pytorch+PyQt5实战：ResNet-18实现CLFAR-10图像分类，并利用PyQt5进行人机界面显示

实验环境：

1.pytorch-1.6.0
2.python-3.7.9
3.window-10
4.pycharm
5.pyqt5(相应的QT Designer及工具包)

CLFAR-10的数据集

作为一个初学者，在官网下载CLFAR-10的数据集下载速度不仅慢，而且不是常用的图片格式，这里是转换后的数据集，有需要的可以直接百度云盘提取。
链接：https://pan.baidu.com/s/1l7wvWLCscPcGoKzRjggjRA
提取码：ht88

ResNet-18网络：

ResNet全名Residual Network残差网络。残差网络是由何凯明所提出的，他的《Deep Residual Learning for Image Recognition》获得了当年CVPR最佳论文。他提出的深度残差网络在2015年可以说是洗刷了图像方面的各大比赛，以绝对优势取得了多个比赛的冠军。而且它在保证网络精度的前提下，将网络的深度达到了152层，后来又进一步加到1000的深度。我们这里用到的是一个18 层的残差网络。
网络结构如下：

残差学习：一个构建单元

在pytorch上搭建ResNet-18模型

一、新建resnet.py文件

代码如下：

import torch.nn as nn
import torch.nn.functional as F

class ResidualBlock(nn.Module):
    def __init__(self, inchannel, outchannel, stride=1):
        super(ResidualBlock, self).__init__()
        self.left = nn.Sequential(
            nn.Conv2d(inchannel, outchannel, kernel_size=3, stride=stride, padding=1, bias=False),
            nn.BatchNorm2d(outchannel),
            nn.ReLU(inplace=True),
            nn.Conv2d(outchannel, outchannel, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(outchannel)
        )
        self.shortcut = nn.Sequential()
        if stride != 1 or inchannel != outchannel:
            self.shortcut = nn.Sequential(
                nn.Conv2d(inchannel, outchannel, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(outchannel)
            )

    def forward(self, x):
        out = self.left(x)
        out += self.shortcut(x)
        out = F.relu(out)
        return out

class ResNet(nn.Module):
    def __init__(self, ResidualBlock, num_classes=10):
        super(ResNet, self).__init__()
        self.inchannel = 64
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(),
        )
        self.layer1 = self.make_layer(ResidualBlock, 64,  2, stride=1)
        self.layer2 = self.make_layer(ResidualBlock, 128, 2, stride=2)
        self.layer3 = self.make_layer(ResidualBlock, 256, 2, stride=2)
        self.layer4 = self.make_layer(ResidualBlock, 512, 2, stride=2)
        self.fc = nn.Linear(512, num_classes)

    def make_layer(self, block, channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)   #strides=[1,1]
        layers = []
        for stride in strides:
            layers.append(block(self.inchannel, channels, stride))
            self.inchannel = channels
        return nn.Sequential(*layers)

    def forward(self, x):
        out = 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.fc(out)
        return out


def ResNet18():

    return ResNet(ResidualBlock)

一开始没看懂下面代码的意思，后来看懂模型结构发现是真香，大家细品。

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

二、新建train.py文件

代码如下：

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import argparse
from resnet import ResNet18

# 定义是否使用GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# 参数设置,使得我们能够手动输入命令行参数，就是让风格变得和Linux命令行差不多
parser = argparse.ArgumentParser(description='PyTorch CIFAR10 Training')
parser.add_argument('--outf', default='./model/', help='folder to output images and model checkpoints') #输出结果保存路径
parser.add_argument('--net', default='./model/Resnet18.pth', help="path to net (to continue training)")  #恢复训练时的模型路径
args = parser.parse_args()

# 超参数设置
EPOCH = 200  #遍历数据集次数
pre_epoch = 0  # 定义已经遍历数据集的次数
BATCH_SIZE = 128      #批处理尺寸(batch_size)
LR = 0.001        #学习率



# 准备数据集并预处理
transform_train = transforms.Compose([
    transforms.RandomCrop(32, padding=4),  #先四周填充0，在吧图像随机裁剪成32*32
    transforms.RandomHorizontalFlip(),  #图像一半的概率翻转，一半的概率不翻转
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)), #R,G,B每层的归一化用到的均值和方差
])

transform_test = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
])

trainset = torchvision.datasets.ImageFolder(root='E:\\CLFAR-10+pyqt5\\data\\train', transform=transform_train) #训练数据集
trainloader = torch.utils.data.DataLoader(trainset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2)   #生成一个个batch进行批训练，组成batch的时候顺序打乱取

testset = torchvision.datasets.ImageFolder(root='E:\\CLFAR-10+pyqt5\\data\\test', transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=True, num_workers=2)
# Cifar-10的标签
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

