.
Args:
in_channels (int): The number of input channels.
out_channels (int): The number of output channels.
res_repeat (int): The number of ResBlocks.
conv_cfg (dict): Config dict for convolution layer. Default: None.
norm_cfg (dict): Dictionary to construct and config norm layer.
Default: dict(type='BN', requires_grad=True)
act_cfg (dict): Config dict for activation layer.
Default: dict(type='LeakyReLU', negative_slope=0.1).
"""
cfg = dict(conv_cfg=conv_cfg, norm_cfg=norm_cfg, act_cfg=act_cfg)
model = nn.Sequential()
model.add_module(
'conv',
ConvModule(in_channels,
out_channels,
3,
stride=2,
padding=1,
**cfg))
for idx in range(res_repeat):
model.add_module('res{}'.format(idx),
ResBlock(out_channels, **cfg))
return model
def __init__(
self,
in_channels,
out_channels,
num_outs, # 输出层个数
start_level=0, # fpn开始层
end_level=-1, # fpn结束层，用于挑选对应的特征图层进行fpn操作
add_extra_convs=False,
extra_convs_on_inputs=True,
relu_before_extra_convs=False,
no_norm_on_lateral=False,
conv_cfg=None,
norm_cfg=None,
act_cfg=None,
upsample_cfg=dict(mode='nearest')):
super(FPN, self).__init__()
assert isinstance(in_channels, list)
self.in_channels = in_channels
self.out_channels = out_channels
self.num_ins = len(in_channels)
self.num_outs = num_outs
self.relu_before_extra_convs = relu_before_extra_convs
self.no_norm_on_lateral = no_norm_on_lateral
self.fp16_enabled = False
self.upsample_cfg = upsample_cfg.copy()
if end_level == -1:
self.backbone_end_level = self.num_ins
assert num_outs >= self.num_ins - start_level
else:
# if end_level < inputs, no extra level is allowed
self.backbone_end_level = end_level
assert end_level <= len(in_channels)
assert num_outs == end_level - start_level
self.start_level = start_level
self.end_level = end_level
self.add_extra_convs = add_extra_convs
assert isinstance(add_extra_convs, (str, bool))
if isinstance(add_extra_convs, str):
# Extra_convs_source choices: 'on_input', 'on_lateral', 'on_output'
assert add_extra_convs in ('on_input', 'on_lateral', 'on_output')
elif add_extra_convs: # True
if extra_convs_on_inputs:
# For compatibility with previous release
# TODO: deprecate `extra_convs_on_inputs`
self.add_extra_convs = 'on_input'
else:
self.add_extra_convs = 'on_output'
self.lateral_convs = nn.ModuleList()
self.fpn_convs = nn.ModuleList()
for i in range(self.start_level, self.backbone_end_level):
l_conv = ConvModule(
in_channels[i],
out_channels,
1,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg if not self.no_norm_on_lateral else None,
act_cfg=act_cfg,
inplace=False) # 中间层
fpn_conv = ConvModule(out_channels,
out_channels,
3,
padding=1,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
inplace=False) # 输出层
self.lateral_convs.append(l_conv)
self.fpn_convs.append(fpn_conv)
# add extra conv layers (e.g., RetinaNet)
extra_levels = num_outs - self.backbone_end_level + self.start_level
if self.add_extra_convs and extra_levels >= 1:
for i in range(extra_levels):
if i == 0 and self.add_extra_convs == 'on_input':
in_channels = self.in_channels[self.backbone_end_level - 1]
else:
in_channels = out_channels
# 额外卷积层得到的下采样都是通过3x3 s=2获得，都没有BN
extra_fpn_conv = ConvModule(in_channels,
out_channels,
3,
stride=2,
padding=1,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
inplace=False)
self.fpn_convs.append(extra_fpn_conv)
def __init__(self,
num_classes,
cls_in_channels=256,
reg_in_channels=256,
roi_feat_size=7,
reg_feat_up_ratio=2,
reg_pre_kernel=3,
