目录

前言

一、前期准备

1.1 数据集介绍

1.2 包和数据导入

1.3 图片处理

1.4 数据集划分

二、模型搭建

三、模型训练

3.1 训练函数和测试函数

3.2 正式训练过程

四、结果可视化

4.1 Loss和Accuracy图

总结


前言

  • 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/)

说在前面

本周目标:探索一下深度学习在医学领域的应用,乳腺癌是女性最常见的癌症形式,浸润性导管癌 (IDC)是最常见的乳腺癌形式。准确识别和分类乳腺癌亚型是一项重要的临床任务,利用深度学习方法识别可以有效节省时间并减少错误

我的环境:Python3.8、Pycharm2020、torch1.12.1+cu113

数据来源:[K同学啊](https://mtyjkh.blog.csdn.net/)


一、前期准备

1.1 数据集介绍

多张以40倍扫描的乳腺癌Bca标本的完整载玻片图像

本项目所采用的数据集未收录于公开数据中,故需要自己在文件目录中导入相应数据合集,并设置对应文件目录,以供后续学习过程中使用

1.2 包和数据导入

代码如下:

import torch
import torch.nn as nn
from torchvision import transforms, datasets
import os, PIL, pathlib, warnings
import torch.nn.functional as F
import matplotlib.pyplot as plt
from torch.utils.data import Dataset
from PIL import Image
import copy


#一、导入数据
'''
1.1 设置GPU
'''
warnings.filterwarnings("ignore")

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

'''
1.2 导入数据
'''
data_dir = './J3-data/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))

classNames = [str(path).split('\\')[1] for path in data_paths]
print(classNames)

输出结果:

cuda
['0', '1']

1.3 图片处理

代码如下:

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("./J3-data/",transform=train_transforms)
print(total_data)
print(total_data.class_to_idx)

打印输出:

Dataset ImageFolder
    Number of datapoints: 13403
    Root location: ./J3-data/
    StandardTransform
Transform: Compose(
               Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=warn)
               ToTensor()
               Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
           )
{'0': 0, '1': 1}

1.4 数据集划分

代码如下:

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)

'''
2.3 可视化数据
'''
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
                                       batch_size=batch_size,
                                       shuffle=True)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                      batch_size=batch_size,
                                      shuffle=True)
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

image_folder = './J3-data/0'           #指定图像文件夹路径

image_files = [f for f in os.listdir(image_folder) if f.endswith((".jpg", ".png", ".jpeg"))]
fig, axes = plt.subplots(2, 4, figsize=(16, 6))

for ax, img_file in zip(axes.flat, image_files):
    img_path = os.path.join(image_folder, img_file)
    img = Image.open(img_path)
    ax.imshow(img)
    ax.axis('off')
plt.tight_layout()
plt.show()

打印输出:

<torch.utils.data.dataset.Subset object at 0x00000273802E0670> <torch.utils.data.dataset.Subset object at 0x00000273802E0700>

Shape of X [N, C, H, W]:  torch.Size([32, 3, 224, 224])
Shape of y:  torch.Size([32]) torch.int64

二、模型搭建

第13周:DenseNet算法实战与解析-CSDN博客

与上一篇文章的区别是模型的没有加载预训练权重,所以本次实验虽然epoch只为20,训练了很久才出来结果,收敛速度明显变慢了

模型代码如下:

#三、模型
'''
3.1 DenseLayer层实现
'''
class _DenseLayer(nn.Sequential):
    """Basic unit of DenseBlock (using bottleneck layer) """

    def __init__(self, num_input_features, growth_rate, bn_size, drop_rate):
        super(_DenseLayer, self).__init__()
        self.add_module('norm1', nn.BatchNorm2d(num_input_features)),
        self.add_module('relu1', nn.ReLU(inplace=True)),
        self.add_module('conv1', nn.Conv2d(num_input_features, bn_size * growth_rate,
                                           kernel_size=1, stride=1, bias=False)),
        self.add_module('norm2', nn.BatchNorm2d(bn_size * growth_rate)),
        self.add_module('relu2', nn.ReLU(inplace=True)),
        self.add_module('conv2', nn.Conv2d(bn_size * growth_rate, growth_rate,
                                           kernel_size=3, stride=1, padding=1, bias=False)),
        self.drop_rate = drop_rate

    def forward(self, x):
        new_features = super(_DenseLayer, self).forward(x)
        if self.drop_rate > 0:
            new_features = F.dropout(new_features, p=self.drop_rate, training=self.training)
        return torch.cat([x, new_features], 1)


