1 问题总结
最近一段时间内比较困扰我的问题：
- 做代码练习时，代码有些细节看不太明白，最近在学习pytorch的官方文档，希望能有一些帮助
- 在transform.normalize()中的数字每次都不太一样，这个是有什么计算方法吗
本周学习内容的问题：
- MobileNet V2 代码练习中，“因为 CIFAR10 是 32*32，因此，网络有一定修改”，所以第二层网络的 stride 改为了 1， 为什么要做这样的修改？ 其他网络也会根据数据集来修改网络吗？
2 代码练习
2.1 MobileNet
1.论文阅读
https://www.cnblogs.com/anxifeng/p/13443330.html
2.代码练习
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
class Block(nn.Module):
'''Depthwise conv + Pointwise conv'''
def __init__(self, in_planes, out_planes, stride=1):
super(Block, self).__init__()
# Depthwise 卷积，3*3 的卷积核，分为 in_planes，即各层单独进行卷积
self.conv1 = nn.Conv2d(in_planes, in_planes, kernel_size=3, stride=stride, padding=1, groups=in_planes, bias=False)
self.bn1 = nn.BatchNorm2d(in_planes)
# Pointwise 卷积，1*1 的卷积核
self.conv2 = nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=1, padding=0, bias=False)
self.bn2 = nn.BatchNorm2d(out_planes)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = F.relu(self.bn2(self.conv2(out)))
return out
创建DataLoader
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)
创建 MobileNetV1 网络
32×32×3 ==>
32×32×32 ==> 32×32×64 ==> 16×16×128 ==> 16×16×128 ==>
8×8×256 ==> 8×8×256 ==> 4×4×512 ==> 4×4×512 ==>
2×2×1024 ==> 2×2×1024
接下来为均值 pooling ==> 1×1×1024
最后全连接到 10个输出节点
class MobileNetV1(nn.Module):
# (128,2) means conv planes=128, stride=2
cfg = [(64,1), (128,2), (128,1), (256,2), (256,1), (512,2), (512,1),
(1024,2), (1024,1)]
def __init__(self, num_classes=10):
super(MobileNetV1, 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.linear = nn.Linear(1024, num_classes)
def _make_layers(self, in_planes):
layers = []
for x in self.cfg:
out_planes = x[0]
stride = x[1]
layers.append(Block(in_planes, out_planes, 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.avg_pool2d(out, 2)
out = out.view(out.size(0), -1)
out = self.linear(out)
return out
实例化网络
# 网络放到GPU上
net = MobileNetV1().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
创建网络
for epoch in range(10): # 重复多轮训练
for i, (inputs, labels) in enumerate(trainloader):
inputs = inputs.to(device)
labels = labels.to(device)
# 优化器梯度归零
optimizer.zero_grad()
# 正向传播 + 反向传播 + 优化
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# 输出统计信息
if i % 100 == 0:
print('Epoch: %d Minibatch: %5d loss: %.3f' %(epoch + 1, i + 1, loss.item()))
print('Finished Training')
模型测试
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: 78.11 %
2.2 MobileNet V2
1.论文阅读
https://www.cnblogs.com/anxifeng/p/13458998.html
2.代码练习
下面就是 Inverted residual block 部分的代码，主要思路就是:
expand + Depthwise + Pointwise 其中，expand就是增大feature map数量的意思。需要指出的是，当步长为1的时候，要加一个 shortcut；步长为2的时候，目的是降低feature map尺寸，就不需要加 shortcut 了。
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
class Block(nn.Module):
'''expand + depthwise + pointwise'''
def __init__(self, in_planes, out_planes, expansion, stride):
super(Block, self).__init__()
self.stride = stride
# 通过 expansion 增大 feature map 的数量
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)
# 步长为 1 时，如果 in 和 out 的 feature map 通道不同，用一个卷积改变通道数
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))
# 步长为 1 时，如果 in 和 out 的 feature map 通道相同，直接返回输入
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))
# 步长为1，加 shortcut 操作
if self.stride == 1:
return out + self.shortcut(x)
# 步长为2，直接输出
else:
return out
创建 MobileNetV2 网络
注意，因为 CIFAR10 是 32*32，因此，网络有一定修改。
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:
strides = [stride] + [1]*(num_blocks-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
创建 DataLoader
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)
实例化网络
# 网络放到GPU上
net = MobileNetV2().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
模型训练
for epoch in range(10): # 重复多轮训练
for i, (inputs, labels) in enumerate(trainloader):
inputs = inputs.to(device)
labels = labels.to(device)
# 优化器梯度归零
optimizer.zero_grad()
# 正向传播 + 反向传播 + 优化
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# 输出统计信息
if i % 100 == 0:
print('Epoch: %d Minibatch: %5d loss: %.3f' %(epoch + 1, i + 1, loss.item()))
print('Finished Training')
模型测试
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 %