reg_post_kernel=3,
reg_pre_num=2,
reg_post_num=1,
cls_out_channels=1024,
reg_offset_out_channels=256,
reg_cls_out_channels=256,
num_cls_fcs=1,
num_reg_fcs=0,
reg_class_agnostic=True,
norm_cfg=None,
bbox_coder=dict(type='BucketingBBoxCoder',
num_buckets=14,
scale_factor=1.7),
loss_cls=dict(type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox_cls=dict(type='CrossEntropyLoss',
use_sigmoid=True,
loss_weight=1.0),
loss_bbox_reg=dict(type='SmoothL1Loss',
beta=0.1,
loss_weight=1.0)):
super(SABLHead, self).__init__()
self.cls_in_channels = cls_in_channels
self.reg_in_channels = reg_in_channels
self.roi_feat_size = roi_feat_size
self.reg_feat_up_ratio = int(reg_feat_up_ratio)
self.num_buckets = bbox_coder['num_buckets']
assert self.reg_feat_up_ratio // 2 >= 1
self.up_reg_feat_size = roi_feat_size * self.reg_feat_up_ratio
assert self.up_reg_feat_size == bbox_coder['num_buckets']
self.reg_pre_kernel = reg_pre_kernel
self.reg_post_kernel = reg_post_kernel
self.reg_pre_num = reg_pre_num
self.reg_post_num = reg_post_num
self.num_classes = num_classes
self.cls_out_channels = cls_out_channels
self.reg_offset_out_channels = reg_offset_out_channels
self.reg_cls_out_channels = reg_cls_out_channels
self.num_cls_fcs = num_cls_fcs
self.num_reg_fcs = num_reg_fcs
self.reg_class_agnostic = reg_class_agnostic
assert self.reg_class_agnostic
self.norm_cfg = norm_cfg
self.bbox_coder = build_bbox_coder(bbox_coder)
self.loss_cls = build_loss(loss_cls)
self.loss_bbox_cls = build_loss(loss_bbox_cls)
self.loss_bbox_reg = build_loss(loss_bbox_reg)
self.cls_fcs = self._add_fc_branch(self.num_cls_fcs,
self.cls_in_channels,
self.roi_feat_size,
self.cls_out_channels)
self.side_num = int(np.ceil(self.num_buckets / 2))
if self.reg_feat_up_ratio > 1:
self.upsample_x = nn.ConvTranspose1d(reg_in_channels,
reg_in_channels,
self.reg_feat_up_ratio,
stride=self.reg_feat_up_ratio)
self.upsample_y = nn.ConvTranspose1d(reg_in_channels,
reg_in_channels,
self.reg_feat_up_ratio,
stride=self.reg_feat_up_ratio)
self.reg_pre_convs = nn.ModuleList()
for i in range(self.reg_pre_num):
reg_pre_conv = ConvModule(reg_in_channels,
reg_in_channels,
kernel_size=reg_pre_kernel,
padding=reg_pre_kernel // 2,
norm_cfg=norm_cfg,
act_cfg=dict(type='ReLU'))
self.reg_pre_convs.append(reg_pre_conv)
self.reg_post_conv_xs = nn.ModuleList()
for i in range(self.reg_post_num):
reg_post_conv_x = ConvModule(reg_in_channels,
reg_in_channels,
kernel_size=(1, reg_post_kernel),
padding=(0, reg_post_kernel // 2),
norm_cfg=norm_cfg,
act_cfg=dict(type='ReLU'))
self.reg_post_conv_xs.append(reg_post_conv_x)
self.reg_post_conv_ys = nn.ModuleList()
for i in range(self.reg_post_num):
reg_post_conv_y = ConvModule(reg_in_channels,
reg_in_channels,
kernel_size=(reg_post_kernel, 1),
padding=(reg_post_kernel // 2, 0),
norm_cfg=norm_cfg,
act_cfg=dict(type='ReLU'))
self.reg_post_conv_ys.append(reg_post_conv_y)
self.reg_conv_att_x = nn.Conv2d(reg_in_channels, 1, 1)
self.reg_conv_att_y = nn.Conv2d(reg_in_channels, 1, 1)
self.fc_cls = nn.Linear(self.cls_out_channels, self.num_classes + 1)
self.relu = nn.ReLU(inplace=True)
self.reg_cls_fcs = self._add_fc_branch(self.num_reg_fcs,
self.reg_in_channels, 1,
self.reg_cls_out_channels)
self.reg_offset_fcs = self._add_fc_branch(self.num_reg_fcs,
self.reg_in_channels, 1,
self.reg_offset_out_channels)
self.fc_reg_cls = nn.Linear(self.reg_cls_out_channels, 1)
self.fc_reg_offset = nn.Linear(self.reg_offset_out_channels, 1)