def make_res_layer(block,
inplanes,
planes,
blocks,
stride=1,
dilation=1,
groups=1,
base_width=4,
style='pytorch',
with_cp=False,
conv_cfg=None,
norm_cfg=dict(type='BN'),
dcn=None,
gcb=None,
sac=None,
rfp=None):
downsample = None
if stride != 1 or inplanes != planes * block.expansion:
downsample = nn.Sequential(
build_conv_layer(conv_cfg,
inplanes,
planes * block.expansion,
kernel_size=1,
stride=stride,
bias=False),
build_norm_layer(norm_cfg, planes * block.expansion)[1],
)
layers = []
layers.append(
block(inplanes=inplanes,
planes=planes,
stride=stride,
dilation=dilation,
downsample=downsample,
groups=groups,
base_width=base_width,
style=style,
with_cp=with_cp,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
dcn=dcn,
gcb=gcb,
sac=sac,
rfp=rfp))
inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(
block(inplanes=inplanes,
planes=planes,
stride=1,
dilation=dilation,
groups=groups,
base_width=base_width,
style=style,
with_cp=with_cp,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
dcn=dcn,
gcb=gcb,
sac=sac))
return nn.Sequential(*layers)
def __init__(self,
extra,
in_channels=3,
conv_cfg=None,
norm_cfg=dict(type='BN'),
norm_eval=True,
with_cp=False,
zero_init_residual=False,
with_dcn=None,
with_gcb=None,
dcn=None,
gcb=None):
super(HRNet, self).__init__()
self.extra = extra
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.norm_eval = norm_eval
self.with_cp = with_cp
self.zero_init_residual = zero_init_residual
# stem net
self.norm1_name, norm1 = build_norm_layer(self.norm_cfg, 64, postfix=1)
self.norm2_name, norm2 = build_norm_layer(self.norm_cfg, 64, postfix=2)
self.conv1 = build_conv_layer(self.conv_cfg,
in_channels,
64,
kernel_size=3,
stride=2,
padding=1,
bias=False)
self.add_module(self.norm1_name, norm1)
self.conv2 = build_conv_layer(self.conv_cfg,
64,
64,
kernel_size=3,
stride=2,
padding=1,
bias=False)
self.add_module(self.norm2_name, norm2)
self.relu = nn.ReLU(inplace=True)
# stage 1
self.stage1_cfg = self.extra['stage1']
num_channels = self.stage1_cfg['num_channels'][0]
block_type = self.stage1_cfg['block']
num_blocks = self.stage1_cfg['num_blocks'][0]
block = self.blocks_dict[block_type]
stage1_out_channels = num_channels * block.expansion
self.layer1 = self._make_layer(block, 64, num_channels, num_blocks)
# stage 2
self.stage2_cfg = self.extra['stage2']
num_channels = self.stage2_cfg['num_channels']
block_type = self.stage2_cfg['block']
block = self.blocks_dict[block_type]
num_channels = [channel * block.expansion for channel in num_channels]
self.transition1 = self._make_transition_layer([stage1_out_channels],
num_channels)
self.stage2, pre_stage_channels = self._make_stage(
self.stage2_cfg, num_channels)
# stage 3
self.stage3_cfg = self.extra['stage3']
num_channels = self.stage3_cfg['num_channels']
block_type = self.stage3_cfg['block']
block = self.blocks_dict[block_type]
num_channels = [channel * block.expansion for channel in num_channels]
self.transition2 = self._make_transition_layer(pre_stage_channels,
num_channels)
self.stage3, pre_stage_channels = self._make_stage(
self.stage3_cfg, num_channels)
# stage 4
self.stage4_cfg = self.extra['stage4']
num_channels = self.stage4_cfg['num_channels']
block_type = self.stage4_cfg['block']
block = self.blocks_dict[block_type]
num_channels = [channel * block.expansion for channel in num_channels]
self.transition3 = self._make_transition_layer(pre_stage_channels,
num_channels)
dcn_branches_repeats, gcb_branches_repeats = None, None
if with_dcn is not None:
assert len(with_dcn) == self.stage4_cfg['num_modules']
dcn_branches_repeats = [
[] for _ in range(self.stage4_cfg['num_modules'])
]
for repeatid, dcn_branches in enumerate(with_dcn):
assert len(dcn_branches) == self.stage4_cfg['num_branches']
for use_dcn in dcn_branches:
if use_dcn is False:
dcn_branches_repeats[repeatid].append(None)
else:
assert isinstance(dcn, dict)
dcn_branches_repeats[repeatid].append(dcn)
if with_gcb is not None:
assert len(with_gcb) == self.stage4_cfg['num_modules']
gcb_branches_repeats = [
[] for _ in range(self.stage4_cfg['num_modules'])
]
for repeatid, gcb_branches in enumerate(gcb_branches_repeats):
assert len(gcb_branches) == self.stage4_cfg['num_branches']
for use_gcb in gcb_branches:
if use_gcb is False:
gcb_branches_repeats[repeatid].append(None)
else:
assert isinstance(gcb, dict)
gcb_branches_repeats[repeatid].append(gcb)
self.stage4, pre_stage_channels = self._make_stage(
self.stage4_cfg,
num_channels,
dcn_branches_repeats=dcn_branches_repeats,
gcb_branches_repeats=gcb_branches_repeats) # NOTE
def __init__(self, inplanes, planes, groups=1, base_width=4, **kwargs):
"""Bottleneck block for ResNeXt.
