深度学习第J6周：ResNeXt-50实战解析

import copy
 
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
loss_fn = nn.CrossEntropyLoss()  # 创建损失函数
 
epochs = 10
 
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):
    # 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_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')

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同学的学习圈子深度学习第J6周：ResNeXt-50实战解析K同学的学习圈子

一、模型结构介绍
ResNeXt是由何凯明团队在2017年CVPR会议上提出来的新型图像分类网络。

这篇文章介绍了一种用于图像分类的简单而有效的网络架构，称为Aggregated Residual Transformations for Deep Neural Networks。该网络采用了VGG/ResNets的策略，通过重复层来增加深度和宽度，并利用分裂-变换-合并策略以易于扩展的方式进行转换。文章还提出了一个新的维度——“基数”，它是指转换集合的大小，可以在保持复杂性不变的情况下提高分类准确性。作者在ImageNet-1K数据集上进行了实证研究，证明了这种方法的有效性。

下图是ResNet（左）与ResNeXt（右）block的差异。在ResNet中，输入的具有256个通道的特征经过1×1卷积压缩4倍到64个通道，之后3×3的卷积核用于处理特征，经1×1卷积扩大通道数与原特征残差连接后输出。

ResNeXt也是相同的处理策略，但在ResNeXt中，输入的具有256个通道的特征被分为32个组，每组被压缩64倍到4个通道后进行处理。32个组相加后与原特征残差连接后输出。这里cardinatity指的是一个block中所具有的相同分支的数目。

分组卷积
ResNeXt中采用的分组卷机简单来说就是将特征图分为不同的组，再对每组特征图分别进行卷积，这个操作可以有效的降低计算量。
在分组卷积中，每个卷积核只处理部分通道，比如下图中，红色卷积核只处理红色的通道，绿色卷积核只处理绿色通道，黄色卷积核只处理黄色通道。此时每个卷积核有2个通道，每个卷积核生成一张特征图。

总结来说就是：ResNeXt-50网络简单讲就是在ResNet结构的基础上采用了聚合残差结构和局部连接结构，同时引入了Random Erasing和Mixup等数据增强和正则化方法。 

二.代码部分

import os,PIL,random,pathlib
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
 
 
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
print(device)
 
data_dir = './data4/'
data_dir = pathlib.Path(data_dir)
 
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
print(classeNames)
 
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为：", image_count)

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("./data4/", transform=train_transforms)
print(total_data.class_to_idx)
 
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

模型

class BN_Conv2d(nn.Module):
    """
    BN_CONV_RELU
    """
 
    def __init__(self, in_channels, out_channels, kernel_size, stride, padding, dilation=1, groups=1, bias=False):
        super(BN_Conv2d, self).__init__()
        self.seq = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=kernel_size, stride=stride,
                      padding=padding, dilation=dilation, groups=groups, bias=bias),
            nn.BatchNorm2d(out_channels)
        )
 
    def forward(self, x):
        return F.relu(self.seq(x))
 
class ResNeXt_Block(nn.Module):
    """
    ResNeXt block with group convolutions
    """
 
    def __init__(self, in_chnls, cardinality, group_depth, stride):
        super(ResNeXt_Block, self).__init__()
        self.group_chnls = cardinality * group_depth
        self.conv1 = BN_Conv2d(in_chnls, self.group_chnls, 1, stride=1, padding=0)
        self.conv2 = BN_Conv2d(self.group_chnls, self.group_chnls, 3, stride=stride, padding=1, groups=cardinality)
        self.conv3 = nn.Conv2d(self.group_chnls, self.group_chnls*2, 1, stride=1, padding=0)
        self.bn = nn.BatchNorm2d(self.group_chnls*2)
        self.short_cut = nn.Sequential(
            nn.Conv2d(in_chnls, self.group_chnls*2, 1, stride, 0, bias=False),
            nn.BatchNorm2d(self.group_chnls*2)
        )
 
    def forward(self, x):
        out = self.conv1(x)
        out = self.conv2(out)
        out = self.bn(self.conv3(out))
        out += self.short_cut(x)
        return F.relu(out)
 
class ResNeXt(nn.Module):
    """
    ResNeXt builder
    """
 
    def __init__(self, layers: object, cardinality, group_depth, num_classes) -> object:
        super(ResNeXt, self).__init__()
        self.cardinality = cardinality
        self.channels = 64
        self.conv1 = BN_Conv2d(3, self.channels, 7, stride=2, padding=3)
        d1 = group_depth
        self.conv2 = self.___make_layers(d1, layers[0], stride=1)
        d2 = d1 * 2
        self.conv3 = self.___make_layers(d2, layers[1], stride=2)
        d3 = d2 * 2
        self.conv4 = self.___make_layers(d3, layers[2], stride=2)
        d4 = d3 * 2
        self.conv5 = self.___make_layers(d4, layers[3], stride=2)
        self.fc = nn.Linear(self.channels, num_classes)   # 224x224 input size
 
    def ___make_layers(self, d, blocks, stride):
        strides = [stride] + [1] * (blocks-1)
        layers = []
        for stride in strides:
            layers.append(ResNeXt_Block(self.channels, self.cardinality, d, stride))
            self.channels = self.cardinality*d*2
        return nn.Sequential(*layers)
 
    def forward(self, x):
        out = self.conv1(x)
        out = F.max_pool2d(out, 3, 2, 1)
        out = self.conv2(out)
        out = self.conv3(out)
        out = self.conv4(out)
        out = self.conv5(out)
        out = F.avg_pool2d(out, 7)
        out = out.view(out.size(0), -1)
        out = F.softmax(self.fc(out),dim=1)
        return out

# 定义完成，测试一下
import torch.nn.functional as F
model = ResNeXt([3, 4, 6, 3], 32, 4, 4)
model.to(device)
 
# 统计模型参数量以及其他指标
import torchsummary as summary
summary.summary(model, (3, 224, 224))

import copy
 
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
loss_fn = nn.CrossEntropyLoss()  # 创建损失函数
 
epochs = 10
 
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):
    # 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_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')

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()

指定图片预测

 
from PIL import Image
 
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='./data/Others/NM01_01_01.jpg',
                  model=model,
                  transform=train_transforms,
                  classes=classes)