深度学习-【图像分类】学习笔记2LeNet

2.1pytorch官方demo（LeNet）

Pytorch Tensor的通道排序：[batch, channel, height, width]。

经卷积后的矩阵尺寸大小计算公式：
N = (W - F + 2P) / S + 1

图像预处理

ToTensor()：

Normalize()：

为什么每计算一个batch，就需要调用以此optimizer.zero_grad()？
如果不清除历史梯度，就会对计算的历史梯度进行累加（通过这个特性你能够变相实现一个很大batch数值的训练）

---

代码示例

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)
        x = F.relu(self.fc1(x))      # output(120)
        x = F.relu(self.fc2(x))      # output(84)
        x = self.fc3(x)              # output(10)
        return x


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


if __name__ == '__main__':
    main()

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():
    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=True, transform=transform)
    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
    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()       # 实例化模型
    loss_function = nn.CrossEntropyLoss()   # 定义损失函数
    optimizer = optim.Adam(net.parameters(), lr=0.001)      # 定义优化器，传入所需要训练的所有参数

    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()
            # 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)  # 除以验证样本的总数

                    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():
    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'))

    im = Image.open('1.jpg')
    im = transform(im)  # 从[H, W, C] 转成 [C, H, W]
    im = torch.unsqueeze(im, dim=0)  # [N, C, H, W] # 这个函数主要是对数据维度进行扩充。给指定位置加上维数为一的维度

    with torch.no_grad():
        outputs = net(im)
        predict = torch.max(outputs, dim=1)[1].numpy()      # 取出对应的下标
        # predict = torch.softmax(outputs, dim=1)       # softmax处理
    print(classes[int(predict)])


if __name__ == '__main__':
    main()