>- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/Z9yL_wt7L8aPOr9Lqb1K3w) 中的学习记录博客**
>- **🍖 原作者：[K同学啊](https://mtyjkh.blog.csdn.net/)**
我的环境：Anaconda
编译器：pytorch
一、 前期准备
设置GPU与之前操作相同，不再赘述
导入数据：
import os,PIL,random,pathlib
data_dir = './PotatoPlants/'#根据自己情况修改路径
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
classeNames
# 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.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("./PotatoPlants/",transform=train_transforms)
total_data
total_data.class_to_idx
运行结果：
{'Early_blight': 0, 'Late_blight': 1, 'healthy': 2}
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
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
运行结果：
Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32]) torch.int64
二、搭建VGG-16模型
以下是VGG-16的主要特点：
- 深度：VGG-16由16个卷积层和3个全连接层组成，因此具有相对较深的网络结构。这种深度有助于网络学习到更加抽象和复杂的特征。
- 卷积层的设计：VGG-16的卷积层全部采用
3x3的卷积核和步长为1的卷积操作，同时在卷积层之后都接有ReLU激活函数。这种设计的好处在于，通过堆叠多个较小的卷积核，可以提高网络的非线性建模能力，同时减少了参数数量，从而降低了过拟合的风险。 - 池化层：在卷积层之后，VGG-16使用最大池化层来减少特征图的空间尺寸，帮助提取更加显著的特征并减少计算量。
- 全连接层：VGG-16在卷积层之后接有3个全连接层，最后一个全连接层输出与类别数相对应的向量，用于进行分类。
VGG-16结构说明：
- 13个卷积层（Convolutional Layer），分别用
blockX_convX表示； - 3个全连接层（Fully connected Layer），用
classifier表示； - 5个池化层（Pool layer）
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( nn.Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), nn.ReLU(), nn.Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), nn.ReLU(), nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)) ) # 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=3) ) 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运行结果：
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=3, bias=True) ) )三、 训练模型
1. 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 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_loss2. 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_loss3. 正式训练
import copy optimizer = torch.optim.Adam(model.parameters(), lr= 1e-4) loss_fn = nn.CrossEntropyLoss() # 创建损失函数 epochs = 40 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')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()可视化展示：
扫一扫
791
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
