MobileNetV2代碼實現

頭文件

import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
import torch.optim as optim

可分離卷積

主要思路就是:

expand + Depthwise + Pointwise 其中，expand就是增大feature map數量的意思。需要指出的是，當步長為1的時候，要加一個 shortcut（即ResNet里的f(x)+x操作）；步長為2的時候，目的是降低feature map尺寸，就不需要加 shortcut 了。

class Block(nn.Module):
    '''expand + depthwise + pointwise'''
    def __init__(self, in_planes, out_planes, expansion, stride):
        super(Block, self).__init__()
        self.stride = stride
        # 通過 expansion 增大 feature map 的數量
        planes = expansion * in_planes
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, groups=planes, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, out_planes, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn3 = nn.BatchNorm2d(out_planes)

        # 步長為 1 時，如果 in 和 out 的 feature map 通道不同，用一個卷積改變通道數
        if stride == 1 and in_planes != out_planes:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=1, padding=0, bias=False),
                nn.BatchNorm2d(out_planes))
        # 步長為 1 時，如果 in 和 out 的 feature map 通道相同，直接返回輸入
        if stride == 1 and in_planes == out_planes:
            self.shortcut = nn.Sequential()

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = F.relu(self.bn2(self.conv2(out)))
        out = self.bn3(self.conv3(out))
        # 步長為1，加 shortcut 操作
        if self.stride == 1:
            return out + self.shortcut(x)
        # 步長為2，直接輸出
        else:
            return out

創建 MobileNetV2 網絡

因為 CIFAR10 是 32*32，因此，網絡有一定修改。

class MobileNetV2(nn.Module):
    # (expansion, out_planes, num_blocks, stride)
    cfg = [(1,  16, 1, 1),
           (6,  24, 2, 1), 
           (6,  32, 3, 2),
           (6,  64, 4, 2),
           (6,  96, 3, 1),
           (6, 160, 3, 2),
           (6, 320, 1, 1)]

    def __init__(self, num_classes=10):
        super(MobileNetV2, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(32)
        self.layers = self._make_layers(in_planes=32)
        self.conv2 = nn.Conv2d(320, 1280, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn2 = nn.BatchNorm2d(1280)
        self.linear = nn.Linear(1280, num_classes)

    def _make_layers(self, in_planes):
        layers = []
        for expansion, out_planes, num_blocks, stride in self.cfg:
            #第一個ResidualBlock的步幅由make_layer的函數參數stride指定
            #后續的num_blocks-1個ResidualBlock步幅是1
            strides = [stride] + [1]*(num_blocks-1)
            '''
            [1]
			[1, 1]
			[2, 1, 1]
			[2, 1, 1, 1]
			[1, 1, 1]
			[2, 1, 1]
			[1]
            '''
            for stride in strides:
                layers.append(Block(in_planes, out_planes, expansion, stride))
                in_planes = out_planes
        return nn.Sequential(*layers)

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.layers(out)
        out = F.relu(self.bn2(self.conv2(out)))
        out = F.avg_pool2d(out, 4)
        out = out.view(out.size(0), -1)
        out = self.linear(out)
        return out

創建 DataLoader

# 使用GPU訓練，可以在菜單 "代碼執行工具" -> "更改運行時類型" 里進行設置
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

transform_train = transforms.Compose([
    transforms.RandomCrop(32, padding=4),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])

transform_test = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,  download=True, transform=transform_train)
testset  = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform_test)

trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True, num_workers=2)
testloader = torch.utils.data.DataLoader(testset, batch_size=128, shuffle=False, num_workers=2)

實例化網絡

# 網絡放到GPU上
net = MobileNetV2().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)

模型訓練

for epoch in range(10):  # 重復多輪訓練
    for i, (inputs, labels) in enumerate(trainloader):
        inputs = inputs.to(device)
        labels = labels.to(device)
        # 優化器梯度歸零
        optimizer.zero_grad()
        # 正向傳播 +　反向傳播 + 優化 
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        # 輸出統計信息
        if i % 100 == 0:   
            print('Epoch: %d Minibatch: %5d loss: %.3f' %(epoch + 1, i + 1, loss.item()))

print('Finished Training')

模型測試

correct = 0
total = 0

for data in testloader:
    images, labels = data
    images, labels = images.to(device), labels.to(device)
    outputs = net(images)
    _, predicted = torch.max(outputs.data, 1)
    total += labels.size(0)
    correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %.2f %%' % (
    100 * correct / total))

Accuracy of the network on the 10000 test images: 82.13 %