A basic case of deep learning in practice - Convolutional Neural Network (CNN) Eye Disease Recognition Based on SqueezeNet | Case 1

foreword

SqueezeNet is a lightweight and efficient CNN model with 50 times fewer parameters than AlexNet, but the model performance (accuracy) is close to AlexNet. As the name suggests, Squeeze means compression and extrusion in Chinese, so we can guess from the name of the algorithm that the algorithm must reduce the amount of model parameters by compressing the model. Of course, the improvement of any algorithm is to improve the accuracy or reduce the model parameters on the original basis, so the main purpose of the algorithm is to reduce the amount of model parameters while maintaining the model accuracy.

---

My environment:

• Basic environment: python3.7
• Compiler: pycharm
• Deep learning framework: pytorch
• Dataset code acquisition: link (extraction code: 2357)

1. Data preparation

The dataset used in this case is the eye disease recognition dataset iChallenge-PM.

1.1 Dataset Introduction

iChallenge-PMIt is a medical data set about pathologic myopia (Pathologic Myopia, PM) provided in the iChallenge competition jointly organized by Baidu Brain and Zhongshan Ophthalmology Center of Sun Yat-sen University, including fundus retina images of 1200 subjects, training, verification and testing There are 400 data sets each.

• training.zip: contains training images and labels
• validation.zip: contains images of the validation set
• valid_gt.zip: contains labels for the validation set

The data set is downloaded from the AI ​​Studio platform, the specific information is as follows:

1.2 Dataset file structure

There are three compressed files in the dataset, namely:

• training.zip

├── PALM-Training400
│   ├── PALM-Training400.zip
│   │   ├── H0002.jpg
│   │   └── ...
│   ├── PALM-Training400-Annotation-D&F.zip
│   │   └── ...
│   └── PALM-Training400-Annotation-Lession.zip
        └── ...

• valid_gt.zip: PM_Lable_and_Fovea_Location.xlsx in the marked location is the marked file

├── PALM-Validation-GT
│   ├── Lession_Masks
│   │   └── ...
│   ├── Disc_Masks
│   │   └── ...
│   └── PM_Lable_and_Fovea_Location.xlsx

• validation.zip: test dataset

├── PALM-Validation
│   ├── V0001.jpg
│   ├── V0002.jpg
│   └── ...

2. Project actual combat

The project structure is as follows:

2.1 Data label division

The format of the eye disease data set is a bit complicated. Here I have processed the data set by myself, writing the training set and verification set into the txt text, corresponding to its image path and label respectively.

import os
import pandas as pd
# 将训练集划分标签
train_dataset = r"F:\SqueezeNet\data\PALM-Training400\PALM-Training400"
train_list = []
label_list = []


train_filenames = os.listdir(train_dataset)

for name in train_filenames:
    filepath = os.path.join(train_dataset, name)
    train_list.append(filepath)
    if name[0] == 'N' or name[0] == 'H':
        label = 0
        label_list.append(label)
    elif name[0] == 'P':
        label = 1
        label_list.append(label)
    else:
        raise('Error dataset!')


with open('F:/SqueezeNet/train.txt', 'w', encoding='UTF-8') as f:
    i = 0
    for train_img in train_list:
        f.write(str(train_img) + ' ' +str(label_list[i]))
        i += 1
        f.write('\n')
# 将验证集划分标签
valid_dataset = r"F:\SqueezeNet\data\PALM-Validation400"
valid_filenames = os.listdir(valid_dataset)
valid_label = r"F:\SqueezeNet\data\PALM-Validation-GT\PM_Label_and_Fovea_Location.xlsx"
data = pd.read_excel(valid_label)
valid_data = data[['imgName', 'Label']].values.tolist()

with open('F:/SqueezeNet/valid.txt', 'w', encoding='UTF-8') as f:
    for valid_img in valid_data:
        f.write(str(valid_dataset) + '/' + valid_img[0] + ' ' + str(valid_img[1]))
        f.write('\n')

