P2-彩色识别

这次实战和之前的mnist实战相似度非常高,只需要改个模型和数据加载就可以直接套用之前的步骤,但是我发现这次的准确率不尽人意,所以决定换个模型提高准确率

>- 🍨 本文为[ 🔗 365天深度学习训练营]( https://mp.weixin.qq.com/s/xLjALoOD8HPZcH563En8bQ) 中的学习记录博客
>- 🍦 参考文章：[365天深度学习训练营-第P2周：彩色识别]( https://mp.weixin.qq.com/s/BKsTrlOtu32bQzgORaMLEw)
>- 🍖 原作者：[K同学啊|接辅导、项目定制]( https://mtyjkh.blog.csdn.net/)

一、 前期准备

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 matplotlib.pyplot as plt
import torchvision
import torch.nn.functional as F
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

二、导入数据

使用dataset下载CIFAR10数据集，并划分好训练集与测试集

使用dataloader加载数据，并设置好基本的batch_size

train_ds = torchvision.datasets.CIFAR10('data', 
                                      train=True, 
                                      transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                      download=True)

test_ds  = torchvision.datasets.CIFAR10('data', 
                                      train=False, 
                                      transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                      download=True)

batch_size = 32

train_dl = torch.utils.data.DataLoader(train_ds, 
                                       batch_size=batch_size, 
                                       shuffle=True)

test_dl  = torch.utils.data.DataLoader(test_ds, 
                                       batch_size=batch_size)

三、设置模型

import torch.nn.functional as F

num_classes = 10  # 图片的类别数

class Model(nn.Module):
     def __init__(self):
        super().__init__()
         # 特征提取网络
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3)   # 第一层卷积,卷积核大小为3*3
        self.pool1 = nn.MaxPool2d(kernel_size=2)       # 设置池化层，池化核大小为2*2
        self.conv2 = nn.Conv2d(64, 64, kernel_size=3)  # 第二层卷积,卷积核大小为3*3   
        self.pool2 = nn.MaxPool2d(kernel_size=2) 
        self.conv3 = nn.Conv2d(64, 128, kernel_size=3) # 第二层卷积,卷积核大小为3*3   
        self.pool3 = nn.MaxPool2d(kernel_size=2) 
                                      
        # 分类网络
        self.fc1 = nn.Linear(512, 256)          
        self.fc2 = nn.Linear(256, num_classes)
     # 前向传播
     def forward(self, x):
        x = self.pool1(F.relu(self.conv1(x)))     
        x = self.pool2(F.relu(self.conv2(x)))
        x = self.pool3(F.relu(self.conv3(x)))
        
        x = torch.flatten(x, start_dim=1)

        x = F.relu(self.fc1(x))
        x = self.fc2(x)
       
        return x
#查看模型
from torchinfo import summary
# 将模型转移到GPU中（我们模型运行均在GPU中进行）
model = Model().to(device)

summary(model)

四、 训练模型

1.设置优化器,损失函数,学习率

loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-2 # 学习率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

2.定义训练,验证函数

训练函数

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小，一共60000张图片
    num_batches = len(dataloader)   # 批次数目，1875（60000/32）

    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loss
        train_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()
            
    train_acc  /= size
    train_loss /= num_batches

    return train_acc, train_loss

验证函数

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 测试集的大小，一共10000张图片
    num_batches = len(dataloader)          # 批次数目，313（10000/32=312.5，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

五. 正式训练

epochs     = 10
train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []

for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
    
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
    
    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)
    
    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%，Test_loss:{:.3f}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')

六、 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()

分析:

虽然训练次数少,还有提升空间,但是感觉也不多最多0.7附近

于是我用残差网络模型训练,结果训练了5次就80%多了,虽然训练时长比较长,但是提升空间还有，可能达到90%,只是训练次数太少,时间短,所以效果还没达到

下面是resnet结果,可以看成效果非常好,趋势肯定能突破90%

模型改进

这里我用的是resnet18,利用下图的resnet18组成,我们可以创建一个resnet18模型

首先上图中可以看出,resnet的5个卷积层的卷积核都说有规律的,因此可以先创建一个基本组件,通过传参,调整输入输出通道数

构建基本组件

# 构建ResNet18的网络基础模块
class BasicBlock(nn.Module):
    def __init__(self, in_planes, planes, stride=1):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(
            in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3,
                               stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)

        self.shortcut = nn.Sequential()
        if stride != 1 or in_planes !=  planes:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_planes, planes,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d( planes)
            )

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        out += self.shortcut(x)
        out = F.relu(out)
        return out

搭建模型

# 搭建ResNet模板块
class ResNet(nn.Module):
    def __init__(self, block, num_blocks, num_classes=10):
        super(ResNet, self).__init__()
        self.in_planes = 64
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3,
                               stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        # 逐层搭建ResNet
        self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
        self.linear = nn.Linear(512, num_classes)

        # 参数初始化
        # for m in self.modules():
        #     if isinstance(m, nn.Conv2d):
        #         nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
        #     elif isinstance(m, nn.BatchNorm2d):
        #         nn.init.constant_(m.weight, 1)
        #         nn.init.constant_(m.bias, 0)

    def _make_layer(self, block, planes, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)
        layers = []
        for stride in strides:
            layers.append(block(self.in_planes, planes, stride))
            self.in_planes = planes
        return nn.Sequential(*layers)

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = F.avg_pool2d(out, 4)
        out = out.view(out.size(0), -1)
        out = self.linear(out)
        return out
def ResNet18():
    return ResNet(BasicBlock, [2, 2, 2, 2])