P4学习笔记

无涯学徒1998

已于 2024-04-05 11:07:42 修改

阅读量520

点赞数 15

文章标签： python

于 2024-04-05 11:07:00 首次发布

本文链接：https://blog.csdn.net/Inface0443/article/details/137396279

版权

🍨 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

猴痘病识别

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

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

device

读取文件夹


import os,PIL,random,pathlib

data_dir = r'C:\Users\11054\Desktop\kLearning\p4_learning\data'
data_dir = pathlib.Path(data_dir)

data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[-1] for path in data_paths]
classeNames

写入数据

total_datadir = data_dir

# 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.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(total_datadir,transform=train_transforms)
print(total_data)
total_data.class_to_idx

Dataset ImageFolder
    Number of datapoints: 2142
    Root location: C:\Users\11054\Desktop\kLearning\p4_learning\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])
           )





{'Monkeypox': 0, 'Others': 1}

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)
train_size,test_size

<torch.utils.data.dataset.Subset object at 0x000002AB506266D0> <torch.utils.data.dataset.Subset object at 0x000002AB50626DC0>





(1713, 429)

导入数据集

batch_size = 32

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([32, 3, 224, 224])
Shape of y:  torch.Size([32]) torch.int64

torch.utils.data.DataLoader 是 PyTorch 中用于加载和管理数据的一个实用工具类。它允许你以小批次的方式迭代你的数据集，这对于训练神经网络和其他机器学习任务非常有用。DataLoader 构造函数接受多个参数，下面是一些常用的参数及其解释：

dataset（必需参数）：这是你的数据集对象，通常是 torch.utils.data.Dataset 的子类，它包含了你的数据样本。
batch_size（可选参数）：指定每个小批次中包含的样本数。默认值为 1。
shuffle（可选参数）：如果设置为 True，则在每个 epoch 开始时对数据进行洗牌，以随机打乱样本的顺序。这对于训练数据的随机性很重要，以避免模型学习到数据的顺序性。默认值为 False。
num_workers（可选参数）：用于数据加载的子进程数量。通常，将其设置为大于 0 的值可以加快数据加载速度，特别是当数据集很大时。默认值为 0，表示在主进程中加载数据。
pin_memory（可选参数）：如果设置为 True，则数据加载到 GPU 时会将数据存储在 CUDA 的锁页内存中，这可以加速数据传输到 GPU。默认值为 False。
drop_last（可选参数）：如果设置为 True，则在最后一个小批次可能包含样本数小于 batch_size 时，丢弃该小批次。这在某些情况下很有用，以确保所有小批次具有相同的大小。默认值为 False。
timeout（可选参数）：如果设置为正整数，它定义了每个子进程在等待数据加载器传递数据时的超时时间（以秒为单位）。这可以用于避免子进程卡住的情况。默认值为 0，表示没有超时限制。
worker_init_fn（可选参数）：一个可选的函数，用于初始化每个子进程的状态。这对于设置每个子进程的随机种子或其他初始化操作很有用。

创建模型

import torch.nn.functional as F

class Network_bn(nn.Module):
    def __init__(self):
        super(Network_bn, self).__init__()
        """
        nn.Conv2d()函数：
        第一个参数（in_channels）是输入的channel数量
        第二个参数（out_channels）是输出的channel数量
        第三个参数（kernel_size）是卷积核大小
        第四个参数（stride）是步长，默认为1
        第五个参数（padding）是填充大小，默认为0
        """
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(12)
        self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=0)
        self.bn2 = nn.BatchNorm2d(12)
        self.pool = nn.MaxPool2d(2,2)
        self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn4 = nn.BatchNorm2d(24)
        self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn5 = nn.BatchNorm2d(24)
        self.fc1 = nn.Linear(24*50*50, len(classeNames))

    def forward(self, x):
        x = F.relu(self.bn1(self.conv1(x)))
        x = F.relu(self.bn2(self.conv2(x)))
        x = self.pool(x)
        x = F.relu(self.bn4(self.conv4(x)))
        x = F.relu(self.bn5(self.conv5(x)))
        x = self.pool(x)
        x = x.view(-1, 24*50*50)
        x = self.fc1(x)

        return x

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

model = Network_bn().to(device)
model

Using cuda device





Network_bn(
  (conv1): Conv2d(3, 12, kernel_size=(5, 5), stride=(1, 1))
  (bn1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (conv2): Conv2d(12, 12, kernel_size=(5, 5), stride=(1, 1))
  (bn2): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv4): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))
  (bn4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (conv5): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1))
  (bn5): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (fc1): Linear(in_features=60000, out_features=2, bias=True)
)

