Pytorch从零开始实战04

Pytorch从零开始实战——猴痘病识别

本系列来源于365天深度学习训练营

原作者K同学

环境准备

本文基于Jupyter notebook，使用Python3.8，Pytorch2.0.1+cu118，torchvision0.15.2，需读者自行配置好环境且有一些深度学习理论基础。本次实验的目的是学习模型的保存和预测单张图片的结果。
第一步，导入常用包。

import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision
import torch.nn.functional as F
import torchvision.transforms as transforms
import random
import time
import numpy as np
import pandas as pd
import datetime
import gc
import pathlib
import os
import PIL
os.environ['KMP_DUPLICATE_LIB_OK']='True'  # 用于避免jupyter环境突然关闭
torch.backends.cudnn.benchmark=True  # 用于加速GPU运算的代码

创建设备对象

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

设置随机数种子

torch.manual_seed(428)
torch.cuda.manual_seed(428)
torch.cuda.manual_seed_all(428)
random.seed(428)
np.random.seed(428)

数据集

本次实验使用猴痘病图片数据集，共2142张图片，分别为有猴痘病的图片和没有猴痘病的图片，
两种类别的图片分别存在两个文件夹中。

data_dir = './data/monkeydata'
data_dir = pathlib.Path(data_dir)

data_paths = list(data_dir.glob('*'))
classNames = [str(path).split("/")[2] for path in data_paths]
classNames # ['Monkeypox', 'Others']

对数据通过dataset读取，并且将文件夹名设置为标签。

total_datadir = './data/monkeydata'
train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),
    transforms.ToTensor(),
    transforms.Normalize(
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225]
    )
])
total_data = torchvision.datasets.ImageFolder(total_datadir, transform=train_transforms)
total_data

我们可以查看所有标签

total_data.class_to_idx # {'Monkeypox': 0, 'Others': 1}

接下来划分数据集，以8比2划分训练集和测试集

# 划分数据集
train_size = int(0.8 * len(total_data))
test_size = len(total_data) - train_size
train_ds, test_ds = torch.utils.data.random_split(total_data, [train_size, test_size])
len(train_ds), len(test_ds)

随机查看5张图片

def plotsample(data):
    fig, axs = plt.subplots(1, 5, figsize=(10, 10)) #建立子图
    for i in range(5):
        num = random.randint(0, len(data) - 1) #首先选取随机数，随机选取五次
        #抽取数据中对应的图像对象，make_grid函数可将任意格式的图像的通道数升为3，而不改变图像原始的数据
        #而展示图像用的imshow函数最常见的输入格式也是3通道
        npimg = torchvision.utils.make_grid(data[num][0]).numpy()
        nplabel = data[num][1] #提取标签 
        #将图像由(3, weight, height)转化为(weight, height, 3)，并放入imshow函数中读取
        axs[i].imshow(np.transpose(npimg, (1, 2, 0))) 
        axs[i].set_title(nplabel) #给每个子图加上标签
        axs[i].axis("off") #消除每个子图的坐标轴

plotsample(train_ds)

使用DataLoader划分批次和打乱数据集

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, shuffle=True)
for X, y in test_dl:
    print(X.shape) # 32, 3, 224, 224
    print(y) # 1, 0, 1, 1, 1, 1, 0....
    break
print(len(train_dl.dataset) + len(test_dl.dataset)) # 2142

模型选择

本次实验第一次选择的是一个简单的卷积神经网络，经过卷积+卷积+池化+卷积+卷积+池化+线性层，并中间进行数据归一化处理。

class Model(nn.Module):
    def __init__(self):
        super().__init__()

        self.conv1 = nn.Conv2d(3, 12, kernel_size=5, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(12)
        self.conv2 = nn.Conv2d(12, 12, kernel_size=5, stride=1, padding=0)
        self.bn2 = nn.BatchNorm2d(12)
        self.pool = nn.MaxPool2d(2)
        self.conv3 = nn.Conv2d(12, 24, kernel_size=5, stride=1, padding=0)
        self.bn3 = nn.BatchNorm2d(24)
        self.conv4 = nn.Conv2d(24, 24, kernel_size=5, stride=1, padding=0)
        self.bn4 = nn.BatchNorm2d(24)

        self.fc1 = nn.Linear(24 * 50 * 50, len(classNames))

    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.bn3(self.conv3(x)))     
        x = F.relu(self.bn4(self.conv4(x))) 
        x = self.pool(x)  
        x = x.view(-1, 24 * 50 * 50)
        x = self.fc1(x)
        return x;

