P7——pytorch马铃薯病害识别

🍨 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

1.检查GPU

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")            
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

2.查看数据

import os,PIL,random,pathlibdata_dir='data/PotatoPlants'
data_path=pathlib.Path(data_dir)
data_paths=list(data_path.glob('*'))
classNames=[str(path).split('\\')[2] for path in data_paths]
classNames

3.划分数据集

train_transforms=transforms.Compose([transforms.Resize([224,224]),transforms.RandomHorizontalFlip(),transforms.ToTensor(),transforms.Normalize(mean=[0.482,0.456,0.406],std=[0.229,0.224,0.225])
])
test_transforms=transforms.Compose([transforms.Resize([224,224]),transforms.ToTensor(),transforms.Normalize(mean=[0.482,0.456,0.406],std=[0.229,0.224,0.225])
])
total_data=datasets.ImageFolder("data/PotatoPlants/",transform=train_transforms)
total_datatotal_data.class_to_idxtrain_size=int(0.8*len(total_data))
test_size=len(total_data)-train_size
train_data,test_data=torch.utils.data.random_split(total_data,[train_size,test_size])
train_data,test_databatch_size=32
train_dl=torch.utils.data.DataLoader(train_data,batch_size,shuffle=True,num_workers=1)
test_dl=torch.utils.data.DataLoader(test_data,batch_size,shuffle=True,num_workers=1)for X,y in train_dl:print(X.shape)print(y.shape)break

4.创建模型

import torch.nn.functional as Fclass vgg16(nn.Module):def __init__(self):super(vgg16, self).__init__()# 卷积块1self.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2self.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3self.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4self.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5self.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 xdevice = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = vgg16().to(device)
modelimport torchsummary as summary
summary.summary(model, (3, 224, 224))

5.动态调整学习率函数

#调用官方动态学习率接口
learning_rate = 1e-4
lambda1=lambda epoch:0.92**(epoch//4)
optimizer=torch.optim.SGD(model.parameters(),lr=learning_rate)
scheduler=torch.optim.lr_scheduler.LambdaLR(optimizer,lr_lambda=lambda1)

6.编译及训练模型

def train(dataloader,model,loss_fn,optimizer):size=len(dataloader.dataset)num_batches=len(dataloader)train_loss,train_acc=0,0for X,y in dataloader:X,y =X.to(device),y.to(device)pred=model(X)loss=loss_fn(pred,y)#反向传播optimizer.zero_grad()loss.backward()optimizer.step()train_loss+=loss.item()train_acc+=(pred.argmax(1)==y).type(torch.float).sum().item()train_acc/=sizetrain_loss/=num_batchesreturn train_acc,train_lossdef test(dataloader,model,loss_fn):size=len(dataloader.dataset)num_batches=len(dataloader)test_loss,test_acc=0,0with torch.no_grad():for imgs,target in dataloader:imgs,target=imgs.to(device),target.to(device)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/=sizetest_loss/=num_batchesreturn test_acc,test_lossimport copy
optimizer  = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn    = nn.CrossEntropyLoss()
import copy
loss_fn=nn.CrossEntropyLoss()
epochs=5
train_loss=[]
train_acc=[]
test_loss=[]
test_acc=[]
best_acc=0
for epoch in range(epochs):model.train()epoch_train_acc,epoch_train_loss=train(train_dl,model,loss_fn,optimizer)#更新学习率scheduler.step()model.eval()epoch_test_acc,epoch_test_loss=test(test_dl,model,loss_fn)if epoch_test_acc>=best_acc:best_acc=epoch_test_accbest_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)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))
PATH='./best_model.pth'
torch.save(best_model.state_dict(),PATH)
print('Finished Training')

7.结果可视化

import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings("ignore")
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
plt.rcParams['figure.dpi']=100epochs_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()

`8.预测本地图片`

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)test_img=transform(test_img)img=test_img.to(device).unsqueeze(0)model=model.eval()output=model(img)_,pred=torch.max(output,1)pred_class=classes[pred]print('预测结果是:',pred_class)predict_one_image(image_path='data/PotatoPlants/Early_blight/1.JPG', model=model, transform=train_transforms, classes=classes)best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)epoch_test_acc, epoch_test_loss

总结：

1.VGG-16

VGG-16（Visual Geometry Group-16）是由牛津大学视觉几何组（Visual Geometry Group）提出的一种深度卷积神经网络架构，用于图像分类和对象识别任务。VGG-16在2014年被提出，是VGG系列中的一种。VGG-16之所以备受关注，是因为它在ImageNet图像识别竞赛中取得了很好的成绩，展示了其在大规模图像识别任务中的有效性。

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：