LeNet(pytorch)

model.py   

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


class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, 5)
        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):
        x = F.relu(self.conv1(x))    # input(3, 32, 32) output(16, 28, 28)
        x = self.pool1(x)            # output(16, 14, 14)
        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),行数batch_size=32,列数32*5*5,-1表示自适应
        x = F.relu(self.fc1(x))      # output(120)
        x = F.relu(self.fc2(x))      # output(84)
        x = self.fc3(x)              # output(10)
        return x


if __name__ == '__main__':
    import torch
    input=torch.rand([32,3,32,32])
    model=LeNet()
    print(model)
    output=model(input)

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



def main():

    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

    #数据预处理,加载的是CIFAR10数据集,比较标准,预处理比较简单
    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
    # 第一次使用时要将download设置为True才会自动去下载数据集
    #直接调用官方提供的对CIFAR10数据集的加载库,不用再自己写加载数据集的脚本
    #加载后对数据进行预处理操作
    train_set = torchvision.datasets.CIFAR10(root='./data', train=True,
                                             download=True, transform=transform)
    #torch.utils.data.DataLoader  用于加载和批处理数据。它提供了对数据集的迭代访问,并支持并行加载数据。
    #方便地对训练数据进行批处理,以提高训练效率,并且可以自动化地处理数据加载和预处理的过程,
    #具体是怎么对输入数据集进行提取的,后面定义数据集时候再根据具体代码理解,这个是直接用的CIFAR类
    #感兴趣可以看CIFAR数据集加载的定义
    train_loader = torch.utils.data.DataLoader(train_set, batch_size=36,
                                               shuffle=True, num_workers=0)

    # 10000张验证图片
    # 第一次使用时要将download设置为True才会自动去下载数据集
    #CIFAR10数据集的训练集,验证集下载还是分开的
    val_set = torchvision.datasets.CIFAR10(root='./data', train=False,
                                           download=True, transform=transform)
    val_loader = torch.utils.data.DataLoader(val_set, batch_size=5000,
                                             shuffle=False, num_workers=0)

    #iter(val_loader)将验证数据加载器 val_loader 转换为一个迭代器对象 val_data_iter
    #next(val_data_iter) 从迭代器中获取下一个元素,也就是验证数据集中的下一个批次数据。
    #这个操作将返回一个元组,其中 val_image 是验证图像数据的批次,val_label 是相应的标签数据的批次。
    #这个在epoch训练过程中,能从这里直接更新,这个用法很奇妙
    val_data_iter = iter(val_loader)
    val_image, val_label = next(val_data_iter)
    #验证数据没必要放到gpu上
    val_image, val_label =val_image.to(device), val_label.to(device)
    
    # classes = ('plane', 'car', 'bird', 'cat',
    #            'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

    #注意要把模型直接移到device上还要直接赋值给模型
    net = LeNet().to(device)


    loss_function = nn.CrossEntropyLoss()
    optimizer = optim.Adam(net.parameters(), lr=0.001)

    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, labels = data
            inputs,labels=inputs.to(device),labels.to(device)
            # zero the parameter gradients
            optimizer.zero_grad()
            # forward + backward + optimize
            outputs = net(inputs)
            loss = loss_function(outputs, labels)
            loss.backward()
            optimizer.step()

            # print statistics
            #loss是一个torch.Tensor类型的标量值,代表了当前批次的损失。loss.item()方法用于获取该标量张量的Python数值
            running_loss += loss.item()
            if step % 500 == 499:    # print every 500 mini-batches
                with torch.no_grad():
                    outputs = net(val_image)  # [batch, 10]
                    #torch.max(outputs, dim=1)[1]返回了每个样本在预测分数中的最大值所对应的类别索引,也就是模型预测的类别
                    """
                    torch.eq(predict_y, val_label)会比较predict_y和val_label两个张量的对应元素是否相等,
                    返回一个布尔型的张量。通过调用.sum().item(),我们可以计算相等元素的总数,也就是预测正确的样本数。
                    """
                    #torch.max() 函数返回一个元组,其中第一个元素是最大值的张量,第二个元素是最大值所在的索引张量
                    #dim=1表示沿着[batch, 10] num_classes的维度
                    predict_y = torch.max(outputs, dim=1)[1]
                    accuracy = torch.eq(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'
    torch.save(net.state_dict(), save_path)


if __name__ == '__main__':
    main()

predict.py

import torch
import torchvision.transforms as transforms
from PIL import Image

from model import LeNet


def main():

    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

    transform = transforms.Compose(
        [transforms.Resize((32, 32)),
         transforms.ToTensor(),
         transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

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

    net = LeNet()
    net.load_state_dict(torch.load('Lenet.pth'))
    net=net.to(device)

    im = Image.open('1.jpg')
    im = transform(im)  # [C, H, W]
    im = torch.unsqueeze(im, dim=0)  # [N, C, H, W]
    im=im.to(device)

    with torch.no_grad():
        outputs = net(im)
        predict = torch.max(outputs, dim=1)[1]
    print(classes[int(predict)])


if __name__ == '__main__':
    main()

你可能感兴趣的:(pytorch,深度学习,人工智能)