深度学习J2周 ResNet50V2算法

于 2024-11-21 15:25:01 发布
阅读量732 收藏 11
点赞数 27
文章标签： 深度学习 人工智能
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.youkuaiyun.com/Radiantsss/article/details/143931704
版权

本周任务：

1.根据TensorFlow代码，写出pytorch代码

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

一、论文解读

 1.ResNetV2结构与ResNet结构对比

  

改进点：

(a)表示原始的ResNet残差结构，(b)表示新的ResNet残差结构

主要差别：（a）先卷积后进行BN和激活函数计算，最后在执行addition后再进行ReLU计算，（b）先进行BN和激活函数计算后卷积，把addition后的ReLU计算放到残差结构内部。

改进结果：

作者使用两种不同结构在CIFAR-10数据集上测试，模型1001层的ResNet模型；

从图中结果得出，proposed模型的测试集错误率明显更低一些，达到了4.92%的错误率，而原始的结构的测试集错误率是7.61%

2.关于残差结构的不同尝试

（简化了插图，不显示BN层，所有单位均采用权值层后的BN层。）

根据结果，可以看出original结构最好，即identity mapping恒等映射最好。

3.关于激活的尝试

e结果最好，其次是a，再是d。

二.模型复现

这一步也从这个博客进行学习借鉴，感谢！

https://blog.youkuaiyun.com/weixin_46620278/article/details/139296193?fromshare=blogdetail&sharetype=blogdetail&sharerId=139296193&sharerefer=PC&sharesource=Radiantsss&sharefrom=from_link

实验的数据集采用的是上周鸟类识别的数据，除了模型具体结构有变化，其余都和上周的代码一致

2.1数据导入

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os, PIL, pathlib, warnings
import torch.nn.functional as F
import matplotlib.pyplot as plt
import pandas as pd
from torchvision.io import read_image
from torch.utils.data import Dataset
import torch.utils.data as data
from PIL import Image
import copy
import numpy as np

# 一、导入数据
'''
1.1 设置GPU
'''
warnings.filterwarnings("ignore")

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

'''
1.2 导入数据
'''
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
data_dir = './第8天/bird_photos/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))


def count_images(folder):
    count = 0
    for item in folder.iterdir():
        if item.is_file():
            count += 1
        if item.is_dir():
            count += count_images(item)
    return count


image_count = count_images(data_dir)
print("图片总数为：", image_count)
classNames = [str(path).split('\\')[1] for path in data_paths]
# 利用split()函数对data_paths中的每个文件路径执行分割操作，获取各个文件所属的类别名称并储存在classNames中
# 4类天气，各300张图片
print(classNames)

# 二、数据预处理
'''
2.1 加载数据
'''
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("./第8天/bird_photos/", transform=train_transforms)
print(total_data)
print(total_data.class_to_idx)

'''
2.2 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])
print(train_dataset, test_dataset)

'''
2.3 可视化数据
'''
batch_size = 8
train_dl = torch.utils.data.DataLoader(train_dataset,
                                       batch_size=batch_size,
                                       shuffle=True,
                                       num_workers=0)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                      batch_size=batch_size,
                                      shuffle=True,
                                      num_workers=0)
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

image_folder = './第8天/bird_photos/Cockatoo/'  # 指定图像文件夹路径

image_files = [f for f in os.listdir(image_folder) if f.endswith((".jpg", ".png", ".jpeg"))]
fig, axes = plt.subplots(2, 4, figsize=(16, 6))

for ax, img_file in zip(axes.flat, image_files):
    img_path = os.path.join(image_folder, img_file)
    img = Image.open(img_path)
    ax.imshow(img)
    ax.axis('off')
plt.tight_layout()
plt.show()

输出结果： 

2.2模型构建

ResNet50V2、ResNet101V2与ResNet152V2的搭建方式完全一样，区别就在于堆叠的Residual Block的数量不同。

'''
3.1 residual block
'''
class Block2(nn.Module):
    def __init__(self, in_channels, filters, kernel_size=3, stride=1, conv_shortcut=False):
        super(Block2, self).__init__()
        self.conv_shortcut = conv_shortcut
        self.stride = stride
 
        self.bn_preact = nn.BatchNorm2d(in_channels)
        self.relu_preact = nn.ReLU(inplace=True)
 
        if conv_shortcut:
            self.shortcut = nn.Conv2d(in_channels, 4 * filters, kernel_size=1, stride=stride)
        else:
            self.shortcut = nn.MaxPool2d(kernel_size=1, stride=stride) if stride > 1 else nn.Identity()
 
        self.conv1 = nn.Conv2d(in_channels, filters, kernel_size=1, stride=1, bias=False)
        self.bn1 = nn.BatchNorm2d(filters)
        self.relu1 = nn.ReLU(inplace=True)
 
        self.pad2 = nn.ZeroPad2d(1)
        self.conv2 = nn.Conv2d(filters, filters, kernel_size=kernel_size, stride=stride, bias=False)
        self.bn2 = nn.BatchNorm2d(filters)
        self.relu2 = nn.ReLU(inplace=True)
 
        self.conv3 = nn.Conv2d(filters, 4 * filters, kernel_size=1)
 
    def forward(self, x):
        preact = self.bn_preact(x)
        preact = self.relu_preact(preact)
 
