学习Pytorch官方Demo——Lenet，以及遇到的问题

1.官方Demo的项目目录

2.模型

代码：

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


class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__() #调用父类的构造函数
        self.conv1 = nn.Conv2d(3, 16, 5)#卷积层：深度为3的特征矩阵，使用16个卷积核，卷积核的尺寸为5*5
        self.pool1 = nn.MaxPool2d(2, 2)#下采样层：池化核为2*2，布局为2的池化层
        self.conv2 = nn.Conv2d(16, 32, 5)#卷积层
        self.pool2 = nn.MaxPool2d(2, 2)#下采样层
        self.fc1 = nn.Linear(32*5*5, 120)#全连接层：输入是一个一维向量，需要将特征矩阵展平
        self.fc2 = nn.Linear(120, 84)#全连接层
        self.fc3 = nn.Linear(84, 10)#全连接层

    def forward(self, x):
        x = F.relu(self.conv1(x))    # input(3, 32, 32) output(16, 28, 28)
        """ 经卷积后的矩阵尺寸大小计算公式为：N= (W - F + 2P)/S+1 
            W为输入图片大小W*W
            F为卷积核的尺寸
            S为步长Stride=1
            P为Padding=0
        """
        x = self.pool1(x)            # output(16, 14, 14)
        x = F.relu(self.conv2(x))    # output(32, 10, 10) ;池化层只改变矩阵的高和宽，不会影响深度(28-2)/2+1
        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

3.训练

代码：

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():
    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
    train_set = torchvision.datasets.CIFAR10(root='./data', train=True,
                                             download=False, transform=transform)
    train_loader = torch.utils.data.DataLoader(train_set, batch_size=36,
                                               shuffle=True, num_workers=0)
    #每一批随机提取出36张图片，并打乱顺序

    # 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
    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)
    val_data_iter = iter(val_loader)
    val_image, val_label = val_data_iter.next()

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

    net = LeNet()
    loss_function = nn.CrossEntropyLoss()
    optimizer = optim.Adam(net.parameters(), lr=0.001)#使用了Adam优化器

    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

            # zero the parameter gradients
            optimizer.zero_grad()#将历史损失梯度清零
            # forward + backward + optimize
            outputs = net(inputs)
            loss = loss_function(outputs, labels)
            loss.backward()#反向传播
            optimizer.step()#参数更新

            # print statistics
            running_loss += loss.item()
            if step % 500 == 499:    # print every 500 mini-batches
                with torch.no_grad():
                    outputs = net(val_image)  # [batch, 10]
                    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()

运行结果：

4.预测

代码：

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


def main():
    transform = transforms.Compose(
        [transforms.Resize((32, 32)),#缩放
         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'))#载入权重文件

    im = Image.open('1.jpg')#载入图片
    im = transform(im)  # [C, H, W] 预处理
    im = torch.unsqueeze(im, dim=0)  # [N, C, H, W]增加一个新维度

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


if __name__ == '__main__':
    main()

运行结果：

5.遇到的问题

  原以为我先前就调配好了Pytorch的环境，结果今天下载模块与导入模块又遇到了问题，调试了老半天才终于将官方Demo给跑起来：
  首先我的Python Interpreter所处目录如下：

• 遇到的第一个问题：载入格式为’webp‘的图片时报错，
  解决办法：在File->Setting->Project->Python Interpreter中下载libwebp包
  

• 遇到的第二个问题：下载好libwebp包后，出现PIL模块不存在的问题，这时我先使用Anaconda来下载Pillow模块

pip install Pillow

比较奇怪的一点是明明能够在Python Interpreter中搜索到Pillow模块，但是到上方红色方框所圈的目录中无法找到pillow，因此想要引入PIL 却提示无该模块；
解决办法： 卸载Pillow后重新安装
卸载

pip uninstall Pillow 

重新安装

安装成功后能在pycharm中搜索到

这时引入PIL就没有报错了

from PIL import Image