400 lines
12 KiB
Python
400 lines
12 KiB
Python
# Taken from https://github.com/modelscope/modelscope
|
|
|
|
# Implementation here is modified based on hrnet
|
|
# originally Apache 2.0 License and publicly available at https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation
|
|
|
|
from torch import nn
|
|
|
|
BN_MOMENTUM = 0.1
|
|
|
|
|
|
def conv3x3(in_planes, out_planes, stride=1):
|
|
"""3x3 convolution with padding"""
|
|
return nn.Conv2d(
|
|
in_planes,
|
|
out_planes,
|
|
kernel_size=3,
|
|
stride=stride,
|
|
padding=1,
|
|
bias=False)
|
|
|
|
|
|
class BasicBlock(nn.Module):
|
|
expansion = 1
|
|
|
|
def __init__(self, inplanes, planes, stride=1, downsample=None):
|
|
super(BasicBlock, self).__init__()
|
|
self.conv1 = conv3x3(inplanes, planes, stride)
|
|
self.bn1 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.conv2 = conv3x3(planes, planes)
|
|
self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
|
|
self.downsample = downsample
|
|
self.stride = stride
|
|
|
|
def forward(self, x):
|
|
residual = 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:
|
|
residual = self.downsample(x)
|
|
|
|
out += residual
|
|
out = self.relu(out)
|
|
|
|
return out
|
|
|
|
|
|
class Bottleneck(nn.Module):
|
|
expansion = 4
|
|
|
|
def __init__(self, inplanes, planes, stride=1, downsample=None):
|
|
super(Bottleneck, self).__init__()
|
|
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
|
|
self.bn1 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
|
|
self.conv2 = nn.Conv2d(
|
|
planes,
|
|
planes,
|
|
kernel_size=3,
|
|
stride=stride,
|
|
padding=1,
|
|
bias=False)
|
|
self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
|
|
self.conv3 = nn.Conv2d(
|
|
planes, planes * self.expansion, kernel_size=1, bias=False)
|
|
self.bn3 = nn.BatchNorm2d(
|
|
planes * self.expansion, momentum=BN_MOMENTUM)
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.downsample = downsample
|
|
self.stride = stride
|
|
|
|
def forward(self, x):
|
|
residual = 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:
|
|
residual = self.downsample(x)
|
|
|
|
out += residual
|
|
out = self.relu(out)
|
|
|
|
return out
|
|
|
|
|
|
class HighResolutionModule(nn.Module):
|
|
|
|
def __init__(self,
|
|
num_branches,
|
|
blocks,
|
|
num_blocks,
|
|
num_inchannels,
|
|
num_channels,
|
|
fuse_method,
|
|
multi_scale_output=True):
|
|
super(HighResolutionModule, self).__init__()
|
|
self._check_branches(num_branches, blocks, num_blocks, num_inchannels,
|
|
num_channels)
|
|
|
|
self.num_inchannels = num_inchannels
|
|
self.fuse_method = fuse_method
|
|
self.num_branches = num_branches
|
|
|
|
self.multi_scale_output = multi_scale_output
|
|
|
|
self.branches = self._make_branches(num_branches, blocks, num_blocks,
|
|
num_channels)
|
|
self.fuse_layers = self._make_fuse_layers()
|
|
self.relu = nn.ReLU(True)
|
|
|
|
def _check_branches(self, num_branches, blocks, num_blocks, num_inchannels,
|
|
num_channels):
|
|
if num_branches != len(num_blocks):
|
|
error_msg = 'NUM_BRANCHES({}) <> NUM_BLOCKS({})'.format(
|
|
num_branches, len(num_blocks))
|
|
raise ValueError(error_msg)
|
|
|
|
if num_branches != len(num_channels):
|
|
error_msg = 'NUM_BRANCHES({}) <> NUM_CHANNELS({})'.format(
|
|
num_branches, len(num_channels))
