环境：
-
语言环境：python 3.8
-
编译器：jupyter notebook
-
深度学习环境：Pytorch
torch == 2.1.0+cpu
torchvision == 0.16.0+cpu
-
一、准备工作
1. 导入库函数
-
import torch import torch.nn as nn import torchvision.transforms as transforms import torchvision from torchvision import transforms, datasets import os,PIL,pathlib,random2.加载数据
-
data_dir = "文件名" data_dir = pathlib.Path(data_dir) data_paths = list(data_dir.glob('*/')) classNames = [str(path).split("\\")[4] for path in data_paths] classNames3. 数据加载
-
# 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_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。 ]) train_dataset = datasets.ImageFolder("文件名/train",transform=train_transforms) test_dataset = datasets.ImageFolder("文件名/test/",transform=train_transforms) 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二、CNN网络配置、编译、训练
-
1. 模型建立
-
import torch.nn.functional as F class Model(nn.Module): def __init__(self): super(Model, self).__init__() self.conv1=nn.Sequential( nn.Conv2d(3, 12, kernel_size=5, padding=0), # 12*220*220 nn.BatchNorm2d(12), nn.ReLU()) self.conv2=nn.Sequential( nn.Conv2d(12, 12, kernel_size=5, padding=0), # 12*216*216 nn.BatchNorm2d(12), nn.ReLU()) self.pool3=nn.Sequential( nn.MaxPool2d(2)) # 12*108*108 self.conv4=nn.Sequential( nn.Conv2d(12, 24, kernel_size=5, padding=0), # 24*104*104 nn.BatchNorm2d(24), nn.ReLU()) self.conv5=nn.Sequential( nn.Conv2d(24, 24, kernel_size=5, padding=0), # 24*100*100 nn.BatchNorm2d(24), nn.ReLU()) self.pool6=nn.Sequential( nn.MaxPool2d(2)) # 24*50*50 self.dropout = nn.Sequential( nn.Dropout(0.2)) self.fc=nn.Sequential( nn.Linear(24*50*50, len(classNames))) def forward(self, x): batch_size = x.size(0) x = self.conv1(x) # 卷积-BN-激活 x = self.conv2(x) # 卷积-BN-激活 x = self.pool3(x) # 池化 x = self.conv4(x) # 卷积-BN-激活 x = self.conv5(x) # 卷积-BN-激活 x = self.pool6(x) # 池化 x = self.dropout(x) x = x.view(batch_size, -1) # flatten 变成全连接网络需要的输入 (batch, 24*50*50) ==> (batch, -1), -1 此处自动算出的是24*50*50 x = self.fc(x) return x model = Model() Model( (conv1): Sequential( (0): Conv2d(3, 12, kernel_size=(5, 5), stride=(1, 1)) (1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (conv2): Sequential( (0): Conv2d(12, 12, kernel_size=(5, 5), stride=(1, 1)) (1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (pool3): Sequential( (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) ) (conv4): Sequential( (0): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1)) (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (conv5): Sequential( (0): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1)) (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU() ) (pool6): Sequential( (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) ) (dropout): Sequential( (0): Dropout(p=0.2, inplace=False) ) (fc): Sequential( (0): Linear(in_features=60000, out_features=2, bias=True) ) ) import torchinfo torchinfo.summary(model) #显示模型信息2. 训练函数
2.1 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_loss2.2 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_loss2.3 设置动态学习率
-
def adjust_learning_rate(optimizer, epoch, start_lr): # 每 2 个epoch衰减到原来的 0.98 lr = start_lr * (0.92 ** (epoch // 2)) for param_group in optimizer.param_groups: param_group['lr'] = lr learn_rate = 1e-4 # 初始学习率 optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate) #opt = torch.optim.Adam(model.parameters(), lr=learn_rate)2.4 模型训练
三、训练结果可视化
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()
总结：深度学习模型中如学习率、批次大小、层数、神经元数量等，调整这些参数以获得最佳性能，在考虑是否增加optuna库，自动调参，增加学习率调整
407
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
