well its 3 part network I put in order down below and input shape is (3,320,800)
backbone
import torch
from torch import nn
import torch.nn.functional as F
from torch.hub import load_state_dict_from_url
from clrnet.models.registry import BACKBONES
model_urls = {
'resnet18':
'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet34':
'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
'resnet50':
'https://download.pytorch.org/models/resnet50-19c8e357.pth',
'resnet101':
'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
'resnet152':
'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
'resnext50_32x4d':
'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
'resnext101_32x8d':
'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
'wide_resnet50_2':
'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth',
'wide_resnet101_2':
'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth',
}
def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
"""3x3 convolution with padding"""
return nn.Conv2d(in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=dilation,
groups=groups,
bias=False,
dilation=dilation)
def conv1x1(in_planes, out_planes, stride=1):
"""1x1 convolution"""
return nn.Conv2d(in_planes,
out_planes,
kernel_size=1,
stride=stride,
bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self,
inplanes,
planes,
stride=1,
downsample=None,
groups=1,
base_width=64,
dilation=1,
norm_layer=None):
super(BasicBlock, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
if groups != 1 or base_width != 64:
raise ValueError(
'BasicBlock only supports groups=1 and base_width=64')
# if dilation > 1:
# raise NotImplementedError(
# "Dilation > 1 not supported in BasicBlock")
# Both self.conv1 and self.downsample layers downsample the input when stride != 1
self.conv1 = conv3x3(inplanes, planes, stride, dilation=dilation)
self.bn1 = norm_layer(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes, dilation=dilation)
self.bn2 = norm_layer(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class Bottleneck(nn.Module):
expansion = 4
def __init__(self,
inplanes,
planes,
stride=1,
downsample=None,
groups=1,
base_width=64,
dilation=1,
norm_layer=None):
super(Bottleneck, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
width = int(planes * (base_width / 64.)) * groups
# Both self.conv2 and self.downsample layers downsample the input when stride != 1
self.conv1 = conv1x1(inplanes, width)
self.bn1 = norm_layer(width)
self.conv2 = conv3x3(width, width, stride, groups, dilation)
self.bn2 = norm_layer(width)
self.conv3 = conv1x1(width, planes * self.expansion)
self.bn3 = norm_layer(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
@BACKBONES.register_module
class ResNetWrapper(nn.Module):
def __init__(self,
resnet='resnet18',
pretrained=True,
replace_stride_with_dilation=[False, False, False],
out_conv=False,
fea_stride=8,
out_channel=128,
in_channels=[64, 128, 256, 512],
cfg=None):
super(ResNetWrapper, self).__init__()
self.cfg = cfg
self.in_channels = in_channels
self.model = eval(resnet)(
pretrained=pretrained,
replace_stride_with_dilation=replace_stride_with_dilation,
in_channels=self.in_channels)
self.out = None
if out_conv:
out_channel = 512
for chan in reversed(self.in_channels):
if chan < 0: continue
out_channel = chan
break
self.out = conv1x1(out_channel * self.model.expansion,
cfg.featuremap_out_channel)
def forward(self, x):
x = self.model(x)
if self.out:
x[-1] = self.out(x[-1])
return x
class ResNet(nn.Module):
def __init__(self,
block,
layers,
zero_init_residual=False,
groups=1,
width_per_group=64,
replace_stride_with_dilation=None,
norm_layer=None,
in_channels=None):
super(ResNet, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
self._norm_layer = norm_layer
self.inplanes = 64
self.dilation = 1
if replace_stride_with_dilation is None:
# each element in the tuple indicates if we should replace
# the 2x2 stride with a dilated convolution instead
replace_stride_with_dilation = [False, False, False]
if len(replace_stride_with_dilation) != 3:
raise ValueError("replace_stride_with_dilation should be None "
"or a 3-element tuple, got {}".format(
replace_stride_with_dilation))
self.groups = groups
self.base_width = width_per_group
self.conv1 = nn.Conv2d(3,
self.inplanes,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = norm_layer(self.inplanes)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.in_channels = in_channels
self.layer1 = self._make_layer(block, in_channels[0], layers[0])
self.layer2 = self._make_layer(block,
in_channels[1],
layers[1],
stride=2,
dilate=replace_stride_with_dilation[0])
self.layer3 = self._make_layer(block,
in_channels[2],
layers[2],
stride=2,
dilate=replace_stride_with_dilation[1])
if in_channels[3] > 0:
self.layer4 = self._make_layer(
block,
in_channels[3],
layers[3],
stride=2,
dilate=replace_stride_with_dilation[2])
self.expansion = block.expansion
# self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
# self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight,
mode='fan_out',
nonlinearity='relu')
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
