【入门】GPU训练图片分类器

系列文章目录

---

【入门】Pytorch实现简单的图片分类器

【入门】GPU训练图片分类器

---

前言

本文很适合一些想要入门机器视觉的小伙伴。本实验推荐在Juypter Notebook上运行。
我们将按次序做如下步骤：

1. 使用torchvision加载并且归一化CIFAR10的训练和测试数据集
2. 定义一个卷积神经网络
3. 定义一个损失函数
4. 在训练集上训练模型
5. 在测试集上测试模型

---

导入库

使用torchvision加载并归一化数据集。

import torch
import torchvision
import torchvision.transforms as transforms

使用cuda设备

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Assume that we are on a CUDA machine, then this should print a CUDA device:
print(device)

数据归一化

torchvision数据集的输出范围是[0,1]，我们将他们归一化至[-1,1]

tranform = transforms.Compose([transform.ToTensor(),transform.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))])
trainset = torchvision.datasets.CIFAR10(root='./data',train = True,download=True,transform = transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False,download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

下载完成会有如下输出：

查看训练集

# 展示其中的一些训练图片
import matplotlib.pyplot as plt
import numpy as np
# functions to show an image
def imshow(img):
    img = img / 2 + 0.5 # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()
    
# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()
# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))

torchvision.utils.make_grid(images)：将多张图片拼成一张图片，在展示数据时很有用。

图片展示：

构造网络

定义一个卷积神经网络

import torch.nn as nn 
import torch.nn.functional as F
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3,6,5)
        self.pool = nn.MaxPool2d(2,2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)
            
    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
        
net = Net()
net.to(device)

nn.Conv2d(3,6,5)表示输入的图片是3个通道(in_channel)，输出的是6个通道(out_channel)，卷积核大小kernel.size等于5
nn.Conv2d(6, 16, 5)同理。
想查看网络结构的话，可以输出net康康。

print(net)

定义损失函数和优化器

使用分类交叉熵Cross-Enteopy作损失函数
使用动量SGD做优化器

import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

开始训练

for epoch in range(2):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs
        inputs, labels = data

		# use GPU
        inputs, labels = inputs.to(device), labels.to(device)
        
        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

训练两个epoch之后的效果：

查看分类效果

correct = 0
total = 0
with torch.no_grad():
    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: %d %%' % (
 100 * correct / total))

查看每个类别的准确度

class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
     for data in testloader:
        images, labels = data
        images, labels = images.to(device), labels.to(device)
        outputs = net(images)
        _, predicted = torch.max(outputs, 1)
        c = (predicted == labels).squeeze()
        for i in range(4):
            label = labels[i]
            class_correct[label] += c[i].item()
            class_total[label] += 1
for i in range(10):
    print('Accuracy of %5s : %2d %%' % (classes[i], 100 * class_correct[i] / class_total[i]))

结果：

使用你的GPU训练

首先我们定义GPU设备为第一个可见的cuda设备

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Assume that we are on a CUDA machine, then this should print a CUDA device:
print(device)
net.to(device)

你必须在每个步骤向GPU发送输入和目标

inputs, labels = inputs.to(device), labels.to(device)

优化

更改网络结构，尝试增加你的网络宽度，看看会得到怎样的提升。

---

如果本文对你有帮助的话请继续关注，点赞，收藏~ 后续我将继续更新优化部分的内容，以及一些深度学习的东西。