|
|
raise ValueError(error_msg)
|
|
|
|
if num_branches != len(num_inchannels):
|
|
error_msg = 'NUM_BRANCHES({}) <> NUM_INCHANNELS({})'.format(
|
|
num_branches, len(num_inchannels))
|
|
raise ValueError(error_msg)
|
|
|
|
def _make_one_branch(self,
|
|
branch_index,
|
|
block,
|
|
num_blocks,
|
|
num_channels,
|
|
stride=1):
|
|
downsample = None
|
|
if stride != 1 or \
|
|
self.num_inchannels[branch_index] != num_channels[branch_index] * block.expansion:
|
|
downsample = nn.Sequential(
|
|
nn.Conv2d(
|
|
self.num_inchannels[branch_index],
|
|
num_channels[branch_index] * block.expansion,
|
|
kernel_size=1,
|
|
stride=stride,
|
|
bias=False),
|
|
nn.BatchNorm2d(
|
|
num_channels[branch_index] * block.expansion,
|
|
momentum=BN_MOMENTUM),
|
|
)
|
|
layers = []
|
|
layers.append(
|
|
block(self.num_inchannels[branch_index],
|
|
num_channels[branch_index], stride, downsample))
|
|
self.num_inchannels[branch_index] = \
|
|
num_channels[branch_index] * block.expansion
|
|
for i in range(1, num_blocks[branch_index]):
|
|
layers.append(
|
|
block(self.num_inchannels[branch_index],
|
|
num_channels[branch_index]))
|
|
|
|
return nn.Sequential(*layers)
|
|
|
|
def _make_branches(self, num_branches, block, num_blocks, num_channels):
|
|
branches = []
|
|
|
|
for i in range(num_branches):
|
|
branches.append(
|
|
self._make_one_branch(i, block, num_blocks, num_channels))
|
|
|
|
return nn.ModuleList(branches)
|
|
|
|
def _make_fuse_layers(self):
|
|
if self.num_branches == 1:
|
|
return None
|
|
|
|
num_branches = self.num_branches
|
|
num_inchannels = self.num_inchannels
|
|
fuse_layers = []
|
|
for i in range(num_branches if self.multi_scale_output else 1):
|
|
fuse_layer = []
|
|
for j in range(num_branches):
|
|
if j > i:
|
|
fuse_layer.append(
|
|
nn.Sequential(
|
|
nn.Conv2d(
|
|
num_inchannels[j],
|
|
num_inchannels[i],
|
|
1,
|
|
1,
|
|
0,
|
|
bias=False), nn.BatchNorm2d(num_inchannels[i]),
|
|
nn.Upsample(
|
|
scale_factor=2**(j - i), mode='nearest')))
|
|
elif j == i:
|
|
fuse_layer.append(None)
|
|
else:
|
|
conv3x3s = []
|
|
for k in range(i - j):
|
|
if k == i - j - 1:
|
|
num_outchannels_conv3x3 = num_inchannels[i]
|
|
conv3x3s.append(
|
|
nn.Sequential(
|
|
nn.Conv2d(
|
|
num_inchannels[j],
|
|
num_outchannels_conv3x3,
|
|
3,
|
|
2,
|
|
1,
|
|
bias=False),
|
|
nn.BatchNorm2d(num_outchannels_conv3x3)))
|
|
else:
|
|
num_outchannels_conv3x3 = num_inchannels[j]
|
|
conv3x3s.append(
|
|
nn.Sequential(
|
|
nn.Conv2d(
|
|
num_inchannels[j],
|
|
num_outchannels_conv3x3,
|
|
3,
|
|
2,
|
|
1,
|
|
bias=False),
|
|
nn.BatchNorm2d(num_outchannels_conv3x3),
|
|
nn.ReLU(True)))
|
|
fuse_layer.append(nn.Sequential(*conv3x3s))
|
|
fuse_layers.append(nn.ModuleList(fuse_layer))
|
|
|
|
return nn.ModuleList(fuse_layers)
|
|
|
|
def get_num_inchannels(self):
|
|
return self.num_inchannels
|
|
|
|
def forward(self, x):
|
|
if self.num_branches == 1:
|
|
return [self.branches[0](x[0])]
|
|
|
|
for i in range(self.num_branches):
|
|
x[i] = self.branches[i](x[i])
|
|
|
|
x_fuse = []
|
|
|
|
for i in range(len(self.fuse_layers)):
|
|
y = x[0] if i == 0 else self.fuse_layers[i][0](x[0])
|
|
for j in range(1, self.num_branches):
|
|
if i == j:
|
|
y = y + x[j]
|
|
else:
|
|
y = y + self.fuse_layers[i][j](x[j])
|
|
x_fuse.append(self.relu(y))
