P8学习笔记

  • ** 🍨 本文为[🔗365
    天深度学习训练营](https: // mp.weixin.qq.com / s / 0dvHCaOoFnW8SCp3JpzKxg)
    中的学习记录博客 **
  • ** 🍖 原作者:[K同学啊](https: // mtyjkh.blog.csdn.net /) **

设置GPU

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")
device
device(type='cuda')
# 导入数据
import os,PIL,random,pathlib

data_dir = r'C:\Users\11054\Desktop\kLearning\p1_data'
data_dir = pathlib.Path(data_dir)

data_paths  = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[-1] for path in data_paths]
classeNames
['cloudy', 'rain', 'shine', 'sunrise']
# 关于transforms.Compose的更多介绍可以参考:https://blog.csdn.net/qq_38251616/article/details/124878863
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(r"C:\Users\11054\Desktop\kLearning\p1_data",transform=train_transforms)
total_data
Dataset ImageFolder
    Number of datapoints: 1125
    Root location: C:\Users\11054\Desktop\kLearning\p1_data
    StandardTransform
Transform: Compose(
               Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=True)
               ToTensor()
               Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
           )

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])

batch_size = 4

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
Shape of X [N, C, H, W]:  torch.Size([4, 3, 224, 224])
Shape of y:  torch.Size([4]) torch.int64

搭建包含C3模块的模型

import torch.nn.functional as F

def autopad(k, p=None):  # kernel, padding
    # Pad to 'same'
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p

class Conv(nn.Module):
    # Standard convolution
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())

    def forward(self, x):
        return self.act(self.bn(self.conv(x)))

class Bottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_, c2, 3, 1, g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))

class C3(nn.Module):
    # CSP Bottleneck with 3 convolutions
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))

    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))

class model_K(nn.Module):
    def __init__(self):
        super(model_K, self).__init__()

        # 卷积模块
        self.Conv = Conv(3, 32, 3, 2)

        # C3模块1
        self.C3_1 = C3(32, 64, 3, 2)

        # 全连接网络层,用于分类
        self.classifier = nn.Sequential(
            nn.Linear(in_features=802816, out_features=100),
            nn.ReLU(),
            nn.Linear(in_features=100, out_features=4)
        )

    def forward(self, x):
        x = self.Conv(x)
        x = self.C3_1(x)
        x = torch.flatten(x, start_dim=1)
        x = self.classifier(x)

        return x

device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))

model = model_K().to(device)
model
Using cuda device





model_K(
  (Conv): Conv(
    (conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act): SiLU()
  )
  (C3_1): C3(
    (cv1): Conv(
      (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv2): Conv(
      (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv3): Conv(
      (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
        (cv2): Conv(
          (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
      )
      (1): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
        (cv2): Conv(
          (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
      )
      (2): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
        (cv2): Conv(
          (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
      )
    )
  )
  (classifier): Sequential(
    (0): Linear(in_features=802816, out_features=100, bias=True)
    (1): ReLU()
    (2): Linear(in_features=100, out_features=4, bias=True)
  )
)

查看模型

# 统计模型参数量以及其他指标
import torchsummary as summary
summary.summary(model, (3, 224, 224))
----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1         [-1, 32, 112, 112]             864
       BatchNorm2d-2         [-1, 32, 112, 112]              64
              SiLU-3         [-1, 32, 112, 112]               0
              Conv-4         [-1, 32, 112, 112]               0
            Conv2d-5         [-1, 32, 112, 112]           1,024
       BatchNorm2d-6         [-1, 32, 112, 112]              64
              SiLU-7         [-1, 32, 112, 112]               0
              Conv-8         [-1, 32, 112, 112]               0
            Conv2d-9         [-1, 32, 112, 112]           1,024
      BatchNorm2d-10         [-1, 32, 112, 112]              64
             SiLU-11         [-1, 32, 112, 112]               0
             Conv-12         [-1, 32, 112, 112]               0
           Conv2d-13         [-1, 32, 112, 112]           9,216
      BatchNorm2d-14         [-1, 32, 112, 112]              64
             SiLU-15         [-1, 32, 112, 112]               0
             Conv-16         [-1, 32, 112, 112]               0
       Bottleneck-17         [-1, 32, 112, 112]               0
           Conv2d-18         [-1, 32, 112, 112]           1,024
      BatchNorm2d-19         [-1, 32, 112, 112]              64
             SiLU-20         [-1, 32, 112, 112]               0
             Conv-21         [-1, 32, 112, 112]               0
           Conv2d-22         [-1, 32, 112, 112]           9,216
      BatchNorm2d-23         [-1, 32, 112, 112]              64
             SiLU-24         [-1, 32, 112, 112]               0
             Conv-25         [-1, 32, 112, 112]               0
       Bottleneck-26         [-1, 32, 112, 112]               0
           Conv2d-27         [-1, 32, 112, 112]           1,024
      BatchNorm2d-28         [-1, 32, 112, 112]              64
             SiLU-29         [-1, 32, 112, 112]               0
             Conv-30         [-1, 32, 112, 112]               0
           Conv2d-31         [-1, 32, 112, 112]           9,216
      BatchNorm2d-32         [-1, 32, 112, 112]              64
             SiLU-33         [-1, 32, 112, 112]               0
             Conv-34         [-1, 32, 112, 112]               0
       Bottleneck-35         [-1, 32, 112, 112]               0
           Conv2d-36         [-1, 32, 112, 112]           1,024
      BatchNorm2d-37         [-1, 32, 112, 112]              64
             SiLU-38         [-1, 32, 112, 112]               0
             Conv-39         [-1, 32, 112, 112]               0
           Conv2d-40         [-1, 64, 112, 112]           4,096
      BatchNorm2d-41         [-1, 64, 112, 112]             128
             SiLU-42         [-1, 64, 112, 112]               0
             Conv-43         [-1, 64, 112, 112]               0
               C3-44         [-1, 64, 112, 112]               0
           Linear-45                  [-1, 100]      80,281,700
             ReLU-46                  [-1, 100]               0
           Linear-47                    [-1, 4]             404
================================================================
Total params: 80,320,536
Trainable params: 80,320,536
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 150.06
Params size (MB): 306.40
Estimated Total Size (MB): 457.04
----------------------------------------------------------------