使用summary查看模型

from torchsummary import summary
# 将模型转移到GPU中
model = Model().to(device)
summary(model, input_size=(3, 224, 224))

模型训练

训练函数

def train(dataloader, model, loss_fn, opt):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    train_acc, train_loss = 0, 0

    for X, y in dataloader:
        X, y = X.to(device), y.to(device)
        pred = model(X)
        loss = loss_fn(pred, y)

        opt.zero_grad()
        loss.backward()
        opt.step()

        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

测试函数

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    test_acc, test_loss = 0, 0
    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            pred = model(X)
            loss = loss_fn(pred, y)
    
            test_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
            test_loss += loss.item()

    test_acc /= size
    test_loss /= num_batches
    return test_acc, test_loss

定义一些超参数，经实验，将学习率设置为0.01效果最好。

loss_fn = nn.CrossEntropyLoss()
learn_rate = 0.01
opt = torch.optim.SGD(model.parameters(), lr=learn_rate)

开始训练，epochs设置为20，并且将训练集的最优结果保存。

import time
epochs = 20
train_loss = []
train_acc = []
test_loss = []
test_acc = []

T1 = time.time()

best_acc = 0
PATH = './my_model.pth'

for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
    
    model.eval() # 确保模型不会进行训练操作
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)

    if epoch_test_acc > best_acc:
        best_acc = epoch_test_acc
        torch.save(model.state_dict(), PATH)
        print("model save")
        
        
    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)
    
    print("epoch:%d, train_acc:%.1f%%, train_loss:%.3f, test_acc:%.1f%%, test_loss:%.3f"
          % (epoch + 1, epoch_train_acc * 100, epoch_train_loss, epoch_test_acc * 100, epoch_test_loss))
print("Done")
T2 = time.time()
print('程序运行时间:%s毫秒' % ((T2 - T1)*1000))

可以看到，最好的时候，测试集准确率达到百分之91.8

数据可视化

使用matplotlib进行数据可视化。

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()

其他模型

本次实验也使用了ResNet模型，虽然参数量较大，但训练效果较好
定义模型

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        
        # 创建预训练的ResNet-18模型
        self.resnet = torchvision.models.resnet18(pretrained=True)
        
        # 将ResNet的最后一层（全连接层）替换为适合二分类问题的新全连接层
        self.resnet.fc = nn.Linear(self.resnet.fc.in_features, len(classes))
        
    def forward(self, x):
        return self.resnet(x)

from torchsummary import summary
# 将模型转移到GPU中
model = Model().to(device)

经实验，把学习率设置为0.001，效果较好

import time
epochs = 50
train_loss = []
train_acc = []
test_loss = []
test_acc = []

loss_fn = nn.CrossEntropyLoss()
learn_rate = 0.001
opt = torch.optim.SGD(model.parameters(), lr=learn_rate)

T1 = time.time()

best_acc = 0
PATH = './my_model.pth'

for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
    
    model.eval() # 确保模型不会进行训练操作
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)

    if epoch_test_acc > best_acc:
        best_acc = epoch_test_acc
        torch.save(model.state_dict(), PATH)
        print("model save")
        
        
    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)
    
    print("epoch:%d, train_acc:%.1f%%, train_loss:%.3f, test_acc:%.1f%%, test_loss:%.3f"
          % (epoch + 1, epoch_train_acc * 100, epoch_train_loss, epoch_test_acc * 100, epoch_test_loss))
print("Done")
T2 = time.time()
print('程序运行时间:%s毫秒' % ((T2 - T1)*1000))

最终在测试集的准确率可达到97.2%。

可视化训练过程

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()

图片预测

img_path：要进行预测的图像文件的路径。
model：用于进行图像分类预测的深度学习模型。
transform：用于对图像进行预处理的数据转换函数。
classes：包含类别标签的列表，用于将模型的输出索引映射回类别标签。
大致意思是图像与训练时的输入数据格式相匹配，模型接受批量输入，因此我们需要在维度上添加一个批次维度，从而进行预测

classes = list(total_data.class_to_idx)
def predict_img(img_path, model, transform, classes):
    test_img = Image.open(img_path).convert('RGB')
    test_img = transform(test_img)
    img = test_img.to(device).unsqueeze(0)
    model.eval()
    output = model(img)
    _, pred = torch.max(output, 1) # 在张量的第一个维度上取最大值操作
    pred_class = classes[pred]
    print(f'预测结果是：{pred_class}')

开始预测

predict_img(img_path='./data/monkeydata/Monkeypox/M01_01_00.jpg', 
                  model=model, 
                  transform=train_transforms, 
                  classes=classes)
# 预测结果是：Monkeypox