pytorch官网demo代码详解

model.py

# 导入pytorch这个包
import torch.nn as nn
import torch.nn.functional as F

# 定义一个类，叫LeNeT，来自于nn.Module
class LeNet(nn.Module):
    # 初始化
    def __init__(self):
        # super解决的是在一层一层调用父类时出现的问题，反正每次init的时候加上这句话准没错
        super(LeNet, self).__init__()
        # 定义卷积层，参数in_channels输入特征矩阵的深度（如果输入RBG彩色图像就为3），outchannels卷积核的个数，kernelsize卷积核的大小
        self.conv1 = nn.Conv2d(3, 16, 5)
        # 定义下采样层，2×2说明缩小为一半
        self.pool1 = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(16, 32, 5)
        self.pool2 = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(32*5*5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # output 28=(w-f+2p)/s+1=32(图像尺寸大小)-5(卷积核大小)+0(padding=0)/stride(步距为1)+1 = 28
        x = F.relu(self.conv1(x))    # input(3, 32, 32) output(16, 28, 28)
        x = self.pool1(x)            # output(16, 14, 14) 上一个output的一半
        x = F.relu(self.conv2(x))    # output(32, 10, 10)
        x = self.pool2(x)            # output(32, 5, 5)
        x = x.view(-1, 32*5*5)       # output(32*5*5)
        x = F.relu(self.fc1(x))      # output(120)
        x = F.relu(self.fc2(x))      # output(84)
        x = self.fc3(x)              # output(10)
        return x

import torch
input1 = torch.rand([32,3,32,32])
model = LeNet()
print(model)
output = model(input1)

train.py

import torch
import torchvision
import torch.nn as nn
from model import LeNet
import torch.optim as optim
import torchvision.transforms as transforms

# Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor
transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

# 50000张训练图片
train_set = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
# 导入训练数据集，batch_size 批次处理，shuffle是否打乱数据，默认true，
train_loader = torch.utils.data.DataLoader(train_set, batch_size=36,
                                          shuffle=False, num_workers=0)

# 10000张验证图片
val_set = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=False, transform=transform)

val_loader = torch.utils.data.DataLoader(val_set, batch_size=5000,
                                         shuffle=False, num_workers=0)
# 吧val_loader转为可迭代的迭代器
val_data_iter = iter(val_loader)
val_image, val_label = val_data_iter.next()

# 定义分类
classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

net = LeNet()
# 定义损失函数
loss_function = nn.CrossEntropyLoss()
# 定义优化器
optimizer = optim.Adam(net.parameters(), lr=0.001)

# 同一个训练集多次训练
for epoch in range(5):  # loop over the dataset multiple times

    running_loss = 0.0
    for step, data in enumerate(train_loader, start=0):
        # get the inputs; data is a list of [inputs, labels]
        # inputs表示训练的图片，labels表示图片的正确分类
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()
        # forward + backward + optimize
        # outputs表示输出训练数据的分类结果
        outputs = net(inputs)
        # 训练结果和真实结果计算loss
        loss = loss_function(outputs, labels)
        # 损失反向传播
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        # 每500次打印输出
        if step % 500 == 499:    # print every 500 mini-batches
            with torch.no_grad():
                # 输入验证数据集
                outputs = net(val_image)  # [batch, 10]
                # 分类的概率最大的那个类就是结果
                predict_y = torch.max(outputs, dim=1)[1]
                # 计算准确度
                accuracy = (predict_y == val_label).sum().item() / val_label.size(0)

                print('[%d, %5d] train_loss: %.3f  test_accuracy: %.3f' %
                      (epoch + 1, step + 1, running_loss / 500, accuracy))
                running_loss = 0.0

print('Finished Training')

save_path = './Lenet.pth'
# 训练模型存储
torch.save(net.state_dict(), save_path)