- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍖 原作者:K同学啊 | 接辅导、项目定制
一、前期准备
1.设置GPU
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,random
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device
2. 导入数据
data_dir = './Data/猴痘病识别数据/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*/*'))
classeNames = sorted(item.name for item in data_dir.glob('*/') if item.is_dir())
classeNames
['Monkeypox', 'Others']
- 第一步:使用
pathlib.Path()
函数将字符串类型的文件夹路径转换为pathlib.Path
对象。 - 第二步:使用
glob()
方法获取data_dir路径下的所有文件路径,并以列表形式存储在data_paths
中。 - 第三步:通过
split()
函数对data_paths
中的每个文件路径执行分割操作,获得各个文件所属的类别名称,并存储在classeNames
中 - 第四步:打印
classeNames
列表,显示每个文件所属的类别名称。
total_datadir = './Data/猴痘病识别数据/'
# 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。
])
total_data = datasets.ImageFolder(total_datadir,transform=train_transforms)
total_data
Dataset ImageFolder
Number of datapoints: 2142
Root location: ./data/monkeypox_disease_photos/
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
{'Monkeypox': 0, 'Others': 1}
3. 划分数据集
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
train_size,test_size
(1713, 429)
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1)
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
二、构建简单的CNN网络
对于一般的CNN网络来说,都是由特征提取网络和分类网络构成,其中特征提取网络用于提取图片的特征,分类网络用于将图片进行分类。
import torch.nn.functional as F
class Network_bn(nn.Module):
def __init__(self):
super(Network_bn, self).__init__()
"""
nn.Conv2d()函数:
第一个参数(in_channels)是输入的channel数量
第二个参数(out_channels)是输出的channel数量
第三个参数(kernel_size)是卷积核大小
第四个参数(stride)是步长,默认为1
第五个参数(padding)是填充大小,默认为0
"""
self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=0)
self.bn1 = nn.BatchNorm2d(12)
self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=0)
self.bn2 = nn.BatchNorm2d(12)
self.pool = nn.MaxPool2d(2,2)
self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=0)
self.bn4 = nn.BatchNorm2d(24)
self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)
self.bn5 = nn.BatchNorm2d(24)
self.fc1 = nn.Linear(24*50*50, len(classeNames))
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.bn4(self.conv4(x)))
x = F.relu(self.bn5(self.conv5(x)))
x = self.pool(x)
x = x.view(-1, 24*50*50)
x = self.fc1(x)
return x
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = Network_bn().to(device)
model
Network_bn(
(conv1): Conv2d(3, 12, kernel_size=(5, 5), stride=(1, 1))
(bn1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(12, 12, kernel_size=(5, 5), stride=(1, 1))
(bn2): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(conv4): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))
(bn4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv5): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1))
(bn5): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fc1): Linear(in_features=60000, out_features=2, bias=True)
)
三、 训练模型
1. 设置超参数
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-4 # 学习率
opt = torch.optim.SGD(model.parameters(),lr=learn_rate)
# 训练循环
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset) # 训练集的大小,一共60000张图片
num_batches = len(dataloader) # 批次数目,1875(60000/32)
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
3. 编写测试函数
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,一共10000张图片
num_batches = len(dataloader) # 批次数目,313(10000/32=312.5,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
4. 正式训练
epochs = 20
train_loss = []
train_acc = []
test_loss = []
test_acc = []
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
train_acc.append(epoch_train_acc)
train_loss.append(epoch_train_loss)
test_acc.append(epoch_test_acc)
test_loss.append(epoch_test_loss)
