MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
论文链接：https://arxiv.org/pdf/1704.04861.pdf
PyTorch：https://github.com/shanglianlm0525/PyTorch-Networks
Standard Convolution
Depthwise Separable Convolution
Depthwise Convolution
Pointwise Convolution
Depthwise Separable Convolution结构
PyTorch实现：
import torch
import torch.nn as nn
import torchvision
def BottleneckV1(in_channels, out_channels, stride):
return nn.Sequential(
nn.Conv2d(in_channels=in_channels,out_channels=in_channels,kernel_size=3,stride=stride,padding=1,groups=in_channels),
nn.BatchNorm2d(in_channels),
nn.ReLU6(inplace=True),
nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=1),
nn.BatchNorm2d(out_channels),
nn.ReLU6(inplace=True)
)
class MobileNetV1(nn.Module):
def __init__(self, num_classes=1000):
super(MobileNetV1, self).__init__()
self.first_conv = nn.Sequential(
nn.Conv2d(in_channels=3,out_channels=32,kernel_size=3,stride=2,padding=1),
nn.BatchNorm2d(32),
nn.ReLU6(inplace=True),
)
self.bottleneck = nn.Sequential(
BottleneckV1(32, 64, stride=1),
BottleneckV1(64, 128, stride=2),
BottleneckV1(128, 128, stride=1),
BottleneckV1(128, 256, stride=2),
BottleneckV1(256, 256, stride=1),
BottleneckV1(256, 512, stride=2),
BottleneckV1(512, 512, stride=1),
BottleneckV1(512, 512, stride=1),
BottleneckV1(512, 512, stride=1),
BottleneckV1(512, 512, stride=1),
BottleneckV1(512, 512, stride=1),
BottleneckV1(512, 1024, stride=2),
BottleneckV1(1024, 1024, stride=1),
)
self.avg_pool = nn.AvgPool2d(kernel_size=7,stride=1)
self.linear = nn.Linear(in_features=1024,out_features=num_classes)
self.dropout = nn.Dropout(p=0.2)
self.softmax = nn.Softmax(dim=1)
self.init_params()
def init_params(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight)
nn.init.constant_(m.bias,0)
elif isinstance(m, nn.Linear) or isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def forward(self, x):
x = self.first_conv(x)
x = self.bottleneck(x)
x = self.avg_pool(x)
x = x.view(x.size(0),-1)
x = self.dropout(x)
x = self.linear(x)
out = self.softmax(x)
return out
if __name__=='__main__':
model = MobileNetV1()
print(model)
input = torch.randn(1, 3, 224, 224)
out = model(input)
print(out.shape)