2.2 Data preprocessing

The data preprocessing used here mainly includes image resizing, random flipping, normalization, etc.

import os.path
from PIL import Image
from torch.utils.data import DataLoader, Dataset
from torchvision.transforms import transforms

transform_BZ = transforms.Normalize(
    mean=[0.5, 0.5, 0.5],
    std=[0.5, 0.5, 0.5]
)


class LoadData(Dataset):
    def __init__(self, txt_path, train_flag=True):
        self.imgs_info = self.get_images(txt_path)
        self.train_flag = train_flag

        self.train_tf = transforms.Compose([
            transforms.Resize(224),  # 调整图像大小为224x224
            transforms.RandomHorizontalFlip(),  # 随机左右翻转图像
            transforms.RandomVerticalFlip(),  # 随机上下翻转图像
            transforms.ToTensor(),  # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
            transform_BZ  # 执行某些复杂变换操作
        ])
        self.val_tf = transforms.Compose([
            transforms.Resize(224),  # 调整图像大小为224x224
            transforms.ToTensor(),  # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
            transform_BZ  # 执行某些复杂变换操作
        ])

    def get_images(self, txt_path):
        with open(txt_path, 'r', encoding='utf-8') as f:
            imgs_info = f.readlines()
            imgs_info = list(map(lambda x: x.strip().split(' '), imgs_info))
        return imgs_info

    def padding_black(self, img):
        w, h = img.size
        scale = 224. / max(w, h)
        img_fg = img.resize([int(x) for x in [w * scale, h * scale]])
        size_fg = img_fg.size
        size_bg = 224
        img_bg = Image.new("RGB", (size_bg, size_bg))
        img_bg.paste(img_fg, ((size_bg - size_fg[0]) // 2,
                              (size_bg - size_fg[1]) // 2))

        img = img_bg
        return img

    def __getitem__(self, index):
        img_path, label = self.imgs_info[index]

        img_path = os.path.join('', img_path)
        img = Image.open(img_path)
        img = img.convert("RGB")
        img = self.padding_black(img)
        if self.train_flag:
            img = self.train_tf(img)
        else:
            img = self.val_tf(img)
        label = int(label)
        return img, label

    def __len__(self):
        return len(self.imgs_info)

2.3 Build the model

import torch
import torch.nn as nn
import torch.nn.init as init


class Fire(nn.Module):

    def __init__(self, inplanes, squeeze_planes,
                 expand1x1_planes, expand3x3_planes):
        super(Fire, self).__init__()
        self.inplanes = inplanes
        self.squeeze = nn.Conv2d(inplanes, squeeze_planes, kernel_size=1)
        self.squeeze_activation = nn.ReLU(inplace=True)
        self.expand1x1 = nn.Conv2d(squeeze_planes, expand1x1_planes,
                                   kernel_size=1)
        self.expand1x1_activation = nn.ReLU(inplace=True)
        self.expand3x3 = nn.Conv2d(squeeze_planes, expand3x3_planes,
                                   kernel_size=3, padding=1)
        self.expand3x3_activation = nn.ReLU(inplace=True)

    def forward(self, x):
        x = self.squeeze_activation(self.squeeze(x))
        return torch.cat([
            self.expand1x1_activation(self.expand1x1(x)),
            self.expand3x3_activation(self.expand3x3(x))
        ], 1)


class SqueezeNet(nn.Module):

