J2周：ResNet50V2算法实战与解析

最新推荐文章于 2024-07-12 10:45:15 发布

fqldom

最新推荐文章于 2024-07-12 10:45:15 发布

阅读量180

点赞数

文章标签：算法

本文链接：https://blog.csdn.net/fqldom/article/details/131601818

版权

🍨 本文为🔗365天深度学习训练营中的学习记录博客
🍖 原作者：K同学啊 | 接辅导、项目定制
🚀 文章来源：K同学的学习圈子

📌 本周任务：
●1.请根据本文 TensorFlow 代码，编写出相应的 Pytorch 代码（建议使用上周的数据测试一下模型是否构建正确）
●2.了解ResNetV2与ResNetV的区别
●3.改进思路是否可以迁移到其他地方呢（自由探索）

前言

上周复现了何恺明在2015年提出的深度残差网络ResNet，大神在后来的论文中提到一种全新的残差单元，我们命名为ResNet_V2, 本文将在上周的基础上基于Pytorch实现ResNet_V2模型。

一、ResNet50 VS ResNet_V2 的异同

在这里插入图片描述
ResNet50_V2 的框架图多了下面红色框框里的block，不难看出这个block其实就是把ResNet50里面的Conv Block 模块的conv2d 改成了 MaxPool。

二、ResNet_V2实现

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


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

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

"""
Residual Block
"""


class Block2(nn.Module):
    def __init__(self, in_channel, filters, kernel_size=3, stride=1, conv_shortcut=False):
        super(Block2, self).__init__()
        self.preact = nn.Sequential(
            nn.BatchNorm2d(in_channel),
            nn.ReLU(True)
        )

        self.shortcut = conv_shortcut
        if self.shortcut:
            self.short = nn.Conv2d(in_channel, 4*filters, 1, stride=stride, padding=0, bias=False)
        elif stride>1:
            self.short = nn.MaxPool2d(kernel_size=1, stride=stride, padding=0)
        else:
            self.short = nn.Identity()

        self.conv1 = nn.Sequential(
            nn.Conv2d(in_channel, filters, 1, stride=1, bias=False),
            nn.BatchNorm2d(filters),
            nn.ReLU(True)
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(filters, filters, kernel_size, stride=stride, padding=1, bias=False),
            nn.BatchNorm2d(filters),
            nn.ReLU(True)
        )
        self.conv3 = nn.Conv2d(filters, 4*filters, 1, stride=1, bias=False)

    def forward(self, x):
        x1 = self.preact(x)
        if self.shortcut:
            x2 = self.short(x1)
        else:
            x2 = self.short(x)
        x1 = self.conv1(x1)
        x1 = self.conv2(x1)
        x1 = self.conv3(x1)
        x = x1 + x2
        return x


class Stack2(nn.Module):
    def __init__(self, in_channel, filters, blocks, stride=2):
        super(Stack2, self).__init__()
        self.conv = nn.Sequential()
        self.conv.add_module(str(0), Block2(in_channel, filters, conv_shortcut=True))
        for i in range(1, blocks-1):
            self.conv.add_module(str(i), Block2(4*filters, filters))
        self.conv.add_module(str(blocks-1), Block2(4*filters, filters, stride=stride))

    def forward(self, x):
        x = self.conv(x)
        return x


"""
构建ResNet50V2
"""


class ResNet50V2(nn.Module):
    def __init__(self,
                 include_top=True,  # 是否包含位于网络顶部的全链接层
                 preact=True,  # 是否使用预激活
                 use_bias=True,  # 是否对卷积层使用偏置
                 input_shape=[224, 224, 3],
                 classes=1000,
                 pooling=None):  # 用于分类图像的可选类数
        super(ResNet50V2, self).__init__()

        self.conv1 = nn.Sequential()
        self.conv1.add_module('conv', nn.Conv2d(3, 64, 7, stride=2, padding=3, bias=use_bias, padding_mode='zeros'))
        if not preact:
            self.conv1.add_module('bn', nn.BatchNorm2d(64))
            self.conv1.add_module('relu', nn.ReLU())
        self.conv1.add_module('max_pool', nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