template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%,Test_loss:{:.3f}')
print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')
Epoch: 1, Train_acc:61.1%, Train_loss:0.672, Test_acc:66.7%,Test_loss:0.643
Epoch: 2, Train_acc:68.0%, Train_loss:0.590, Test_acc:64.3%,Test_loss:0.597
Epoch: 3, Train_acc:72.3%, Train_loss:0.546, Test_acc:71.6%,Test_loss:0.593
Epoch: 4, Train_acc:74.4%, Train_loss:0.518, Test_acc:76.0%,Test_loss:0.500
Epoch: 5, Train_acc:78.2%, Train_loss:0.478, Test_acc:78.8%,Test_loss:0.476
Epoch: 6, Train_acc:78.8%, Train_loss:0.456, Test_acc:78.6%,Test_loss:0.461
Epoch: 7, Train_acc:81.6%, Train_loss:0.429, Test_acc:80.2%,Test_loss:0.443
Epoch: 8, Train_acc:83.4%, Train_loss:0.410, Test_acc:79.5%,Test_loss:0.441
Epoch: 9, Train_acc:85.2%, Train_loss:0.393, Test_acc:83.4%,Test_loss:0.437
Epoch:10, Train_acc:86.2%, Train_loss:0.371, Test_acc:83.2%,Test_loss:0.416
Epoch:11, Train_acc:86.9%, Train_loss:0.362, Test_acc:82.1%,Test_loss:0.432
Epoch:12, Train_acc:88.9%, Train_loss:0.339, Test_acc:84.8%,Test_loss:0.399
Epoch:13, Train_acc:89.7%, Train_loss:0.329, Test_acc:83.9%,Test_loss:0.393
Epoch:14, Train_acc:90.3%, Train_loss:0.317, Test_acc:85.1%,Test_loss:0.387
Epoch:15, Train_acc:92.0%, Train_loss:0.300, Test_acc:86.0%,Test_loss:0.384
Epoch:16, Train_acc:90.5%, Train_loss:0.300, Test_acc:85.5%,Test_loss:0.378
Epoch:17, Train_acc:91.4%, Train_loss:0.290, Test_acc:84.6%,Test_loss:0.371
Epoch:18, Train_acc:92.6%, Train_loss:0.279, Test_acc:85.3%,Test_loss:0.375
Epoch:19, Train_acc:93.1%, Train_loss:0.265, Test_acc:85.3%,Test_loss:0.372
Epoch:20, Train_acc:93.3%, Train_loss:0.259, Test_acc:85.3%,Test_loss:0.351
Done
四、 结果可视化
1. Loss与Accuracy图
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 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()
2. 指定图片进行预测
-
torch.squeeze()
详解
对数据的维度进行压缩,去掉维数为1的的维度- 函数原型:
torch.squeeze(input, dim=None)
- 参数:
input
:输入张量dim
:要压缩的维度,默认None,表示压缩所有维数为1的维度
- 返回值:
- 压缩后的张量
- 举例:
假设
input
为torch.Size([1, 3, 1, 2])
,则torch.squeeze(input)
返回torch.Size([3, 2])
假设
input
为torch.Size([1, 1, 3, 2])
,则torch.squeeze(input)
返回torch.Size([3, 2])
假设
input
为torch.Size([1, 3, 2, 1])
,则torch.squeeze(input)
返回torch.Size([3, 2])
- 函数原型:
-
torch.unsqueeze()
详解
对数据的维度进行扩展,在指定的维度上添加维数为1的维度- 函数原型:
torch.unsqueeze(input, dim)
- 参数:
input
:输入张量dim
:要添加维度的维度
- 返回值:
- 扩展后的张量
- 举例:
假设
input
为torch.Size([3, 2])
,则torch.unsqueeze(input, 0)
返回torch.Size([1, 3, 2])
假设
input
为torch.Size([3, 2])
,则torch.unsqueeze(input, 1)
返回torch.Size([3, 1, 2])
假设
input
为torch.Size([3, 2])
,则torch.unsqueeze(input, 2)
返回torch.Size([3, 2, 1])
- 函数原型:
from PIL import Image
classes = list(total_data.class_to_idx)
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/猴痘病识别数据/Monkeypox/M24_01_05.jpg',
model=model,
transform=train_transforms,
classes=classes)
五、保存并加载模型
# 模型保存
PATH = './model/Monkeypox_model.pth' # 保存的参数文件名
torch.save(model.state_dict(), PATH)
# 将参数加载到model当中
model.load_state_dict(torch.load(PATH, map_location=device))
六、个人收获
在这个项目中,完成了一个猴痘病识别的深度学习模型,以下是一些个人收获:
- GPU设置和数据准备: 首先设置了GPU,并导入了必要的库和数据。这是深度学习项目的基本步骤,确保在GPU上运行可以加速模型的训练过程。
- 数据导入与处理: 使用了
torchvision
库导入并处理了图像数据。这包括了对图像进行预处理、划分数据集等步骤,这对于建立有效的训练和测试数据集非常重要。 - 构建简单的CNN网络: 建立了一个简单的卷积神经网络(CNN)模型,包括卷积层、批归一化层、池化层和全连接层。这个模型用于提取图像特征并进行分类。
- 训练模型: 定义了训练和测试函数,使用交叉熵作为损失函数,使用梯度下降法进行优化。通过多次训练迭代,观察了模型在训练集和测试集上的准确率和损失的变化。
- 结果可视化: 使用
matplotlib
库绘制了训练和测试过程中准确率和损失的变化图表,使得你能够直观地了解模型的训练效果。 - 保存与加载模型: 最后,保存了训练好的模型的参数,并展示了如何加载这些参数,以便在以后的使用中重新使用模型。
- 图像预测: 实现了对单张图像进行预测的函数,并展示了如何使用训练好的模型进行图像分类。
这个项目涵盖了深度学习项目的多个关键步骤,包括数据处理、模型构建、训练、可视化和保存模型等。通过完成这个项目,你可能学到了如何处理图像数据、构建简单的CNN模型以及如何训练和评估模型的基本知识。