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

测试模型

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

正式训练

import copy

optimizer  = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn    = nn.CrossEntropyLoss() # 创建损失函数

epochs     = 20

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):

    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)

    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')
Epoch: 1, Train_acc:83.6%, Train_loss:0.683, Test_acc:86.2%, Test_loss:0.633, Lr:1.00E-04
Epoch: 2, Train_acc:92.6%, Train_loss:0.326, Test_acc:90.2%, Test_loss:0.388, Lr:1.00E-04
Epoch: 3, Train_acc:96.2%, Train_loss:0.120, Test_acc:91.1%, Test_loss:0.472, Lr:1.00E-04
Epoch: 4, Train_acc:96.2%, Train_loss:0.132, Test_acc:92.4%, Test_loss:0.490, Lr:1.00E-04
Epoch: 5, Train_acc:96.7%, Train_loss:0.156, Test_acc:84.4%, Test_loss:1.356, Lr:1.00E-04
Epoch: 6, Train_acc:98.6%, Train_loss:0.048, Test_acc:87.1%, Test_loss:0.810, Lr:1.00E-04
Epoch: 7, Train_acc:99.0%, Train_loss:0.028, Test_acc:89.3%, Test_loss:0.451, Lr:1.00E-04
Epoch: 8, Train_acc:99.7%, Train_loss:0.010, Test_acc:89.8%, Test_loss:0.478, Lr:1.00E-04
Epoch: 9, Train_acc:97.3%, Train_loss:0.142, Test_acc:82.2%, Test_loss:1.050, Lr:1.00E-04
Epoch:10, Train_acc:97.2%, Train_loss:0.150, Test_acc:83.6%, Test_loss:1.354, Lr:1.00E-04
Epoch:11, Train_acc:98.7%, Train_loss:0.039, Test_acc:87.6%, Test_loss:0.996, Lr:1.00E-04
Epoch:12, Train_acc:99.2%, Train_loss:0.034, Test_acc:88.9%, Test_loss:0.624, Lr:1.00E-04
Epoch:13, Train_acc:99.9%, Train_loss:0.005, Test_acc:92.4%, Test_loss:0.669, Lr:1.00E-04
Epoch:14, Train_acc:99.7%, Train_loss:0.011, Test_acc:87.6%, Test_loss:1.265, Lr:1.00E-04
Epoch:15, Train_acc:99.2%, Train_loss:0.027, Test_acc:89.3%, Test_loss:0.874, Lr:1.00E-04
Epoch:16, Train_acc:100.0%, Train_loss:0.001, Test_acc:88.9%, Test_loss:0.884, Lr:1.00E-04
Epoch:17, Train_acc:100.0%, Train_loss:0.002, Test_acc:88.9%, Test_loss:0.866, Lr:1.00E-04
Epoch:18, Train_acc:99.9%, Train_loss:0.003, Test_acc:90.7%, Test_loss:0.731, Lr:1.00E-04
Epoch:19, Train_acc:99.7%, Train_loss:0.006, Test_acc:85.8%, Test_loss:1.096, Lr:1.00E-04
Epoch:20, Train_acc:98.9%, Train_loss:0.052, Test_acc:89.8%, Test_loss:1.306, Lr:1.00E-04
Done

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

best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)
epoch_test_acc, epoch_test_loss
(0.9244444444444444, 0.3306928659242083)

个人总结

结构特点

  • 跨阶段特征融合:C3 模块利用 CSP 结构将特征图分为两部分,一部分直接通过,而另一部分则通过一系列卷积层。最后,这两部分在深度上合并。这种结构可以减少计算量,同时保持或提高网络性能。

  • 瓶颈设计:在卷积层中,C3 模块通常使用瓶颈设计(即先降维、再升维),这有助于减少参数数量和计算成本,同时仍然可以学习到有效的特征表示。

  • 残差连接:C3 模块中的卷积层经常会包含残差连接,这有助于信息在网络中的传播并减少梯度消失的问题,特别是在深层网络中。

实现细节

  • 卷积层:C3 模块中的卷积层包括批量归一化(Batch Normalization)和激活函数(如 Leaky ReLU 或 Mish)。

  • 组合特征:C3 模块通过将输入特征图分成两个分支,然后在经过一系列操作后再次融合,从而实现特征的组合。这样做可以减少冗余并增强特征的表达能力。

  • 模块化和可重用性:C3 模块的设计使得它可以在网络中多次重用,有助于构建更深但计算效率更高的网络。

性能和效率

  • 减少计算量:与传统的卷积层相比,C3 模块通过减少中间特征图的宽度来减少计算量。

  • 加速推理:C3 模块的结构设计有助于加快推理速度,使得 YOLOv5 在保持较高检测精度的同时仍然适用于实时应用。

  • 优化内存使用:由于减少了参数数量和计算量,C3 模块有助于降低网络的内存占用。

  • 3
    点赞
  • 5
    收藏
    觉得还不错? 一键收藏
  • 1
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
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
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