If style is "pytorch", the stride-two layer is the 3x3 conv layer,
if it is "caffe", the stride-two layer is the first 1x1 conv layer.
"""
super(Bottleneck, self).__init__(inplanes, planes, **kwargs)
if groups == 1:
width = self.planes
else:
width = math.floor(self.planes * (base_width / 64)) * groups
self.norm1_name, norm1 = build_norm_layer(self.norm_cfg,
width,
postfix=1)
self.norm2_name, norm2 = build_norm_layer(self.norm_cfg,
width,
postfix=2)
self.norm3_name, norm3 = build_norm_layer(self.norm_cfg,
self.planes * self.expansion,
postfix=3)
self.conv1 = build_conv_layer(self.conv_cfg,
self.inplanes,
width,
kernel_size=1,
stride=self.conv1_stride,
bias=False)
self.add_module(self.norm1_name, norm1)
fallback_on_stride = False
self.with_modulated_dcn = False
if self.with_dcn:
fallback_on_stride = self.dcn.pop('fallback_on_stride', False)
if self.with_sac:
self.conv2 = build_conv_layer(self.sac,
width,
width,
kernel_size=3,
stride=self.conv2_stride,
padding=self.dilation,
dilation=self.dilation,
groups=groups,
bias=False)
elif not self.with_dcn or fallback_on_stride:
self.conv2 = build_conv_layer(self.conv_cfg,
width,
width,
kernel_size=3,
stride=self.conv2_stride,
padding=self.dilation,
dilation=self.dilation,
groups=groups,
bias=False)
else:
assert self.conv_cfg is None, 'conv_cfg must be None for DCN'
self.conv2 = build_conv_layer(self.dcn,
width,
width,
kernel_size=3,
stride=self.conv2_stride,
padding=self.dilation,
dilation=self.dilation,
groups=groups,
bias=False)
self.add_module(self.norm2_name, norm2)
self.conv3 = build_conv_layer(self.conv_cfg,
width,
self.planes * self.expansion,
kernel_size=1,
bias=False)
self.add_module(self.norm3_name, norm3)
def __init__(
self,
extra,
in_channels=3,
conv_cfg=None,
norm_cfg=dict(type="BN"),
norm_eval=True,
with_cp=False,
zero_init_residual=False,
):
super(HRNet, self).__init__()
self.extra = extra
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.norm_eval = norm_eval
self.with_cp = with_cp
self.zero_init_residual = zero_init_residual
# stem net
self.norm1_name, norm1 = build_norm_layer(self.norm_cfg, 64, postfix=1)
self.norm2_name, norm2 = build_norm_layer(self.norm_cfg, 64, postfix=2)
self.conv1 = build_conv_layer(
self.conv_cfg,
in_channels,
64,
kernel_size=3,
stride=2,
padding=1,
bias=False,
)
self.add_module(self.norm1_name, norm1)
self.conv2 = build_conv_layer(self.conv_cfg,
64,
64,
kernel_size=3,
stride=2,
padding=1,
bias=False)
self.add_module(self.norm2_name, norm2)
self.relu = nn.ReLU(inplace=True)
# stage 1
self.stage1_cfg = self.extra["stage1"]
num_channels = self.stage1_cfg["num_channels"][0]
block_type = self.stage1_cfg["block"]
num_blocks = self.stage1_cfg["num_blocks"][0]
block = self.blocks_dict[block_type]
stage1_out_channels = num_channels * block.expansion
self.layer1 = self._make_layer(block, 64, num_channels, num_blocks)
# stage 2
self.stage2_cfg = self.extra["stage2"]
num_channels = self.stage2_cfg["num_channels"]
block_type = self.stage2_cfg["block"]
block = self.blocks_dict[block_type]
num_channels = [channel * block.expansion for channel in num_channels]
self.transition1 = self._make_transition_layer([stage1_out_channels],
num_channels)
self.stage2, pre_stage_channels = self._make_stage(
self.stage2_cfg, num_channels)
# stage 3
self.stage3_cfg = self.extra["stage3"]
num_channels = self.stage3_cfg["num_channels"]
block_type = self.stage3_cfg["block"]
block = self.blocks_dict[block_type]
