Simple Baselines for Human Pose Estimation and Tracking
PDF: https://arxiv.org/pdf/1804.06208.pdf
PyTorch代码: https://github.com/shanglianlm0525/PyTorch-Networks
PyTorch代码: https://github.com/leoxiaobin/pose.pytorch
网路结构:
网络结构就是在ResNet后加上几层Deconvolution直接生成热力图
实验分析:
Heat map resolution:
Heat map resolution越大,性能越好
Kernel size:
Kernel size减小,AP也稍微降低
Backbone:
backbone越深,模型性能越好
Image size:
Image size越大,性能越好
PyTorch代码:
import torch
import torch.nn as nn
import torchvision
class ResBlock(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(ResBlock, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1,bias=False)
self.bn3 = nn.BatchNorm2d(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.relu(self.bn1(self.conv1(x)))
out = self.relu(self.bn2(self.conv2(out)))
out = self.bn3(self.conv3(out))
if self.downsample is not None:
residual = self.downsample(x)
out += residual
return self.relu(out)
class SimpleBaseline(nn.Module):
def __init__(self, nJoints):
super(SimpleBaseline, self).__init__()
self.inplanes = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(ResBlock, 64, 3)
self.layer2 = self._make_layer(ResBlock, 128, 4, stride=2)
self.layer3 = self._make_layer(ResBlock, 256, 6, stride=2)
self.layer4 = self._make_layer(ResBlock, 512, 3, stride=2)
self.deconv_layers = self._make_deconv_layer()
self.final_layer = nn.Conv2d(in_channels=256,out_channels=nJoints,kernel_size=1,stride=1,padding=0)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def _make_deconv_layer(self):
layers = []
for i in range(3):
layers.append(nn.ConvTranspose2d(in_channels=self.inplanes,out_channels=256,kernel_size=4,
stride=2,padding=1,output_padding=0,bias=False))
layers.append(nn.BatchNorm2d(256))
layers.append(nn.ReLU(inplace=True))
self.inplanes = 256
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.deconv_layers(x)
x = self.final_layer(x)
return x
if __name__ == '__main__':
model = SimpleBaseline(nJoints=16)
print(model)
data = torch.randn(1,3,256,192)
out = model(data)
print(out.shape)