本文为🔗小白入门Pytorch内部限免文章
- 🍨 本文为🔗小白入门Pytorch中的学习记录博客
- 🍦 参考文章:【小白入门Pytorch】乳腺癌识别
- 🍖 原作者:K同学啊
在本案例中,我将带大家探索一下深度学习在医学领域的应用–完成乳腺癌识别,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。 我们的数据集是由多张以 40 倍扫描的乳腺癌 (BCa) 标本的完整载玻片图像组成。
关于环境配置请看我之前缩写博客:https://blog.csdn.net/qq_33489955/article/details/132890434?spm=1001.2014.3001.5501
数据集:链接:https://pan.baidu.com/s/1xkqsqsRRwlBOl5L9t_U0UA?pwd=vgqn
提取码:vgqn
–来自百度网盘超级会员V4的分享
import torch
print(torch.__version__) # 查看pytorch版本
2.0.1+cu118
如果设备上支持GPU就使用GPU,否则使用CPU
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warnings
warnings.filterwarnings("ignore") #忽略警告信息
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device
device(type='cuda')
import os,PIL,random,pathlib
data_dir = './data/2-data/'
data_dir = pathlib.Path(data_dir)
提问:已经有路径不是直接使用就可以了吗,为什么还要将其转化为路径对象。
回答:当我们使用传统的字符串来表示文件路径时,确实可以工作,但pathlib
提供的对象方法对于文件路径的操作更为简洁和直观。
以下是使用pathlib
的一些优点:
pathlib
自动处理不同操作系统的路径分隔符问题。例如,Windows使用\
,而Unix和Mac使用/
。使用pathlib
,你不需要关心这些细节。path.parent
返回父目录,path.stem
返回文件的基本名称(不带扩展名)等。pathlib.Path
对象有read_text()
, write_text()
, read_bytes()
, 和write_bytes()
等方法,可以直接读写文件,而无需再使用open
函数。pathlib
, 你可以很容易地创建 (mkdir()
) 或删除 (rmdir()
) 目录。以下是一个简单的例子来比较两者:
使用传统的os模块:
import os
file_path = os.path.join("folder1", "folder2", "myfile.txt")
使用pathlib
:
from pathlib import Path
file_path = Path("folder1") / "folder2" / "myfile.txt"
所以,虽然直接使用字符串路径是可以的,但使用pathlib
可以使代码更加简洁、可读和跨平台兼容。
# 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。
])
test_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(data_dir, transform=train_transforms)
total_data
Dataset ImageFolder
Number of datapoints: 13403
Root location: data\2-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])
)
total_data.class_to_idx
{'0': 0, '1': 1}
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])
train_dataset, test_dataset
(,
)
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=8)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=8)
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
提问:为什么结果只输出一次,是因为测试数据集只有一个批次,即32张图片吗
回答:不,结果只输出一次是因为您的代码中包含了一个 break
语句。这个 break
会在第一次迭代后立即退出 for
循环,因此您只看到了第一个批次的输出。
如果您想确认 test_dl
中有多少批次,您可以尝试以下代码:
num_batches = len(test_dl)
print("Number of batches in test_dl:", num_batches)
这将告诉您 test_dl
中有多少个批次。如果这个数字是1,那么确实只有32张图片。但是,如果这个数字大于1,那么 test_dl
会包含更多的图片。每个批次都有32张图片(除了可能的最后一个批次,它可能包含少于32张图片,取决于数据集的总数)。
VGG-16结构说明:
blockX_convX
表示;classifier
表示;VGG-16
包含了16个隐藏层(13个卷积层和3个全连接层),故称为VGG-16
import torch.nn.functional as F
class vgg16(nn.Module):
def __init__(self):
super(vgg16, self).__init__()
# 卷积块1
self.block1 = nn.Sequential( # # 这定义了一个名为block1的属性。nn.Sequential是一个容器,它按照它们被添加到容器中的顺序执行其中的层或操作。
nn.Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), # 这添加了一个2D卷积层。它接受3个通道的输入(例如RGB图像),并产生64个通道的输出。它使用3x3的卷积核,步长为1,和1的填充。
nn.ReLU(), # 这添加了一个ReLU激活函数。它将所有的负值变为0,其他值保持不变。
nn.Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), # 这是另一个2D卷积层。它接受上一个卷积层的64个通道的输出,并产生64个通道的输出。
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)) # # 这添加了一个2D最大池化层。它使用2x2的窗口和2的步长来减少每个通道的尺寸的一半。
)
# 卷积块2
self.block2 = nn.Sequential(
nn.Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
)
# 卷积块3
self.block3 = nn.Sequential(
nn.Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