# 模型定义-ResNet
net = ResNet18().to(device)

# 定义损失函数和优化方式
criterion = nn.CrossEntropyLoss()  #损失函数为交叉熵，多用于多分类问题
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9, weight_decay=5e-4) #优化方式为mini-batch momentum-SGD，并采用L2正则化（权重衰减）

# 训练
if __name__ == "__main__":
    best_acc = 85  #2 初始化best test accuracy
    print("Start Training, Resnet-18!")  # 定义遍历数据集的次数
    with open("acc.txt", "w") as f:
        with open("log.txt", "w")as f2:
            for epoch in range(pre_epoch, EPOCH):
                print('\nEpoch: %d' % (epoch + 1))
                net.train()
                sum_loss = 0.0
                correct = 0.0
                total = 0.0
                for i, data in enumerate(trainloader, 0):
                    # 准备数据
                    length = len(trainloader)
                    inputs, labels = data
                    inputs, labels = inputs.to(device), labels.to(device)
                    optimizer.zero_grad()

                    # forward + backward
                    outputs = net(inputs)
                    loss = criterion(outputs, labels)
                    loss.backward()
                    optimizer.step()

                    # 每训练1个batch打印一次loss和准确率
                    sum_loss += loss.item()
                    _, predicted = torch.max(outputs.data, 1)
                    total += labels.size(0)
                    correct += predicted.eq(labels.data).cpu().sum()
                    print('[epoch:%d, iter:%d] Loss: %.03f | Acc: %.3f%% '
                          % (epoch + 1, (i + 1 + epoch * length), sum_loss / (i + 1), 100. * correct / total))
                    f2.write('%03d %05d |Loss: %.03f | Acc: %.3f%% '
                          % (epoch + 1, (i + 1 + epoch * length), sum_loss / (i + 1), 100. * correct / total))
                    f2.write('\n')
                    f2.flush()

                # 每训练完一个epoch测试一下准确率
                print("Waiting Test!")
                with torch.no_grad():
                    correct = 0
                    total = 0
                    for data in testloader:
                        net.eval()
                        images, labels = data
                        images, labels = images.to(device), labels.to(device)
                        outputs = net(images)
                        # 取得分最高的那个类 (outputs.data的索引号)
                        _, predicted = torch.max(outputs.data, 1)
                        total += labels.size(0)
                        correct += (predicted == labels).sum().item()
                        # result = torch.floor_divide(correct, total)
                    # print('测试分类准确率为：%.3f%%' % (100 * result))
                    acc = 100 * correct / total
                    print('测试分类准确率为：%.3f%%' % (acc))
                    # 将每次测试结果实时写入acc.txt文件中
                    print('Saving model......')
                    torch.save(net.state_dict(), '%s/net_%03d.pth' % (args.outf, epoch + 1))
                    f.write("EPOCH=%03d,Accuracy= %.3f%%" % (epoch + 1, acc))
                    f.write('\n')
                    f.flush()
                    # 记录最佳测试分类准确率并写入best_acc.txt文件中
                    if acc > best_acc:
                        f3 = open("best_acc.txt", "w")
                        f3.write("EPOCH=%d,best_acc= %.3f%%" % (epoch + 1, acc))
                        f3.close()
                        best_acc = acc
            print("Training Finished, TotalEPOCH=%d" % EPOCH)
         

将训练过程记录在 log.txt中，将每个epoch的测试精度放在acc.txt中，最后通过if语句将最高精度记录在best_acc.txt中，best_acc.txt中保存的是最高测试准确率所对应的epoch。每次epoch的权重保存在model文件夹下

三、新建predict文件

为了让模型和PyQt5结合，写个预测脚本方便GUI文件调用
代码如下：

import torch
import torchvision.transforms as transforms
from resnet import ResNet18
from PIL import Image

def predict_(img):

    data_transform = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),

    ])
    #img =Image.open('E:\CLFAR-10+pyqt5\4.jpg')
    img = data_transform(img)
    img = torch.unsqueeze(img, dim=0)

    model = ResNet18()

    model_weight_pth = 'E:\\CLFAR-10+pyqt5\\model\\net_200.pth'
    model.load_state_dict(torch.load(model_weight_pth))

    model.eval()
    classes = { '0': '飞机', '1': '汽车', '2': '鸟', '3': '猫', '4': '鹿', '5': '狗', '6': '青蛙', '7': '马', '8': '船', '9': '卡车'}
    with torch.no_grad():
        output = torch.squeeze(model(img))
        print(output)
        predict = torch.softmax(output, dim=0)

        predict_cla = torch.argmax(predict).numpy()

    return classes[str(predict_cla)], predict[predict_cla].item()

在上述训练过程完成后，通过查看best_acc.txt查看测试精度最好的一次所对应的epoch，在预测脚本中使用精度最高的epoch所对应的权重

model_weight_pth = 'E:\\CLFAR-10+pyqt5\\model\\net_200.pth'
model.load_state_dict(torch.load(model_weight_pth))

