PyTorch学习笔记（二）

import torch
import torchvision
import torchvision.transforms as transforms

import matplotlib.pyplot as plt
import numpy as np

import torch.nn as nn
import torch.nn.functional as F

import torch.optim as optim

transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# 定义 下载数据集
trainset    = torchvision.datasets.CIFAR10(root='./data', train=True,download=True, transform=transform)
# 加载训练数据
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,shuffle=True, num_workers=2)

# 定义
testset     = torchvision.datasets.CIFAR10(root='./data', train=False,download=True, transform=transform)
#加载测试数据
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')
# PyTorch 神经网络
# 神经网络可以通过 torch.nn 包来构建
# 一个典型的神经网络训练过程包括以下几点:
#   1.定义一个包含可训练参数的神经网络
#   2.迭代整个输入
#   3.通过神经网络处理输入
#   4.计算损失(loss)
#   5.反向传播梯度到神经网络的参数
#   6.更新网络的参数,典型的用一个简单的更新方法:weight = weight - learning_rate *gradien
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        # 卷积
        self.conv1 = nn.Conv2d(3, 6, 5)
        # 池化
        self.pool = nn.MaxPool2d(2, 2)
        # 卷积
        self.conv2 = nn.Conv2d(6, 16, 5)
        # 全连接
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        # 全连接
        self.fc2 = nn.Linear(120, 84)
        # 全连接
        self.fc3 = nn.Linear(84, 10)
    def forward(self, x):
        # 向前传播

        # 卷积->激活函数->池化
        x = self.pool(F.relu(self.conv1(x)))
        # 卷积->激活函数->池化
        x = self.pool(F.relu(self.conv2(x)))
        # 改变维度
        x = x.view(-1, 16 * 5 * 5)
        # 全连接->激活函数
        x = F.relu(self.fc1(x))
        # 全连接->激活函数
        x = F.relu(self.fc2(x))
        # 全连接
        x = self.fc3(x)
        return x
if __name__ == "__main__":
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    print(device)
    # 网络
    net = Net()
    # 分类交叉熵Cross-Entropy 作损失函数
    # 动量SGD做优化器 ？？？
    criterion = nn.CrossEntropyLoss()
    # lr 学习率 
    # momentum 我理解等价于衰减率
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

    for epoch in range(3):
        running_loss = 0.0
        for index,data in enumerate(trainloader,0):
            inputs , labels = data
            optimizer.zero_grad()
            outputs =net(inputs)
            loss = criterion(outputs,labels)
            loss.backward()
            optimizer.step()
            running_loss += loss.item()
            if index % 2000 == 1999:
                # print every 2000 mini-batches
                print('[%d, %5d] loss: %.3f' %
                (epoch + 1, index + 1, running_loss / 2000))
                running_loss = 0.0
    correct = 0
    total = 0
    with torch.no_grad():
        for data in testloader:
            images, labels = data
            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))

    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
            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]))
    print('Finished Training')