第J2周：Resnet-50V2

• 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
• 🍦 参考文章：[Pytorch实战 | 第J2周：Resnet-50V2
• 🍖 原作者：K同学啊|接辅导、项目定制

🏡 我的环境：
● 语言环境：Python 3.8
● 编译器：Pycharm
● 深度学习环境：Pytorch

一、 前期准备

1. 设置GPU

如果设备上支持GPU就使用GPU,否则使用CPU

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")

2. 导入数据

本地数据集位于./data/bird_photos/目录下

import os,PIL,random,pathlib

data_dir = './data/bird_photos/'
data_dir = pathlib.Path(data_dir)

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

f = []
for root, dirs, files in os.walk(data_dir):
    for name in files:
        f.append(os.path.join(root, name))
print("图片总数：",len(f))

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。
])

total_data = datasets.ImageFolder("./data/7-data/",transform=train_transforms)

total_data.class_to_idx

3. 划分数据集

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 = 32

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

4. 显示图片信息

#%%
import matplotlib.pyplot as plt
 # 指定图片大小，图像大小为20宽、5高的绘图(单位为英寸inch)
plt.figure(figsize=(80, 20))
for i, imgs in enumerate(X[:20]):
    # 维度缩减X
    npimg = imgs.numpy().transpose((1, 2, 0))
    # 将整个figure分成2行10列，绘制第i+1个子图。
    plt.subplot(2, 10, i+1)
    plt.imshow(npimg, cmap=plt.cm.binary)
    plt.axis('off')

二、手动搭建Resnet-50V2模型

1.模型

2.代码

#%%
''' 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)
''' 显示网络结构 '''

3. 统计模型参数量以及其他指标

import torchsummary as summary
summary.summary(model, (3, 224, 224))

三、训练模型

1. 编写训练和测试函数

见之前文章

## 2.正式训练
 
![在这里插入图片描述](https://img-blog.csdnimg.cn/75e2350989694309b8f61308e44f3366.png)
![在这里插入图片描述](https://img-blog.csdnimg.cn/1e49932c2bb04af6af6d65dc2f5043a1.png)

## 3.指定图片预测

![在这里插入图片描述](https://img-blog.csdnimg.cn/26c1467e47bb47beb7535b5dc7a930f6.png)

## 4.模型评估
![在这里插入图片描述](https://img-blog.csdnimg.cn/512376d39e114b75807707bbdce640ff.png)