接下来测试一下预测代码：
打印一下output

img = Image.open('E:\\CLFAR-10+pyqt5\data\\test\\bird\\25.jpg')
net = predict_(img)
print(net)

结果：

tensor([ 1.2775, -3.7718,  6.0837, -0.4484, -4.9533,  3.0170, -4.3821,  3.7511,
         1.8174, -2.6302])
('鸟', 0.8564958572387695)
tensor([19.7340, -4.3800, -3.0140, -3.5426, -2.8213, -2.6680, -3.8995, -4.8666,
         4.2137,  0.3724])
Process finished with exit code 0

预测正确！

四、新建GUI.py文件

这里就是建立界面了，代码如下：

from PyQt5.QtWidgets import (QWidget,QLCDNumber,QSlider,QMainWindow,
                             QGridLayout,QApplication,QPushButton, QLabel, QLineEdit)

from PyQt5.QtGui import *
from PyQt5.QtCore import *
from PyQt5.QtWidgets import *
import sys
from PyQt5.QtCore import Qt
from predict import predict_
from PIL import Image


class Ui_example(QWidget):
    def __init__(self):
        super().__init__()

        self.layout = QGridLayout(self)
        self.label_image = QLabel(self)
        self.label_predict_result = QLabel('识别结果',self)
        self.label_predict_result_display = QLabel(self)
        self.label_predict_acc = QLabel('识别准确率',self)
        self.label_predict_acc_display = QLabel(self)

        self.button_search_image = QPushButton('选择图片',self)
        self.button_run = QPushButton('运行',self)
        self.setLayout(self.layout)
        self.initUi()

    def initUi(self):

        self.layout.addWidget(self.label_image,1,1,3,2)
        self.layout.addWidget(self.button_search_image,1,3,1,2)
        self.layout.addWidget(self.button_run,3,3,1,2)
        self.layout.addWidget(self.label_predict_result,4,3,1,1)
        self.layout.addWidget(self.label_predict_result_display,4,4,1,1)
        self.layout.addWidget(self.label_predict_acc,5,3,1,1)
        self.layout.addWidget(self.label_predict_acc_display,5,4,1,1)

        self.button_search_image.clicked.connect(self.openimage)
        self.button_run.clicked.connect(self.run)

        self.setGeometry(300,300,300,300)
        self.setWindowTitle('CLFAR-10十分类')
        self.show()

    def openimage(self):
        global fname
        imgName, imgType = QFileDialog.getOpenFileName(self, "选择图片", "", "*.jpg;;*.png;;All Files(*)")
        jpg = QPixmap(imgName).scaled(self.label_image.width(), self.label_image.height())
        self.label_image.setPixmap(jpg)
        fname = imgName



    def run(self):
        global fname
        file_name = str(fname)
        img = Image.open(file_name)

        a, b = predict_(img)
        self.label_predict_result_display.setText(a)
        self.label_predict_acc_display.setText(str(b))




if __name__ == '__main__':
    app = QApplication(sys.argv)
    ex = Ui_example()
    sys.exit(app.exec_())

结果演示

遇到的问题

我学习中遇到的一些问题，通过百度和博客解决了。

1》nn.Sequential(*layers)为什么需要加一个星号？

答：如果星号加在了是实参上，代表的是将输入迭代器拆成一个个元素。

2》net.train()和net.eval()区别？

答：使用PyTorch进行训练和测试时一定注意要把实例化的模型指定train/eval，eval()时，框架会自动把BN和DropOut固定住，不会取平均，而是用训练好的值，不然的话，一旦test的batch_size过小，很容易就会被BN层导致生成图片颜色失真极大。原因就是对于BN层来说，它在训练过程中，是对每一个batch去一个样本均值和方差，然后使用滑动指数平均所有的batch的均值和方差来近似整个样本的均值和方差。对于测试阶段，我们固定我们样本和方差，bn相当于一个线性的映射关系。所以说对于pytorch来说，在训练阶段我们net.train相当于打开滑动指数平均按钮，不断的更新；测试阶段我们关闭它，相当于一个线性映射关系。

3》correct += predicted.eq(labels.data).cpu().sum()是什么意思？

答：correct += predicted.eq(labels.data).cpu().sum()其实和correct += (predicted == labels).sum().item()是一个意思，.item()返回的是一个具体值，而.data返回的是一个tensor，要注意item()不能丢，不然返回的是tensor，而tensor不能相加。

如果对大家的学习有所帮助，希望大家帮我点个赞，让我觉得我的分享是有价值的，也欢迎大家和我交流

总结和引用

这篇文章大概算是我两个月来初学pytorch的总结，后面大概要去看tensorflow了。

参考文章：
1.Pytorch实战2：ResNet-18实现Cifar-10图像分类（测试集分类准确率95.170%）

2.PYQT5+Pytorch的猫狗分类（从数据集制作->网络模型搭建和训练->界面演示）