        shortcut = self.shortcut(preact)
 
        x = self.conv1(preact)
        x = self.bn1(x)
        x = self.relu1(x)
 
        x = self.pad2(x)
        x = self.conv2(x)
        x = self.bn2(x)
        x = self.relu2(x)
 
        x = self.conv3(x)
 
        x += shortcut
        return x
class Stack2(nn.Module):
    def __init__(self, in_channels, filters, blocks, stride=2):
        super(Stack2, self).__init__()
        self.blocks = nn.ModuleList()
        self.blocks.append(Block2(in_channels, filters, conv_shortcut=True))
        for i in range(1, blocks - 1):
            self.blocks.append(Block2(4 * filters, filters))
        self.blocks.append(Block2(4 * filters, filters, stride=stride))
 
    def forward(self, x):
        for block in self.blocks:
            x = block(x)
        return x
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)
print(model)


        (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu1): ReLU(inplace=True)
        (pad2): ZeroPad2d((1, 1, 1, 1))
        (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), bias=False)
        (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu2): ReLU(inplace=True)
        (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
      )
      (3): Block2(
        (bn_preact): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu_preact): ReLU(inplace=True)
        (shortcut): MaxPool2d(kernel_size=1, stride=2, padding=0, dilation=1, ceil_mode=False)
        (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu1): ReLU(inplace=True)
        (pad2): ZeroPad2d((1, 1, 1, 1))
        (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), bias=False)
        (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu2): ReLU(inplace=True)
        (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
      )
    )
  )
  (conv4): Stack2(
    (blocks): ModuleList(
      (0): Block2(
        (bn_preact): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu_preact): ReLU(inplace=True)
        (shortcut): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1))
        (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu1): ReLU(inplace=True)
        (pad2): ZeroPad2d((1, 1, 1, 1))
        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), bias=False)
        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu2): ReLU(inplace=True)
        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
      )
      (1-4): 4 x Block2(
        (bn_preact): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu_preact): ReLU(inplace=True)
        (shortcut): Identity()
        (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu1): ReLU(inplace=True)
        (pad2): ZeroPad2d((1, 1, 1, 1))
        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), bias=False)
        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu2): ReLU(inplace=True)
        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
      )
      (5): Block2(
        (bn_preact): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu_preact): ReLU(inplace=True)
        (shortcut): MaxPool2d(kernel_size=1, stride=2, padding=0, dilation=1, ceil_mode=False)
        (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu1): ReLU(inplace=True)
        (pad2): ZeroPad2d((1, 1, 1, 1))
        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), bias=False)
        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu2): ReLU(inplace=True)
        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
      )
    )
  )
  (conv5): Stack2(
    (blocks): ModuleList(
      (0): Block2(
        (bn_preact): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu_preact): ReLU(inplace=True)
        (shortcut): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1))
        (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu1): ReLU(inplace=True)
        (pad2): ZeroPad2d((1, 1, 1, 1))
        (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), bias=False)
        (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu2): ReLU(inplace=True)
        (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1))
      )
      (1-2): 2 x Block2(
        (bn_preact): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu_preact): ReLU(inplace=True)
        (shortcut): Identity()
        (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu1): ReLU(inplace=True)
        (pad2): ZeroPad2d((1, 1, 1, 1))
        (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), bias=False)
        (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu2): ReLU(inplace=True)
        (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1))
      )
    )
  )
  (post): Sequential(
    (bn): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (relu): ReLU()
    (avg_pool): AdaptiveAvgPool2d(output_size=(1, 1))
    (flatten): Flatten(start_dim=1, end_dim=-1)
    (fc): Linear(in_features=2048, out_features=1000, bias=True)
  )
) 

三、模型训练

'''
4.1 编写训练函数
'''
def train(dataloader, model, optimizer, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
 
    train_acc, train_loss = 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_acc, train_loss
 
'''
4.2 编写测试函数
'''
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
 
'''
4.3 正式训练
'''
 
loss_fn = nn.CrossEntropyLoss()   #交叉熵函数
learn_rate = 1e-3
opt = torch.optim.Adam(model.parameters(), lr=learn_rate)
 
epochs = 30
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0
 
# 开始训练
for epoch in range(epochs):
 
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, opt, loss_fn)
 
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
 
    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)
 
    lr = opt.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))
 
print('Done')

结果输出： 

 

四、结果可视化

#五、结果可视化
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()

五、指定图片预测

#六、指定图片预测
classes = list(total_data.class_to_idx)
def predict_one_image(image_path, model, transform, classes):
    test_img = Image.open(image_path).convert('RGB')
    plt.imshow(test_img)  # 展示预测的图片
 
    test_img = transform(test_img)
 
    img = test_img.to(device).unsqueeze(0)
 
    model.eval()
    output = model(img)
 
    _, pred = torch.max(output, 1)
    pred_class = classes[pred]
    print(f'预测结果是：{pred_class}')
 
    # 预测训练集中的某张照片
 
predict_one_image(image_path='./bird_photos/Bananaquit/008.jpg',
                  model=model,
                  transform=train_transforms,
                  classes=classes)

六、总结

  • 了解ResNetV2的结构，并对比与ResNet的不同
  • 将tensflow代码转换为pytorch
  • 具体的细节还得再去读一下论文， 有些专有名词还是不太懂
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值