ResNet50V2算法实战与解析

weixin_44523812

于 2024-12-20 22:32:37 发布

阅读量230

点赞数 5

文章标签：算法

本文链接：https://blog.youkuaiyun.com/weixin_44523812/article/details/144615475

版权

- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/kV8ZsJv6cPNzJLEuhPfvXg) 中的学习记录博客**
- **🍖 原作者：[K同学啊](https://mtyjkh.blog.youkuaiyun.com/)**

本周任务：

根据Tensorflow代码，编写对应的pytorch代码
了解ResNetV2与ResNetV的区别

一：前期准备

1.设置GPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warnings

warnings.filterwarnings("ignore")             #忽略警告信息

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

2.导入数据集

data_dir = "/content/drive/MyDrive/bird_photos"
data_dir = pathlib.Path(data_dir)

data_paths  = list(data_dir.glob('*'))
classeNames = [str(path).split("/")[-1] for path in data_paths]
classeNames

train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
    # transforms.RandomHorizontalFlip(), # 随机水平翻转
    transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
    transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
        mean=[0.485, 0.456, 0.406], 
        std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])

test_transform = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
    transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
    transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
        mean=[0.485, 0.456, 0.406], 
        std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])

total_data = datasets.ImageFolder("/content/drive/MyDrive/bird_photos",transform=train_transforms)
total_data

total_data.class_to_idx

二：数据预处理

1.划分数据

train_size = int(0.8 * len(total_data))
test_size  = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
train_dataset, test_dataset

batch_size = 4

train_dl = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True,
                                           num_workers=1)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                          batch_size=batch_size,
                                          shuffle=True,
                                          num_workers=1)

for X, y in test_dl:
    print("Shape of X [N, C, H, W]: ", X.shape)
    print("Shape of y: ", y.shape, y.dtype)
    break

三：搭建Resnet-50V2模型

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

class ConvBlock(nn.Module):
    def __init__(self, in_channels, filters, kernel_size=3, stride=1, conv_shortcut=False):
        super(ConvBlock, self).__init__()
        self.conv_shortcut = conv_shortcut
        self.stride = stride

        out_channels = 4 * filters

        self.preact_bn = nn.BatchNorm2d(in_channels)
        self.preact_relu = nn.ReLU(inplace=True)

        if conv_shortcut:
            self.shortcut = nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride)
        elif stride > 1:
            self.shortcut = nn.MaxPool2d(kernel_size=1, stride=stride)
        else:
            self.shortcut = nn.Identity()

        self.conv1 = nn.Conv2d(in_channels, filters, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(filters)
        
        self.conv2 = nn.Conv2d(filters, filters, kernel_size=kernel_size, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(filters)
        
        self.conv3 = nn.Conv2d(filters, out_channels, kernel_size=1)

    def forward(self, x):
        shortcut = self.shortcut(self.preact_relu(self.preact_bn(x)))

        x = self.conv1(self.preact_relu(self.preact_bn(x)))
        x = self.bn1(x)
        x = F.relu(x, inplace=True)

        x = self.conv2(x)
        x = self.bn2(x)
        x = F.relu(x, inplace=True)

        x = self.conv3(x)

        return F.relu(x + shortcut, inplace=True)


class ResNetBlock(nn.Module):
    def __init__(self, in_channels, filters, blocks, stride1=2):
        super(ResNetBlock, self).__init__()

        self.blocks = nn.ModuleList()
        self.blocks.append(ConvBlock(in_channels, filters, conv_shortcut=True, stride=stride1))
        for _ in range(1, blocks - 1):
            self.blocks.append(ConvBlock(4 * filters, filters))
        self.blocks.append(ConvBlock(4 * filters, filters, stride=1))

    def forward(self, x):
        for block in self.blocks:
            x = block(x)
        return x


class ResNet50V2(nn.Module):
    def __init__(self, num_classes=1000, include_top=True, input_channels=3):
        super(ResNet50V2, self).__init__()
        self.include_top = include_top

        self.conv1 = nn.Conv2d(input_channels, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        self.conv2 = ResNetBlock(64, 64, 3, stride1=1)
        self.conv3 = ResNetBlock(256, 128, 4)
        self.conv4 = ResNetBlock(512, 256, 6)
        self.conv5 = ResNetBlock(1024, 512, 3, stride1=1)

        self.post_bn = nn.BatchNorm2d(2048)
        self.post_relu = nn.ReLU(inplace=True)

        if include_top:
            self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
            self.fc = nn.Linear(2048, num_classes)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.conv2(x)
        x = self.conv3(x)
        x = self.conv4(x)
        x = self.conv5(x)

        x = self.post_relu(self.post_bn(x))

        if self.include_top:
            x = self.avgpool(x)
            x = torch.flatten(x, 1)
            x = self.fc(x)
        return x


model = ResNet50V2().to(device)
model

# 统计模型参数量以及其他指标
import torchsummary as summary
summary.summary(model, (3, 224, 224))

四：训练模型

1.编写训练函数

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小
    num_batches = len(dataloader)   # 批次数目, (size/batch_size，向上取整)

    train_loss, train_acc = 0, 0  # 初始化训练损失和正确率
    
    for X, y in dataloader:  # 获取图片及其标签
        X, y = X.to(device), y.to(device)
        
        # 计算预测误差
        pred = model(X)          # 网络输出
        loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失
        
        # 反向传播
        optimizer.zero_grad()  # grad属性归零
        loss.backward()        # 反向传播
        optimizer.step()       # 每一步自动更新
        
        # 记录acc与loss
        train_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()
            
    train_acc  /= size
    train_loss /= num_batches

    return train_acc, train_loss

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 测试集的大小
    num_batches = len(dataloader)          # 批次数目, (size/batch_size，向上取整)
    test_loss, test_acc = 0, 0
    
    # 当不进行训练时，停止梯度更新，节省计算内存消耗
    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)
            
            # 计算loss
            target_pred = model(imgs)
            loss        = loss_fn(target_pred, target)
            
            test_loss += loss.item()
            test_acc  += (target_pred.argmax(1) == target).type(torch.float).sum().item()

    test_acc  /= size
    test_loss /= num_batches

    return test_acc, test_loss

2.训练器的选择和训练

import copy

optimizer  = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn    = nn.CrossEntropyLoss() # 创建损失函数

epochs     = 20

train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []

best_acc = 0    # 设置一个最佳准确率，作为最佳模型的判别指标

for epoch in range(epochs):
    
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
    
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
    
    # 保存最佳模型到 best_model
    if epoch_test_acc > best_acc:
        best_acc   = epoch_test_acc
        best_model = copy.deepcopy(model)
    
    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)
    
    # 获取当前的学习率
    lr = optimizer.state_dict()['param_groups'][0]['lr']
    
    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, 
                          epoch_test_acc*100, epoch_test_loss, lr))
    
# 保存最佳模型到文件中
PATH = './best_model.pth'  # 保存的参数文件名
torch.save(model.state_dict(), PATH)

print('Done')

3.结果可视化

import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore")               #忽略警告信息
plt.rcParams['font.sans-serif']    = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False      # 用来正常显示负号
plt.rcParams['figure.dpi']         = 100        #分辨率

epochs_range = range(epochs)

plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)

plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)

七：总结

相较于之前的Resnet-50v2,我们发现模型的准确率略有提高