    def __init__(self, version='1_0', num_classes=1000):
        super(SqueezeNet, self).__init__()
        self.num_classes = num_classes
        if version == '1_0':
            self.features = nn.Sequential(
                nn.Conv2d(3, 96, kernel_size=7, stride=2),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(96, 16, 64, 64),
                Fire(128, 16, 64, 64),
                Fire(128, 32, 128, 128),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(256, 32, 128, 128),
                Fire(256, 48, 192, 192),
                Fire(384, 48, 192, 192),
                Fire(384, 64, 256, 256),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(512, 64, 256, 256),
            )
        elif version == '1_1':
            self.features = nn.Sequential(
                nn.Conv2d(3, 64, kernel_size=3, stride=2),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(64, 16, 64, 64),
                Fire(128, 16, 64, 64),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(128, 32, 128, 128),
                Fire(256, 32, 128, 128),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(256, 48, 192, 192),
                Fire(384, 48, 192, 192),
                Fire(384, 64, 256, 256),
                Fire(512, 64, 256, 256),
            )
        else:
            # FIXME: Is this needed? SqueezeNet should only be called from the
            # FIXME: squeezenet1_x() functions
            # FIXME: This checking is not done for the other models
            raise ValueError("Unsupported SqueezeNet version {version}:"
                             "1_0 or 1_1 expected".format(version=version))

        # Final convolution is initialized differently from the rest
        final_conv = nn.Conv2d(512, self.num_classes, kernel_size=1)
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            final_conv,
            nn.ReLU(inplace=True),
            nn.AdaptiveAvgPool2d((1, 1))
        )

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                if m is final_conv:
                    init.normal_(m.weight, mean=0.0, std=0.01)
                else:
                    init.kaiming_uniform_(m.weight)
                if m.bias is not None:
                    init.constant_(m.bias, 0)

    def forward(self, x):
        x = self.features(x)
        x = self.classifier(x)
        return torch.flatten(x, 1)

2.4 Start training

import torch
import torch.nn as nn
from torch.utils.data import DataLoader, Dataset
from model import SqueezeNet
import torchsummary
from dataloader import LoadData
import copy

device = "cuda:0" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))

model = SqueezeNet(num_classes=2).to(device)
# print(model)
#print(torchsummary.summary(model, (3, 224, 224), 1))


# 加载训练集和验证集
train_data = LoadData(r"F:\SqueezeNet\train.txt", True)
train_dl = torch.utils.data.DataLoader(train_data, batch_size=16, pin_memory=True,
                                           shuffle=True, num_workers=0)
test_data = LoadData(r"F:\SqueezeNet\valid.txt", True)
test_dl = torch.utils.data.DataLoader(test_data, batch_size=16, pin_memory=True,
                                           shuffle=True, num_workers=0)


# 编写训练函数
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)
    print('num_batches:', num_batches)
    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

# 编写验证函数
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




# 开始训练

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


loss_function = nn.CrossEntropyLoss()  # 定义损失函数
optimizer = torch.optim.Adam(model.parameters(), lr=0.001) # 定义Adam优化器

for epoch in range(epochs):

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

    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_function)

    # 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(best_model.state_dict(), PATH)

print('Done')

2.5 Results Visualization

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 Test 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 Test Loss')
plt.show()

The visualization results are as follows:

You can adjust the learning rate and batch_size by yourself, and my hyperparameters are not adjusted here.

3. Data set individual prediction

import matplotlib.pyplot as plt
from PIL import Image
from torchvision.transforms import transforms
from model import SqueezeNet
import torch

data_transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Resize((224, 224)),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

img = Image.open("F:\SqueezeNet\data\PALM-Validation400\V0008.jpg")
plt.imshow(img)
img = data_transform(img)
img = torch.unsqueeze(img, dim=0)
name = ['非病理性近视', '病理性近视']
model_weight_path = r"F:\SqueezeNet\best_model.pth"
model = SqueezeNet(num_classes=2)
model.load_state_dict(torch.load(model_weight_path))
model.eval()
with torch.no_grad():
    output = torch.squeeze(model(img))

    predict = torch.softmax(output, dim=0)
    # 获得最大可能性索引
    predict_cla = torch.argmax(predict).numpy()
    print('索引为', predict_cla)
print('预测结果为：{},置信度为: {}'.format(name[predict_cla], predict[predict_cla].item()))
plt.show()

索引为 1
预测结果为：病理性近视,置信度为: 0.9768268465995789

For more details, please see the implementation of the paddle version: Deep Learning Practical Basic Case - Convolutional Neural Network (CNN) Eye Disease Recognition Based on SqueezeNet