|
|
|
|
return x_fuse
|
|
|
|
|
|
def conv_bn(in_channels, out_channels, kernel_size, stride, padding, groups=1):
|
|
result = nn.Sequential()
|
|
result.add_module(
|
|
'conv',
|
|
nn.Conv2d(
|
|
in_channels=in_channels,
|
|
out_channels=out_channels,
|
|
kernel_size=kernel_size,
|
|
stride=stride,
|
|
padding=padding,
|
|
groups=groups,
|
|
bias=False))
|
|
result.add_module('bn', nn.BatchNorm2d(num_features=out_channels))
|
|
return result
|
|
|
|
|
|
def upsample(scale, oup):
|
|
return nn.Sequential(
|
|
nn.Upsample(scale_factor=scale, mode='bilinear'),
|
|
nn.Conv2d(
|
|
in_channels=oup,
|
|
out_channels=oup,
|
|
kernel_size=3,
|
|
stride=1,
|
|
padding=1,
|
|
groups=1,
|
|
bias=False), nn.BatchNorm2d(oup), nn.PReLU())
|
|
|
|
|
|
class SE_Block(nn.Module):
|
|
|
|
def __init__(self, c, r=16):
|
|
super().__init__()
|
|
self.squeeze = nn.AdaptiveAvgPool2d(1)
|
|
self.excitation = nn.Sequential(
|
|
nn.Linear(c, c // r, bias=False), nn.ReLU(inplace=True),
|
|
nn.Linear(c // r, c, bias=False), nn.Sigmoid())
|
|
|
|
def forward(self, x):
|
|
bs, c, _, _ = x.shape
|
|
y = self.squeeze(x).view(bs, c)
|
|
y = self.excitation(y).view(bs, c, 1, 1)
|
|
return x * y.expand_as(x)
|
|
|
|
|
|
class BasicBlockSE(nn.Module):
|
|
expansion = 1
|
|
|
|
def __init__(self, inplanes, planes, stride=1, downsample=None, r=64):
|
|
super(BasicBlockSE, self).__init__()
|
|
self.conv1 = conv3x3(inplanes, planes, stride)
|
|
self.bn1 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.conv2 = conv3x3(planes, planes)
|
|
self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
|
|
self.downsample = downsample
|
|
self.stride = stride
|
|
self.se = SE_Block(planes, r)
|
|
|
|
def forward(self, x):
|
|
residual = x
|
|
|
|
out = self.conv1(x)
|
|
out = self.bn1(out)
|
|
out = self.relu(out)
|
|
|
|
out = self.conv2(out)
|
|
out = self.bn2(out)
|
|
out = self.se(out)
|
|
|
|
if self.downsample is not None:
|
|
residual = self.downsample(x)
|
|
|
|
out += residual
|
|
out = self.relu(out)
|
|
|
|
return out
|
|
|
|
|
|
class BottleneckSE(nn.Module):
|
|
expansion = 4
|
|
|
|
def __init__(self, inplanes, planes, stride=1, downsample=None, r=64):
|
|
super(BottleneckSE, self).__init__()
|
|
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
|
|
self.bn1 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
|
|
self.conv2 = nn.Conv2d(
|
|
planes,
|
|
planes,
|
|
kernel_size=3,
|
|
stride=stride,
|
|
padding=1,
|
|
bias=False)
|
|
self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
|
|
self.conv3 = nn.Conv2d(
|
|
planes, planes * self.expansion, kernel_size=1, bias=False)
|
|
self.bn3 = nn.BatchNorm2d(
|
|
planes * self.expansion, momentum=BN_MOMENTUM)
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.downsample = downsample
|
|
self.stride = stride
|
|
|
|
self.se = SE_Block(planes * self.expansion, r)
|
|
|
|
def forward(self, x):
|
|
residual = 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)
|
|
|
|
out = self.se(out)
|
|
|
|
if self.downsample is not None:
|
|
residual = self.downsample(x)
|
|
|
|
out += residual
|
|
out = self.relu(out)
|
|
|
|
return out
|
|
|
|
|
|
blocks_dict = {
|
|
'BASIC': BasicBlock,
|
|
'BOTTLENECK': Bottleneck,
|
|
'BASICSE': BasicBlockSE,
|
|
'BOTTLENECKSE': BottleneckSE,
|
|
}
|