编写训练方法

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

编写测试方法

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

正式训练

loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-4 # 学习率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

epochs     = 20
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')

Epoch: 1, Train_acc:55.6%, Train_loss:0.698, Test_acc:58.5%，Test_loss:0.688
Epoch: 2, Train_acc:67.1%, Train_loss:0.621, Test_acc:69.7%，Test_loss:0.619
Epoch: 3, Train_acc:70.2%, Train_loss:0.587, Test_acc:71.8%，Test_loss:0.579
Epoch: 4, Train_acc:74.4%, Train_loss:0.532, Test_acc:71.6%，Test_loss:0.576
Epoch: 5, Train_acc:77.5%, Train_loss:0.506, Test_acc:76.7%，Test_loss:0.548
Epoch: 6, Train_acc:80.7%, Train_loss:0.470, Test_acc:77.4%，Test_loss:0.520
Epoch: 7, Train_acc:83.0%, Train_loss:0.445, Test_acc:77.4%，Test_loss:0.499
Epoch: 8, Train_acc:83.4%, Train_loss:0.426, Test_acc:76.5%，Test_loss:0.505
Epoch: 9, Train_acc:84.2%, Train_loss:0.412, Test_acc:80.2%，Test_loss:0.477
Epoch:10, Train_acc:86.6%, Train_loss:0.387, Test_acc:78.8%，Test_loss:0.474
Epoch:11, Train_acc:87.2%, Train_loss:0.372, Test_acc:80.4%，Test_loss:0.456
Epoch:12, Train_acc:88.6%, Train_loss:0.358, Test_acc:80.2%，Test_loss:0.467
Epoch:13, Train_acc:88.4%, Train_loss:0.344, Test_acc:80.9%，Test_loss:0.433
Epoch:14, Train_acc:89.7%, Train_loss:0.331, Test_acc:81.4%，Test_loss:0.431
Epoch:15, Train_acc:90.5%, Train_loss:0.316, Test_acc:80.4%，Test_loss:0.453
Epoch:16, Train_acc:89.7%, Train_loss:0.314, Test_acc:80.0%，Test_loss:0.417
Epoch:17, Train_acc:90.8%, Train_loss:0.295, Test_acc:81.8%，Test_loss:0.414
Epoch:18, Train_acc:91.8%, Train_loss:0.285, Test_acc:81.4%，Test_loss:0.406
Epoch:19, Train_acc:91.8%, Train_loss:0.280, Test_acc:81.6%，Test_loss:0.412
Epoch:20, Train_acc:92.2%, Train_loss:0.272, Test_acc:84.6%，Test_loss:0.401
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

指定图片进行预测

torch.squeeze()详解
对数据的维度进行压缩，去掉维数为1的的维度

x = torch.zeros(2, 1, 2, 1, 2)
print(x.size())
y = torch.squeeze(x)
print(y.size())
y = torch.squeeze(x, 0)
print(y.size())
y = torch.squeeze(x, 1)
print(y.size())

torch.Size([2, 1, 2, 1, 2])
torch.Size([2, 2, 2])
torch.Size([2, 1, 2, 1, 2])
torch.Size([2, 2, 1, 2])

torch.unsqueeze()
对数据维度进行扩充。给指定位置加上维数为一的维度

x = torch.tensor([1, 2, 3, 4])
print(torch.unsqueeze(x, 0))
print(torch.unsqueeze(x, 1))

tensor([[1, 2, 3, 4]])
tensor([[1],
        [2],
        [3],
        [4]])

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=r'C:\Users\11054\Desktop\kLearning\p4_learning\data\Others\NM01_01_00.jpg',
                  model=model,
                  transform=train_transforms,
                  classes=classes)

预测结果是：Others

# 模型保存
PATH = r'C:\Users\11054\Desktop\kLearning\p4_learning\model.pth'  # 保存的参数文件名
torch.save(model.state_dict(), PATH)

# 将参数加载到model当中
model.load_state_dict(torch.load(PATH, map_location=device))