num_channels = [channel * block.expansion for channel in num_channels]
self.transition2 = self._make_transition_layer(pre_stage_channels,
num_channels)
self.stage3, pre_stage_channels = self._make_stage(
self.stage3_cfg, num_channels)
# stage 4
self.stage4_cfg = self.extra["stage4"]
num_channels = self.stage4_cfg["num_channels"]
block_type = self.stage4_cfg["block"]
block = self.blocks_dict[block_type]
num_channels = [channel * block.expansion for channel in num_channels]
self.transition3 = self._make_transition_layer(pre_stage_channels,
num_channels)
self.stage4, pre_stage_channels = self._make_stage(
self.stage4_cfg, num_channels)
def __init__(self,
inplanes,
planes,
stride=1,
dilation=1,
downsample=None,
style='pytorch',
with_cp=False,
conv_cfg=None,
norm_cfg=dict(type='BN'),
dcn=None,
gcb=None,
gen_attention=None):
# super(BasicBlockPlugins, self).__init__()
super().__init__()
assert not with_cp
self.dcn = dcn
self.with_dcn = dcn is not None
self.gcb = gcb
self.with_gcb = gcb is not None
# self.gen_attention = gen_attention
self.with_gen_attention = gen_attention is not None
self.downsample = downsample
self.stride = stride
self.dilation = dilation
self.norm1_name, norm1 = build_norm_layer(norm_cfg, planes, postfix=1)
self.norm2_name, norm2 = build_norm_layer(norm_cfg, planes, postfix=2)
fallback_on_stride = False
if self.with_dcn:
fallback_on_stride = dcn.pop('fallback_on_stride', False)
if not self.with_dcn or fallback_on_stride:
self.conv1 = build_conv_layer(conv_cfg,
inplanes,
planes,
3,
stride=stride,
padding=dilation,
dilation=dilation,
bias=False)
else:
assert conv_cfg is None
self.conv1 = build_conv_layer(dcn,
inplanes,
planes,
kernel_size=3,
stride=stride,
padding=dilation,
dilation=dilation,
bias=False)
self.add_module(self.norm1_name, norm1)
self.conv2 = build_conv_layer(conv_cfg,
planes,
planes,
3,
padding=1,
bias=False)
self.add_module(self.norm2_name, norm2)
self.relu = nn.ReLU(inplace=True)
if self.with_gcb:
self.context_block = ContextBlock(inplanes=planes, **gcb)
def _make_fuse_layers(self):
if self.num_branches == 1:
return None
num_branches = self.num_branches
in_channels = self.in_channels
fuse_layers = []
num_out_branches = num_branches if self.multiscale_output else 1
for i in range(num_out_branches):
fuse_layer = []
for j in range(num_branches):
if j > i:
fuse_layer.append(
nn.Sequential(
build_conv_layer(
self.conv_cfg,
in_channels[j],
in_channels[i],
kernel_size=1,
stride=1,
padding=0,
bias=False,
),
build_norm_layer(self.norm_cfg, in_channels[i])[1],
nn.Upsample(scale_factor=2**(j - i),
mode="nearest"),
))
elif j == i:
fuse_layer.append(None)
else:
conv_downsamples = []
for k in range(i - j):
if k == i - j - 1:
conv_downsamples.append(
nn.Sequential(
build_conv_layer(
self.conv_cfg,
in_channels[j],
in_channels[i],
kernel_size=3,
stride=2,
padding=1,
bias=False,
),
build_norm_layer(self.norm_cfg,
in_channels[i])[1],
))
else:
conv_downsamples.append(
nn.Sequential(
build_conv_layer(
self.conv_cfg,
in_channels[j],
in_channels[j],
kernel_size=3,
stride=2,
padding=1,
bias=False,
),
build_norm_layer(self.norm_cfg,
in_channels[j])[1],
nn.ReLU(inplace=False),
))
fuse_layer.append(nn.Sequential(*conv_downsamples))
fuse_layers.append(nn.ModuleList(fuse_layer))
return nn.ModuleList(fuse_layers)
def __init__(self,
inplanes,
planes,
stride=1,
dilation=1,
downsample=None,
style='pytorch',
with_cp=False,
conv_cfg=None,
norm_cfg=dict(type='BN'),
dcn=None,
gcb=None,
gen_attention=None):
"""Bottleneck block for ResNet.
