深度学习图片分类模型总结（附部分代码）_深度学习图片分类模型

作者：2023面试高手 | 2024-04-29 07:20:55

踩

深度学习图片分类模型

参考视频：2.1 pytorch官方demo(Lenet)_哔哩哔哩_bilibili

LeNet（1998）

pytorch 示例

笔记

Pytorch Tensor的通道排序：[batch,channel,height,width]
CIFAR10 dataset: It has the classes: ‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’. The images in CIFAR-10 are of size 3x32x32, i.e. 3-channel color images of 32x32 pixels in size.
为什么每计算一个batch就需要调用一次optimizer.zero_grad()：
1. PyTorch中在反向传播前为什么要手动将梯度清零？ - 知乎
pytorch官网：-docs可查看各个函数的用法，-tutorials可以查看示例
data = torch.max(outputs, dim=1), then data will be a tuple containing two tensors.
1. data[0]: This tensor will contain the maximum values along dimension 1 (the class dimension) of the outputs tensor. It will have a shape of [batch], where batch is the number of validation images in the batch.
2. data[1]: This tensor will contain the indices of the maximum values along dimension 1 (the class dimension) of the outputs tensor. It will also have a shape of [batch], where each element represents the predicted class label (index) for each validation image in the batch.

get the size of a tensor along a specific dimension, you use the method size() or the property shape[].


import torch
# Assuming val_label is a tensor with shape [batch_size, ...]
# Using size() method
size_along_first_dim = val_label.size(0)
# Using shape property
size_along_first_dim = val_label.shape[0]

model


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

train


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():
		'''
		ToTensor:Converts a PIL Image or numpy.ndarray (H x W x C) in the range
    [0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0]
		Normalize: a tensor image with mean and standard deviation.
	    Given mean: ``(mean[1],...,mean[n])`` and std: ``(std[1],..,std[n])`` for ``n``
	    channels, this transform will normalize each channel of the input ``torch.*Tensor`` i.e.,
	    ``output[channel] = (input[channel] - mean[channel]) / std[channel]
		'''
    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)
		#shuffle:是否打乱数据集
    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=10000,
                                             shuffle=False, num_workers=0)
    val_data_iter = iter(val_loader) #将val_loader转化为一个可迭代的迭代器
    val_image, val_label = next(val_data_iter)  #获取图片和标签值
    
    classes = ('plane', 'car', 'bird', 'cat',
                'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
		def imshow(img):
        img = img / 2 + 0.5     # unnormalize 返标准化
        npimg = img.numpy()
        plt.imshow(np.transpose(npimg, (1, 2, 0)))
        plt.show()
    
    # print labels
    print(' '.join(f'{classes[val_label[j]]:5s}' for j in range(4)))
    # show images
    imshow(torchvision.utils.make_grid(val_image))
 
    net = LeNet()
    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):
				'''
				step最多为50000/36
				50000是因为该数据集的训练集有50000张图片，36是在下载数据集时设置的batch_size
				'''
            # 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) #正向传播计算输出
            loss = loss_function(outputs, labels)#计算loss
            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
								'''
								%：这是模运算符，计算step除以500时的余数。
								使用数字 499 而不是 500，以确保在第 500 次迭代之后立即执行操作，而不是在第 501 次迭代之后执行。
								'''
                with torch.no_grad(): 
										#在接下来的过程中不计算梯度，没有这一行的话在测试过程中也会计算误差损失梯度，会占用很多资源
                    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()

AlexNet（2012）

VGG(2014)

笔记

在train时，如果是基于初始化权重进行迁移学习，需要在数据预处理时先将图片减去[123.68,116.78,103.94],这是imagenet的所有图片的三通道的均值，如果是从头训练，不需要减去
num_workers:线程数，windows系统只能为0

model


import torch.nn as nn
import torch
 
# official pretrain weights
model_urls = {
    'vgg11': '<https://download.pytorch.org/models/vgg11-bbd30ac9.pth>',
    'vgg13': '<https://download.pytorch.org/models/vgg13-c768596a.pth>',
    'vgg16': '<https://download.pytorch.org/models/vgg16-397923af.pth>',
    'vgg19': '<https://download.pytorch.org/models/vgg19-dcbb9e9d.pth>'
}
 
class VGG(nn.Module):
    def __init__(self, features, num_classes=1000, init_weights=False):
        super(VGG, self).__init__()
        self.features = features
        self.classifier = nn.Sequential(
            nn.Linear(512*7*7, 4096),
            nn.ReLU(True),
            nn.Dropout(p=0.5),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
            nn.Dropout(p=0.5),
            nn.Linear(4096, num_classes)
        )
        if init_weights:
            self._initialize_weights()
 
    def forward(self, x):
        # N x 3 x 224 x 224
        x = self.features(x)
        # N x 512 x 7 x 7
        x = torch.flatten(x, start_dim=1)
        # N x 512*7*7
        x = self.classifier(x)
        return x
 
    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                nn.init.xavier_uniform_(m.weight)
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.xavier_uniform_(m.weight)
                # nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)
 
def make_features(cfg: list):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == "M":
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            layers += [conv2d, nn.ReLU(True)]
            in_channels = v
    return nn.Sequential(*layers)#非关键字参数
 
#数字：卷积核个数 'M':池化层
cfgs = {
    'vgg11': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],#A
    'vgg13': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],#B
    'vgg16': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],#D
    'vgg19': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],#E
}
 
def vgg(model_name="vgg16", **kwargs):
    assert model_name in cfgs, "Warning: model number {} not in cfgs dict!".format(model_name)
    cfg = cfgs[model_name]
 
    model = VGG(make_features(cfg), **kwargs)
    return model