>- **🍨 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/)**引言
1.复习上周并反思
K同学针对大家近期的学习状态，写了一篇文章，希望可以让大家有所思考
https://www.yuque.com/mingtian-fkmxf/yb7bg5/lrsbsdx6q4prla0f
K同学推荐正确的实验方式https://blog.csdn.net/Banana0840/article/details/137651851
本机环境欠佳，下次争取在云gpu上训练，并积极探索，实现目标准确率
天气识别http://t.csdnimg.cn/sEYUf
2.摆正心态
数据集http://xn--https-bl8js66z7n7i//pan.baidu.com/s/1N2otldhzYZSqyh-E69IdjA?pwd=6666%20%20%E6%8F%90%E5%8F%96%E7%A0%81%EF%BC%9A6666%20%20--%E6%9D%A5%E8%87%AA%E7%99%BE%E5%BA%A6%E7%BD%91%E7%9B%98%E8%B6%85%E7%BA%A7%E4%BC%9A%E5%91%98V3%E7%9A%84%E5%88%86%E4%BA%AB
3.本机环境
同上期，
4.学习目标
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, datasetsimport os,PIL,pathlibdevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")device2.导入数据
import os,PIL,random,pathlibdata_dir = './4-data/'
data_dir = pathlib.Path(data_dir)data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
classeNames3.图像预处理
图片大小处理
total_datadir = './4-data/'# 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_datatotal_data.class_to_idx{'Monkeypox': 0, 'Others': 1}
total_data.class_to_idx是一个存储了数据集类别和对应索引的字典。在PyTorch的ImageFolder数据加载器中，根据数据集文件夹的组织结构，每个文件夹代表一个类别，class_to_idx字典将每个类别名称映射为一个数字索引。
具体来说，如果数据集文件夹包含两个子文件夹，比如Monkeypox和Others，class_to_idx字典将返回类似以下的映射关系：{'Monkeypox': 0, 'Others': 1}划分数据集（4：1）
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数据集分类
train_size,test_size使用dataloder便于之后使用
batch_size = 32train_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)breakShape 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
import torch.nn.functional as Fclass 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 xdevice = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))model = Network_bn().to(device)
model输出结果
Using cuda deviceNetwork_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)2.编写训练函数
# 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losstrain_acc += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc /= sizetrain_loss /= num_batchesreturn train_acc, train_loss3.编写测试函数
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losstarget_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 /= sizetest_loss /= num_batchesreturn test_acc, test_loss4.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') 
四、结果可视化
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()
五、保存模型并预测
# 模型保存
PATH = './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))输出
<All keys matched successfully>六指定图片进行预测·
补充知识：torch.squeeze() & torch.unsqueeze() 详解
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='./4-data/Monkeypox/M01_01_00.jpg', model=model, transform=train_transforms, classes=classes)
七，总结
1，之前还在想字典文件是怎么获取的，这次清楚了，原来是此
total_data.class_to_idx是一个存储了数据集类别和对应索引的字典。在PyTorch的ImageFolder数据加载器中，根据数据集文件夹的组织结构，每个文件夹代表一个类别，class_to_idx字典将每个类别名称映射为一个数字索引。
具体来说，如果数据集文件夹包含两个子文件夹，比如Monkeypox和Others，class_to_idx字典将返回类似以下的映射关系：{'Monkeypox': 0, 'Others': 1}2指定单张图片预测
接收图像路径和类别文件等参数，对图像进行读取和预处理，然后通过模型得到预测结果，并将其转换为可读的类别名称，最后打印出预测结果。