norm_layer = self._norm_layer
downsample = None
previous_dilation = self.dilation
if dilate:
self.dilation *= stride
stride = 1
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
norm_layer(planes * block.expansion),
)
layers = []
layers.append(
block(self.inplanes, planes, stride, downsample, self.groups,
self.base_width, previous_dilation, norm_layer))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(
block(self.inplanes,
planes,
groups=self.groups,
base_width=self.base_width,
dilation=self.dilation,
norm_layer=norm_layer))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
out_layers = []
for name in ['layer1', 'layer2', 'layer3', 'layer4']:
if not hasattr(self, name):
continue
layer = getattr(self, name)
x = layer(x)
out_layers.append(x)
return out_layers
def _resnet(arch, block, layers, pretrained, progress, **kwargs):
model = ResNet(block, layers, **kwargs)
if pretrained:
print('pretrained model: ', model_urls[arch])
# state_dict = torch.load(model_urls[arch])['net']
state_dict = load_state_dict_from_url(model_urls[arch])
model.load_state_dict(state_dict, strict=False)
return model
def resnet18(pretrained=False, progress=True, **kwargs):
r"""ResNet-18 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet('resnet18', BasicBlock, [2, 2, 2, 2], pretrained, progress,
**kwargs)
def resnet34(pretrained=False, progress=True, **kwargs):
r"""ResNet-34 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet('resnet34', BasicBlock, [3, 4, 6, 3], pretrained, progress,
**kwargs)
def resnet50(pretrained=False, progress=True, **kwargs):
r"""ResNet-50 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, progress,
**kwargs)
def resnet101(pretrained=False, progress=True, **kwargs):
r"""ResNet-101 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet('resnet101', Bottleneck, [3, 4, 23, 3], pretrained,
progress, **kwargs)
def resnet152(pretrained=False, progress=True, **kwargs):
r"""ResNet-152 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet('resnet152', Bottleneck, [3, 8, 36, 3], pretrained,
progress, **kwargs)
def resnext50_32x4d(pretrained=False, progress=True, **kwargs):
r"""ResNeXt-50 32x4d model from
`"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs['groups'] = 32
kwargs['width_per_group'] = 4
return _resnet('resnext50_32x4d', Bottleneck, [3, 4, 6, 3], pretrained,
progress, **kwargs)
def resnext101_32x8d(pretrained=False, progress=True, **kwargs):
r"""ResNeXt-101 32x8d model from
`"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs['groups'] = 32
kwargs['width_per_group'] = 8
return _resnet('resnext101_32x8d', Bottleneck, [3, 4, 23, 3], pretrained,
progress, **kwargs)
def wide_resnet50_2(pretrained=False, progress=True, **kwargs):
r"""Wide ResNet-50-2 model from
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
The model is the same as ResNet except for the bottleneck number of channels
which is twice larger in every block. The number of channels in outer 1x1
convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
channels, and in Wide ResNet-50-2 has 2048-1024-2048.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs['width_per_group'] = 64 * 2
return _resnet('wide_resnet50_2', Bottleneck, [3, 4, 6, 3], pretrained,
progress, **kwargs)
def wide_resnet101_2(pretrained=False, progress=True, **kwargs):
r"""Wide ResNet-101-2 model from
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
The model is the same as ResNet except for the bottleneck number of channels
which is twice larger in every block. The number of channels in outer 1x1
convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
channels, and in Wide ResNet-50-2 has 2048-1024-2048.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs['width_per_group'] = 64 * 2
return _resnet('wide_resnet101_2', Bottleneck, [3, 4, 23, 3], pretrained,
progress, **kwargs)
neck which is FPN network
import warnings
import torch
import torch.nn as nn
import torch.nn.functional as F
from mmcv.cnn import ConvModule
from ..registry import NECKS
@NECKS.register_module
class FPN(nn.Module):
def __init__(self,
in_channels,
out_channels,
num_outs,
start_level=0,
end_level=-1,
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,
attention=False,
act_cfg=None,
upsample_cfg=dict(mode='nearest'),
init_cfg=dict(type='Xavier',
layer='Conv2d',
distribution='uniform'),
cfg=None):
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.attention = attention
self.relu_before_extra_convs = relu_before_extra_convs
self.no_norm_on_lateral = no_norm_on_lateral
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:
# TODO: deprecate `extra_convs_on_inputs`
warnings.simplefilter('once')
warnings.warn(
'"extra_convs_on_inputs" will be deprecated in v2.9.0,'
'Please use "add_extra_convs"', DeprecationWarning)
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)
fpn_conv = ConvModule(out_channels,
out_channels,
3,
padding=1,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
inplace=False)
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
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 forward(self, inputs):
"""Forward function."""