)
# 卷积块4
self.block4 = nn.Sequential(
nn.Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
)
# 卷积块5
self.block5 = nn.Sequential(
nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
)
# 全连接网络层,用于分类
self.classifier = nn.Sequential(
nn.Linear(in_features=512*7*7, out_features=4096),
nn.ReLU(),
nn.Linear(in_features=4096, out_features=4096),
nn.ReLU(),
nn.Linear(in_features=4096, out_features=2)
)
def forward(self, x):
x = self.block1(x)
x = self.block2(x)
x = self.block3(x)
x = self.block4(x)
x = self.block5(x)
x = torch.flatten(x, start_dim=1)
x = self.classifier(x)
return x
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = vgg16().to(device)
model
Using cuda device
vgg16(
(block1): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU()
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU()
(4): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
)
(block2): Sequential(
(0): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU()
(2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU()
(4): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
)
(block3): Sequential(
(0): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU()
(2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU()
(4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(5): ReLU()
(6): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
)
(block4): Sequential(
(0): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU()
(2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU()
(4): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(5): ReLU()
(6): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
)
(block5): Sequential(
(0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU()
(2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU()
(4): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(5): ReLU()
(6): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
)
(classifier): Sequential(
(0): Linear(in_features=25088, out_features=4096, bias=True)
(1): ReLU()
(2): Linear(in_features=4096, out_features=4096, bias=True)
(3): ReLU()
(4): Linear(in_features=4096, out_features=2, bias=True)
)
)
!pip install torchsummary
Defaulting to user installation because normal site-packages is not writeable
Requirement already satisfied: torchsummary in c:\users\cheng\appdata\roaming\python\python310\site-packages (1.5.1)
# 统计模型参数量以及其他指标
import torchsummary as summary
summary.summary(model, (3, 224, 224))
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 64, 224, 224] 1,792
ReLU-2 [-1, 64, 224, 224] 0
Conv2d-3 [-1, 64, 224, 224] 36,928
ReLU-4 [-1, 64, 224, 224] 0
MaxPool2d-5 [-1, 64, 112, 112] 0
Conv2d-6 [-1, 128, 112, 112] 73,856
ReLU-7 [-1, 128, 112, 112] 0
Conv2d-8 [-1, 128, 112, 112] 147,584
ReLU-9 [-1, 128, 112, 112] 0
MaxPool2d-10 [-1, 128, 56, 56] 0
Conv2d-11 [-1, 256, 56, 56] 295,168
ReLU-12 [-1, 256, 56, 56] 0
Conv2d-13 [-1, 256, 56, 56] 590,080
ReLU-14 [-1, 256, 56, 56] 0
Conv2d-15 [-1, 256, 56, 56] 590,080
ReLU-16 [-1, 256, 56, 56] 0
MaxPool2d-17 [-1, 256, 28, 28] 0
Conv2d-18 [-1, 512, 28, 28] 1,180,160
ReLU-19 [-1, 512, 28, 28] 0
Conv2d-20 [-1, 512, 28, 28] 2,359,808
ReLU-21 [-1, 512, 28, 28] 0
Conv2d-22 [-1, 512, 28, 28] 2,359,808
ReLU-23 [-1, 512, 28, 28] 0