'''
3.2 DenseBlock模块
'''
class _DenseBlock(nn.Sequential):
    def __init__(self, num_layers, num_input_features, bn_size, growth_rate, drop_rate):
        super(_DenseBlock, self).__init__()
        for i in range(num_layers):
            layer = _DenseLayer(num_input_features+i*growth_rate, growth_rate, bn_size, drop_rate)
            self.add_module("denselayer%d" % (i+1,), layer)

'''
3.3 Transition层
'''
class _Transition(nn.Sequential):
    def __init__(self, num_input_feature, num_output_features):
        super(_Transition, self).__init__()
        self.add_module("norm", nn.BatchNorm2d(num_input_feature))
        self.add_module("relu", nn.ReLU(inplace=True))
        self.add_module("conv", nn.Conv2d(num_input_feature,num_output_features,kernel_size=1, stride=1, bias=False))
        self.add_module("pool", nn.AvgPool2d(2, stride=2))

'''
3.4 DenseNet网络实现
'''
from collections import OrderedDict
class DenseNet(nn.Module):
    def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64,
                 bn_size=4, compression_rate=0.5, drop_rate=0, num_classes=1000):
        super(DenseNet, self).__init__()
        #first Conv2d
        self.features = nn.Sequential(OrderedDict([
            ("conv0", nn.Conv2d(3, num_init_features, kernel_size=7, stride=2, padding=3, bias=False)),
            ("norm0", nn.BatchNorm2d(num_init_features)),
            ("relu0", nn.ReLU(inplace=True)),
            ("pool0", nn.MaxPool2d(3, stride=2, padding=1))
        ]))

        #DenseBlock
        num_features = num_init_features
        for i, num_layers in enumerate(block_config):
            block = _DenseBlock(num_layers, num_features, bn_size, growth_rate, drop_rate)
            self.features.add_module("denseblock%d" % (i+1),block)
            num_features += num_layers*growth_rate
            if i !=len(block_config) - 1:
                transition = _Transition(num_features, int(num_features*compression_rate))
                self.features.add_module("transition%d" % (i+1), transition)
                num_features = int(num_features * compression_rate)

        #final bn+ReLu
        self.features.add_module("norm5", nn.BatchNorm2d(num_features))
        self.features.add_module("relu5", nn.ReLU(inplace=True))

        #classification layer
        self.classifier = nn.Linear(num_features,num_classes)

        #params initialization
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal(m.weight)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.bias, 0)
                nn.init.constant_(m.weight, 1)
            elif isinstance(m, nn.Linear):
                nn.init.constant_(m.bias, 0)

    def forward(self, x):
        features = self.features(x)
        out = F.avg_pool2d(features, 7, stride=1).view(features.size(0), -1)
        out = self.classifier(out)
        return out



"""搭建densenet121模型"""
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format((device)))

densenet121 = DenseNet(num_init_features=64, growth_rate=32,block_config=(6,12,24,16),
                       num_classes=len(classNames))
import torchsummary as summary
model = densenet121.to(device)
print(model)
print(summary.summary(model, (3, 224, 224)))  # 查看模型的参数量以及相关指标

打印的部分内容截图如下:

三、模型训练

3.1 训练函数和测试函数

训练函数和测试函数与前面文章中都一直,没有变化,代码如下:

def train(dataloader, model, optimizer, loss_fn):
    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)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        train_loss += loss.item()
        train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()

    train_loss /= num_batches
    train_acc /= size

    return train_acc, train_loss

'''
4.2 编写测试函数
'''
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

3.2 正式训练过程

正式训练过程保存了最佳模型的相关参数

代码如下:

loss_fn = nn.CrossEntropyLoss()   #交叉熵函数
learn_rate = 1e-4
opt = torch.optim.Adam(model.parameters(), lr=learn_rate)

epochs = 20
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0

# 开始训练
for epoch in range(epochs):

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

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

    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)

    lr = opt.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'
torch.save(best_model.state_dict(), PATH)

print('Done')

训练过程如下:

四、结果可视化

4.1 Loss和Accuracy图

代码如下:

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()

打印如下:

4.2 模型评估

调用最佳模型参数查看

#六、模型评估
best_model.load_state_dict(torch.load(PATH, map_location=device))
print(f'epoch_test_acc:{epoch_test_acc}, epoch_test_loss:{epoch_test_loss}')

打印输出:

epoch_test_acc:0.9239089891831406, epoch_test_loss:0.25888495129488764

保存正确


总结

对DeseNet网络在乳腺癌细胞与正常细胞识别进行了应用,模型训练结果并不好,存在过拟合情况,在训练集上效果明显优于测试集,需要进一步优化模型相关参数设置

由于此处的DeseNet网络没有调用预训练权重,所以大大增加了训练收敛时间

点赞(0) 打赏

评论列表 共有 0 条评论

暂无评论

微信公众账号

微信扫一扫加关注

发表
评论
返回
顶部