assert len(inputs) >= len(self.in_channels)
if len(inputs) > len(self.in_channels):
for _ in range(len(inputs) - len(self.in_channels)):
del inputs[0]
# build laterals
laterals = [
lateral_conv(inputs[i + self.start_level])
for i, lateral_conv in enumerate(self.lateral_convs)
]
# build top-down path
used_backbone_levels = len(laterals)
for i in range(used_backbone_levels - 1, 0, -1):
# In some cases, fixing `scale factor` (e.g. 2) is preferred, but
# it cannot co-exist with `size` in `F.interpolate`.
if 'scale_factor' in self.upsample_cfg:
laterals[i - 1] += F.interpolate(laterals[i],
**self.upsample_cfg)
else:
prev_shape = laterals[i - 1].shape[2:]
laterals[i - 1] += F.interpolate(laterals[i],
size=prev_shape,
**self.upsample_cfg)
# build outputs
# part 1: from original levels
outs = [
self.fpn_convs[i](laterals[i]) for i in range(used_backbone_levels)
]
# part 2: add extra levels
if self.num_outs > len(outs):
# use max pool to get more levels on top of outputs
# (e.g., Faster R-CNN, Mask R-CNN)
if not self.add_extra_convs:
for i in range(self.num_outs - used_backbone_levels):
outs.append(F.max_pool2d(outs[-1], 1, stride=2))
# add conv layers on top of original feature maps (RetinaNet)
else:
if self.add_extra_convs == 'on_input':
extra_source = inputs[self.backbone_end_level - 1]
elif self.add_extra_convs == 'on_lateral':
extra_source = laterals[-1]
elif self.add_extra_convs == 'on_output':
extra_source = outs[-1]
else:
raise NotImplementedError
outs.append(self.fpn_convs[used_backbone_levels](extra_source))
for i in range(used_backbone_levels + 1, self.num_outs):
if self.relu_before_extra_convs:
outs.append(self.fpn_convs[i](F.relu(outs[-1])))
else:
outs.append(self.fpn_convs[i](outs[-1]))
return tuple(outs)
and head
import warnings
import torch
import torch.nn as nn
import torch.nn.functional as F
from mmcv.cnn import ConvModule
from ..registry import NECKS
@NECKS.register_module
class FPN(nn.Module):
def __init__(self,
in_channels,
out_channels,
num_outs,
start_level=0,
end_level=-1,
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,
attention=False,
act_cfg=None,
upsample_cfg=dict(mode='nearest'),
init_cfg=dict(type='Xavier',
layer='Conv2d',
distribution='uniform'),
cfg=None):
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.attention = attention
self.relu_before_extra_convs = relu_before_extra_convs
self.no_norm_on_lateral = no_norm_on_lateral
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:
# TODO: deprecate `extra_convs_on_inputs`
warnings.simplefilter('once')
warnings.warn(
'"extra_convs_on_inputs" will be deprecated in v2.9.0,'
'Please use "add_extra_convs"', DeprecationWarning)
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)
fpn_conv = ConvModule(out_channels,
out_channels,
3,
padding=1,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
inplace=False)
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
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 forward(self, inputs):
"""Forward function."""
assert len(inputs) >= len(self.in_channels)
if len(inputs) > len(self.in_channels):
for _ in range(len(inputs) - len(self.in_channels)):
del inputs[0]
# build laterals
laterals = [
lateral_conv(inputs[i + self.start_level])
for i, lateral_conv in enumerate(self.lateral_convs)
]
# build top-down path
used_backbone_levels = len(laterals)
for i in range(used_backbone_levels - 1, 0, -1):
# In some cases, fixing `scale factor` (e.g. 2) is preferred, but
# it cannot co-exist with `size` in `F.interpolate`.
if 'scale_factor' in self.upsample_cfg:
laterals[i - 1] += F.interpolate(laterals[i],
**self.upsample_cfg)
else:
prev_shape = laterals[i - 1].shape[2:]
laterals[i - 1] += F.interpolate(laterals[i],
size=prev_shape,
**self.upsample_cfg)
# build outputs
# part 1: from original levels
outs = [
self.fpn_convs[i](laterals[i]) for i in range(used_backbone_levels)
]
# part 2: add extra levels
if self.num_outs > len(outs):
# use max pool to get more levels on top of outputs
# (e.g., Faster R-CNN, Mask R-CNN)
if not self.add_extra_convs:
for i in range(self.num_outs - used_backbone_levels):
outs.append(F.max_pool2d(outs[-1], 1, stride=2))
# add conv layers on top of original feature maps (RetinaNet)
else:
if self.add_extra_convs == 'on_input':
extra_source = inputs[self.backbone_end_level - 1]
elif self.add_extra_convs == 'on_lateral':
extra_source = laterals[-1]
elif self.add_extra_convs == 'on_output':
extra_source = outs[-1]
else:
raise NotImplementedError
outs.append(self.fpn_convs[used_backbone_levels](extra_source))
for i in range(used_backbone_levels + 1, self.num_outs):
if self.relu_before_extra_convs:
outs.append(self.fpn_convs[i](F.relu(outs[-1])))
else:
outs.append(self.fpn_convs[i](outs[-1]))
return tuple(outs)