第J2周：ResNet50V2算法实战与解析

🍨 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

1.ResNetV2结构与ResNet结构对比

在这里插入图片描述
🧲 改进点：(a)original 表示原始的 ResNet 的残差结构，(b)proposed 表示新的 ResNet 的残差结构。主要差别就是(a)结构先卷积后进行 BN 和激活函数计算，最后执行 addition 后再进行ReLU 计算； (b)结构先进行 BN 和激活函数计算后卷积，把 addition 后的 ReLU 计算放到了残差结构内部。

📌 改进结果：作者使用这两种不同的结构在 CIFAR-10 数据集上做测试，模型用的是 1001层的 ResNet 模型。从图中结果我们可以看出，(b)proposed 的测试集错误率明显更低一些，达到了 4.92%的错误率，(a)original 的测试集错误率是 7.61%。

1.2关于残差结构的不同尝试

在这里插入图片描述

(b-f)中的快捷连接被不同的组件阻碍。为了简化插图，我们不显示BN层，这里所有单位均采用权值层之后的BN层。图中(a-f)都是作者对残差结构的 shortcut 部分进行的不同尝试，作者对不同 shortcut 结构的尝试结果如下表所示。

作者用不同 shortcut 结构的 ResNet-110 在 CIFAR-10 数据集上做测试，发现最原始的(a)original 结构是最好的，也就是 identity mapping 恒等映射是最好的。

1.3关于激活的尝试

在这里插入图片描述

最好的结果是(e)full pre-activation，其次到(a)original。

二、论文复现
思路：因为本章是识别四种鸟类，pytorch框架

2.1.1. 设置GPU

如果设备上支持GPU就使用GPU,否则使用CPU。尽量配置好GPU使用。

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warningswarnings.filterwarnings("ignore")             #忽略警告信息device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

2.1.2. 导入数据

data_dir = '/home/aiusers/space_yjl/深度学习训练营/进阶/第J1周：ResNet-50算法实战与解析/第8天/bird_photos'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classNames = [str(path).split('/')[9] for path in data_paths]
print(data_dir)
print(classNames)

在这里插入图片描述
图形变换，输出一下：用到torchvision.transforms.Compose()类，

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("/home/aiusers/space_yjl/深度学习训练营/进阶/第J1周：ResNet-50算法实战与解析/第8天/bird_photos", transform=train_transforms)
print(total_data.class_to_idx)

在这里插入图片描述

2.1.3. 划分数据集

划分训练集和测试集.

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])

batch_size = 32
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

在这里插入图片描述

2.2搭建Resnet-50V2模型

在这里插入图片描述

2.2.1代码

Residual Block+堆叠Residual Block+ResNet50V2架构复现

#%%
''' 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_shortcutif 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 + x2return xclass 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 xmodel = ResNet50V2().to(device)
model
''' 显示网络结构 '''

在这里插入图片描述

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

在这里插入图片描述

三、训练与运行

编写训练和测试函数

# 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losstrain_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc  /= sizetrain_loss /= num_batchesreturn 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losstarget_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  /= sizetest_loss /= num_batchesreturn test_acc, test_loss

2.训练器的选择和训练

import copyoptimizer  = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn    = nn.CrossEntropyLoss() # 创建损失函数epochs = 10train_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):# 更新学习率（使用自定义学习率时使用）# adjust_learning_rate(optimizer, epoch, learn_rate)model.train()epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)# scheduler.step() # 更新学习率（调用官方动态学习率接口时使用）model.eval()epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)# 保存最佳模型到 best_modelif epoch_test_acc > best_acc:best_acc = epoch_test_accbest_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')

在这里插入图片描述

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()

在这里插入图片描述

四、模型预测

from PIL import Imageclasses = 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='/home/aiusers/space_yjl/深度学习训练营/进阶/第J1周：ResNet-50算法实战与解析/第8天/bird_photos/Black Skimmer/002.jpg',model=model,transform=train_transforms,classes=classes)