If style is "pytorch", the stride-two layer is the 3x3 conv layer,
if it is "caffe", the stride-two layer is the first 1x1 conv layer.
"""
super(Bottleneck, self).__init__()
assert style in ['pytorch', 'caffe']
assert dcn is None or isinstance(dcn, dict)
assert gcb is None or isinstance(gcb, dict)
assert gen_attention is None or isinstance(gen_attention, dict)
self.inplanes = inplanes
self.planes = planes
self.stride = stride
self.dilation = dilation
self.style = style
self.with_cp = with_cp
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.dcn = dcn
self.with_dcn = dcn is not None
self.gcb = gcb
self.with_gcb = gcb is not None
self.gen_attention = gen_attention
self.with_gen_attention = gen_attention is not None
if self.style == 'pytorch':
self.conv1_stride = 1
self.conv2_stride = stride
else:
self.conv1_stride = stride
self.conv2_stride = 1
self.norm1_name, norm1 = build_norm_layer(norm_cfg, planes, postfix=1)
self.norm2_name, norm2 = build_norm_layer(norm_cfg, planes, postfix=2)
self.norm3_name, norm3 = build_norm_layer(norm_cfg,
planes * self.expansion,
postfix=3)
self.conv1 = build_conv_layer(conv_cfg,
inplanes,
planes,
kernel_size=1,
stride=self.conv1_stride,
bias=False)
self.add_module(self.norm1_name, norm1)
fallback_on_stride = False
if self.with_dcn:
fallback_on_stride = dcn.pop('fallback_on_stride', False)
if not self.with_dcn or fallback_on_stride:
self.conv2 = build_conv_layer(conv_cfg,
planes,
planes,
kernel_size=3,
stride=self.conv2_stride,
padding=dilation,
dilation=dilation,
bias=False)
else:
assert self.conv_cfg is None, 'conv_cfg cannot be None for DCN'
self.conv2 = build_conv_layer(dcn,
planes,
planes,
kernel_size=3,
stride=self.conv2_stride,
padding=dilation,
dilation=dilation,
bias=False)
self.add_module(self.norm2_name, norm2)
self.conv3 = build_conv_layer(conv_cfg,
planes,
planes * self.expansion,
kernel_size=1,
bias=False)
self.add_module(self.norm3_name, norm3)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
if self.with_gcb:
gcb_inplanes = planes * self.expansion
self.context_block = ContextBlock(inplanes=gcb_inplanes, **gcb)
# gen_attention
if self.with_gen_attention:
self.gen_attention_block = GeneralizedAttention(
planes, **gen_attention)
def make_res_layer(block,
inplanes,
planes,
blocks,
stride=1,
dilation=1,
style='pytorch',
with_cp=False,
conv_cfg=None,
norm_cfg=dict(type='BN'),
dcn=None,
gcb=None,
gen_attention=None,
gen_attention_blocks=[]):
downsample = None
if stride != 1 or inplanes != planes * block.expansion:
downsample = nn.Sequential(
build_conv_layer(conv_cfg,
inplanes,
planes * block.expansion,
kernel_size=1,
stride=stride,
bias=False),
build_norm_layer(norm_cfg, planes * block.expansion)[1],
)
layers = []
layers.append(
block(inplanes=inplanes,
planes=planes,
stride=stride,
dilation=dilation,
downsample=downsample,
style=style,
with_cp=with_cp,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
dcn=dcn,
gcb=gcb,
gen_attention=gen_attention if
(0 in gen_attention_blocks) else None))
inplanes = planes * block.expansion
for i in range(1, blocks):
dcn1 = None
if dcn is not None:
if i % 3 == 0:
dcn1 = dcn
layers.append(
block(inplanes=inplanes,
planes=planes,
stride=1,
dilation=dilation,
style=style,
with_cp=with_cp,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
dcn=dcn1,
gcb=gcb,
gen_attention=gen_attention if
(i in gen_attention_blocks) else None))
return nn.Sequential(*layers)
def make_res_layer(block,
inplanes,
planes,
blocks,
stride=1,
dilation=1,
style='pytorch',
with_cp=False,
conv_cfg=None,
norm_cfg=dict(type='BN'),
dcn=None,
gcb=None,
gen_attention=None,
gen_attention_blocks=[],
scale=4,
baseWidth=26):
downsample = None
if stride != 1 or inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.AvgPool2d(kernel_size=stride,
stride=stride,
ceil_mode=True,
count_include_pad=False),