        self.conv2 = Stack2(64, 64, 3)
        self.conv3 = Stack2(256, 128, 4)
        self.conv4 = Stack2(512, 256, 6)
        self.conv5 = Stack2(1024, 512, 3, stride=1)

        self.post = nn.Sequential()
        if preact:
            self.post.add_module('bn', nn.BatchNorm2d(2048))
            self.post.add_module('relu', nn.ReLU())
        if include_top:
            self.post.add_module('avg_pool', nn.AdaptiveAvgPool2d((1, 1)))
            self.post.add_module('flatten', nn.Flatten())
            self.post.add_module('fc', nn.Linear(2048, classes))
        else:
            if pooling=='avg':
                self.post.add_module('avg_pool', nn.AdaptiveAvgPool2d((1, 1)))
            elif pooling=='max':
                self.post.add_module('max_pool', nn.AdaptiveMaxPool2d((1, 1)))

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.conv3(x)
        x = self.conv4(x)
        x = self.conv5(x)
        x = self.post(x)
        return x


model = ResNet50V2().to(device)
summary(model, (3, 224, 224))

三、在CIFAR-10上进行训练

import torchvision.datasets as datasets
import torchvision.transforms as transforms

# 定义预处理转换
transform = transforms.Compose([
    transforms.ToTensor(),  # 将 PIL 图像转换为张量
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))  # 归一化
])

# 加载 CIFAR-10 数据集
train_dataset = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
test_dataset = datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)

# 创建数据加载器
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=False)
def train(dataloader,model,loss_fn,optimizer):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    train_loss,train_acc = 0,0
    for x,y in dataloader:
        x,y = x.to(device),y.to(device)
        pred = model(x)
        loss = loss_fn(pred,y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        train_loss += loss.item()
        train_acc += (pred.argmax(1)==y).type(torch.float).sum().item()
    train_loss /= num_batches
    train_acc /= size
    return train_loss,train_acc
def test(dataloader,model,loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    test_loss,test_acc = 0,0
    with torch.no_grad():
        for x,y in dataloader:
            x,y = x.to(device),y.to(device)
            pred = model(x)
            loss = loss_fn(pred,y)
            test_loss += loss.item()
            test_acc += (pred.argmax(1)==y).type(torch.float).sum().item()
    test_loss /= num_batches
    test_acc /= size
    return test_loss,test_acc

loss_fn = nn.CrossEntropyLoss()
epochs = 50
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0
learning_rate = 1e-3
optimizer = torch.optim.Adam(model.parameters(),lr=learning_rate)
for epoch in range(1,epochs+1):
    model.train()
    eopch_train_loss,epoch_train_acc = train(train_loader,model,loss_fn,optimizer)
    model.eval()
    epoch_test_loss,epoch_test_acc = test(test_loader,model,loss_fn)
    train_loss.append(eopch_train_loss)
    train_acc.append(epoch_train_acc)
    test_loss.append(epoch_test_loss)
    test_acc.append(epoch_test_acc)
    lr = optimizer.param_groups[0]['lr']
    tmp = "Epoch:{},lr:{:.6f},train_loss:{:.4f},train_acc:{:.4f},test_loss:{:.4f},test_acc:{:.4f}"
    print(tmp.format(epoch,lr,eopch_train_loss,epoch_train_acc,epoch_test_loss,epoch_test_acc))

四、效果可视化

import matplotlib.pyplot as plt
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()

在这里插入图片描述

fqldom

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
1
评论
J2周：ResNet50V2算法实战与解析

上周复现了何恺明在2015年提出的深度残差网络ResNet，大神在后来的论文中提到一种全新的残差单元，我们命名为ResNet_V2, 本文将在上周的基础上基于Pytorch实现ResNet_V2模型。
复制链接

扫一扫