MaxPool2d-24 [-1, 512, 14, 14] 0
Conv2d-25 [-1, 512, 14, 14] 2,359,808
ReLU-26 [-1, 512, 14, 14] 0
Conv2d-27 [-1, 512, 14, 14] 2,359,808
ReLU-28 [-1, 512, 14, 14] 0
Conv2d-29 [-1, 512, 14, 14] 2,359,808
ReLU-30 [-1, 512, 14, 14] 0
MaxPool2d-31 [-1, 512, 7, 7] 0
Linear-32 [-1, 4096] 102,764,544
ReLU-33 [-1, 4096] 0
Linear-34 [-1, 4096] 16,781,312
ReLU-35 [-1, 4096] 0
Linear-36 [-1, 2] 8,194
================================================================
Total params: 134,268,738
Trainable params: 134,268,738
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 218.52
Params size (MB): 512.19
Estimated Total Size (MB): 731.29
----------------------------------------------------------------
# 训练循环
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)
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
测试函数和训练函数大致相同,但是由于不进行梯度下降对网络权重进行更新,所以不需要传入优化器
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
1. model.train()
model.train()
的作用是启用 Batch Normalization 和 Dropout。
如果模型中有BN
层(Batch Normalization)和Dropout
,需要在训练时添加model.train()
。model.train()
是保证BN层能够用到每一批数据的均值和方差。对于Dropout
,model.train()
是随机取一部分网络连接来训练更新参数。
2. model.eval()
model.eval()
的作用是不启用 Batch Normalization 和 Dropout。
如果模型中有BN层(Batch Normalization)和Dropout,在测试时添加model.eval()
。model.eval()
是保证BN层能够用全部训练数据的均值和方差,即测试过程中要保证BN层的均值和方差不变。对于Dropout
,model.eval()
是利用到了所有网络连接,即不进行随机舍弃神经元。
训练完train样本后,生成的模型model要用来测试样本。在model(test)
之前,需要加上model.eval()
,否则的话,有输入数据,即使不训练,它也会改变权值。这是model中含有BN层和Dropout所带来的的性质。
import copy
optimizer = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
epochs = 10
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
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
# 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(model.state_dict(), PATH)
print('Done')
Epoch: 1, Train_acc:76.6%, Train_loss:0.487, Test_acc:82.7%, Test_loss:0.385, Lr:1.00E-04
Epoch: 2, Train_acc:84.9%, Train_loss:0.364, Test_acc:79.9%, Test_loss:0.442, Lr:1.00E-04
Epoch: 3, Train_acc:84.0%, Train_loss:0.376, Test_acc:84.3%, Test_loss:0.349, Lr:1.00E-04
Epoch: 4, Train_acc:85.7%, Train_loss:0.339, Test_acc:86.1%, Test_loss:0.319, Lr:1.00E-04
Epoch: 5, Train_acc:86.3%, Train_loss:0.329, Test_acc:85.5%, Test_loss:0.331, Lr:1.00E-04
Epoch: 6, Train_acc:86.3%, Train_loss:0.324, Test_acc:86.2%, Test_loss:0.315, Lr:1.00E-04
Epoch: 7, Train_acc:86.8%, Train_loss:0.313, Test_acc:87.8%, Test_loss:0.298, Lr:1.00E-04
Epoch: 8, Train_acc:87.3%, Train_loss:0.302, Test_acc:86.3%, Test_loss:0.325, Lr:1.00E-04
Epoch: 9, Train_acc:87.7%, Train_loss:0.297, Test_acc:84.7%, Test_loss:0.363, Lr:1.00E-04
Epoch:10, Train_acc:88.5%, Train_loss:0.282, Test_acc:87.7%, Test_loss:0.295, Lr:1.00E-04
Done
import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore") #忽略警告信息
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()
from PIL import Image
classes = ["正常细胞", "乳腺癌细胞"]
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='./data/2-data/0/8863_idx5_x451_y501_class0.png',
model=model,
transform=train_transforms,
classes=classes)
预测结果是:正常细胞
best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)
epoch_test_acc, epoch_test_loss
(0.8780305856023871, 0.29799242158021244)
# 查看是否与我们记录的最高准确率一致
epoch_test_acc
0.8780305856023871