build_conv_layer(conv_cfg,
inplanes,
planes * block.expansion,
kernel_size=1,
stride=1,
bias=False),
build_norm_layer(norm_cfg, planes * block.expansion)[1],
)
layers = []
layers.append(
block(inplanes=inplanes,
planes=planes,
stride=stride,
dilation=dilation,
downsample=downsample,
style=style,
with_cp=with_cp,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
dcn=dcn,
gcb=gcb,
gen_attention=gen_attention if
(0 in gen_attention_blocks) else None,
scale=scale,
baseWidth=baseWidth,
stype='stage'))
inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(
block(inplanes=inplanes,
planes=planes,
stride=1,
dilation=dilation,
style=style,
with_cp=with_cp,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
dcn=dcn,
gcb=gcb,
gen_attention=gen_attention if
(i in gen_attention_blocks) else None,
scale=scale,
baseWidth=baseWidth))
return nn.Sequential(*layers)
def __init__(self,
inplanes,
planes,
stride=1,
dilation=1,
downsample=None,
style='pytorch',
with_cp=False,
conv_cfg=None,
norm_cfg=dict(type='BN'),
dcn=None,
gcb=None,
gen_attention=None,
scale=4,
baseWidth=26,
stype='normal'):
"""Bottle2neck block for Res2Net.
If style is "pytorch", the stride-two layer is the 3x3 conv layer,
if it is "caffe", the stride-two layer is the first 1x1 conv layer.
"""
super(Bottle2neck, self).__init__()
assert style in ['pytorch', 'caffe']
assert dcn is None or isinstance(dcn, dict)
assert gcb is None or isinstance(gcb, dict)
assert gen_attention is None or isinstance(gen_attention, dict)
width = int(math.floor(planes * (baseWidth / 64.0)))
self.inplanes = inplanes
self.planes = planes
self.stride = stride
self.dilation = dilation
self.style = style
self.with_cp = with_cp
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.dcn = dcn
self.with_dcn = dcn is not None
self.gcb = gcb
self.with_gcb = gcb is not None
self.gen_attention = gen_attention
self.with_gen_attention = gen_attention is not None
if self.style == 'pytorch':
self.conv1_stride = 1
self.conv2_stride = stride
else:
self.conv1_stride = stride
self.conv2_stride = 1
self.norm1_name, norm1 = build_norm_layer(norm_cfg,
width * scale,
postfix=1)
self.norm3_name, norm3 = build_norm_layer(norm_cfg,
planes * self.expansion,
postfix=3)
self.conv1 = build_conv_layer(conv_cfg,
inplanes,
width * scale,
kernel_size=1,
stride=self.conv1_stride,
bias=False)
self.add_module(self.norm1_name, norm1)
if scale == 1:
self.nums = 1
else:
self.nums = scale - 1
if stype == 'stage':
self.pool = nn.AvgPool2d(kernel_size=3, stride=stride, padding=1)
convs = []
bns = []
fallback_on_stride = False
if self.with_dcn:
fallback_on_stride = dcn.pop('fallback_on_stride', False)
if not self.with_dcn or fallback_on_stride:
for i in range(self.nums):
convs.append(
build_conv_layer(conv_cfg,
width,
width,
kernel_size=3,
stride=self.conv2_stride,
padding=dilation,
dilation=dilation,
bias=False))
bns.append(build_norm_layer(norm_cfg, width, postfix=i + 1)[1])
self.convs = nn.ModuleList(convs)
self.bns = nn.ModuleList(bns)
else:
assert self.conv_cfg is None, 'conv_cfg cannot be None for DCN'
for i in range(self.nums):
convs.append(
build_conv_layer(dcn,
width,
width,
kernel_size=3,
stride=self.conv2_stride,
padding=dilation,
dilation=dilation,
bias=False))
bns.append(build_norm_layer(norm_cfg, width, postfix=i + 1)[1])
self.convs = nn.ModuleList(convs)
self.bns = nn.ModuleList(bns)
self.conv3 = build_conv_layer(conv_cfg,
width * scale,
planes * self.expansion,
kernel_size=1,
bias=False)
self.add_module(self.norm3_name, norm3)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stype = stype
self.scale = scale
self.width = width
if self.with_gcb:
gcb_inplanes = planes * self.expansion
self.context_block = ContextBlock(inplanes=gcb_inplanes, **gcb)
# gen_attention
if self.with_gen_attention:
self.gen_attention_block = GeneralizedAttention(
planes, **gen_attention)
