HRnet
Deep High-Resolution Representation Learning for Human Pose Estimation
算法流程如下：
其中Bottleneck的网络如下：
stage：
其中BasicBlock的网络如下：
以下是Hrnet特征间信息交互过程，为x_fuse过程，本身并不改变各个分辨率特征的大小
fuse_layers是hrnet多个不同分辨率特征信息交互的网络，本身并不改变各个分辨率特征的大小 以下为fuse_layers的构造代码：
hrnet：code
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))以下为fuse_layers的前向传播代码：
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))