第P7周-Pytorch实现马铃薯病害识别（VGG16复现）

🍨 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

目标

马铃薯病害数据集，该数据集包含表现出各种疾病的马铃薯植物的高分辨率图像，包括早期疫病、晚期疫病和健康叶子。它旨在帮助开发和测试图像识别模型，以实现准确的疾病检测和分类，从而促进农业诊断的进步。

具体实现

（一）环境

语言环境：Python 3.10
编译器: PyCharm
框架: Pytorch

（二）具体步骤

1. Utils.py

**import torch  
import pathlib  
import matplotlib.pyplot as plt  
from torchvision.transforms import transforms  # 第一步：设置GPU  
def USE_GPU():  if torch.cuda.is_available():  print('CUDA is available, will use GPU')  device = torch.device("cuda")  else:  print('CUDA is not available. Will use CPU')  device = torch.device("cpu")  return device  temp_dict = dict()  
def recursive_iterate(path):  """  根据所提供的路径遍历该路径下的所有子目录，列出所有子目录下的文件  :param path: 路径  :return: 返回最后一级目录的数据  """    path = pathlib.Path(path)  for file in path.iterdir():  if file.is_file():  temp_key = str(file).split('\\')[-2]  if temp_key in temp_dict:  temp_dict.update({temp_key: temp_dict[temp_key] + 1})  else:  temp_dict.update({temp_key: 1})  # print(file)  elif file.is_dir():  recursive_iterate(file)  return temp_dict  def data_from_directory(directory, train_dir=None, test_dir=None, show=False):  """  提供是的数据集是文件形式的，提供目录方式导入数据，简单分析数据并返回数据分类  :param test_dir: 是否设置了测试集目录  :param train_dir: 是否设置了训练集目录  :param directory: 数据集所在目录  :param show: 是否需要以柱状图形式显示数据分类情况,默认显示  :return: 数据分类列表,类型: list  """    global total_image  print("数据目录：{}".format(directory))  data_dir = pathlib.Path(directory)  # for d in data_dir.glob('**/*'): # **/*通配符可以遍历所有子目录  #     if d.is_dir():  #         print(d)    class_name = []  total_image = 0  # temp_sum = 0  if train_dir is None or test_dir is None:  data_path = list(data_dir.glob('*'))  class_name = [str(path).split('\\')[-1] for path in data_path]  print("数据分类: {}, 类别数量：{}".format(class_name, len(list(data_dir.glob('*')))))  total_image = len(list(data_dir.glob('*/*')))  print("图片数据总数: {}".format(total_image))  else:  temp_dict.clear()  train_data_path = directory + '/' + train_dir  train_data_info = recursive_iterate(train_data_path)  print("{}目录:{},{}".format(train_dir, train_data_path, train_data_info))  temp_dict.clear()  test_data_path = directory + '/' + test_dir  print("{}目录:{},{}".format(test_dir,  test_data_path, recursive_iterate(test_data_path)))  class_name = temp_dict.keys()  if show:  # 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  for i in class_name:  data = len(list(pathlib.Path((directory + '\\' + i + '\\')).glob('*')))  plt.title('数据分类情况')  plt.grid(ls='--', alpha=0.5)  plt.bar(i, data)  plt.text(i, data, str(data), ha='center', va='bottom')  print("类别-{}:{}".format(i, data))  # temp_sum += data  plt.show()  # if temp_sum == total_image:  #     print("图片数据总数检查一致")  # else:    #     print("数据数据总数检查不一致，请检查数据集是否正确！")  return class_name  def get_transforms_setting(size):  """  获取transforms的初始设置  :param size: 图片大小  :return: transforms.compose设置  """    transform_setting = {  'train': transforms.Compose([  transforms.Resize(size),  transforms.ToTensor(),  transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])  ]),  'test': transforms.Compose([  transforms.Resize(size),  transforms.ToTensor(),  transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])  ])  }  return transform_setting  # 训练循环  
def train(dataloader, device, 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_loss  def test(dataloader, device, 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_loss  from PIL import Image  def predict_one_image(image_path, device, model, transform, classes):  """  预测单张图片  :param image_path: 图片路径  :param device: CPU or GPU    :param model: cnn模型  :param transform:    :param classes:    :return:   """  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}')**

2. model.py

import torch.nn as nn  
import torch
import torch.nn.functional as Fclass VGG16(nn.Module):  def __init__(self, num_classes):  super(VGG16, self).__init__()  # 卷积块1  self.block1 = nn.Sequential(  nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.MaxPool2d(kernel_size=2, stride=2)  )  # 卷积块2  self.block2 = nn.Sequential(  nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.Conv2d(in_channels=128, out_channels=128, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.MaxPool2d(kernel_size=2, stride=2)  )  # 卷积块3  self.block3 = nn.Sequential(  nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.MaxPool2d(kernel_size=2, stride=2)  )  # 卷积块4  self.block4 = nn.Sequential(  nn.Conv2d(in_channels=256, out_channels=512, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.MaxPool2d(kernel_size=2, stride=2)  )  # 卷积块5  self.block5 = nn.Sequential(  nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),  nn.ReLU(),  nn.MaxPool2d(kernel_size=2, stride=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=num_classes)  )  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, 1)  x = self.classifier(x)  return x

3. main.py

import torch.utils.data  
from torchvision import datasets  from Utils import USE_GPU, data_from_directory, get_transforms_setting, train, test  
from config import get_options  
from model import VGG16  # 获取参数配置  
opt = get_options()  # 设置GPU  
device = USE_GPU()  DATA_DIR = "./data/PotatoPlants"  # 导入数据  
classes_name = data_from_directory(DATA_DIR, show=True)  transforms_setting = get_transforms_setting((224, 224))  total_data = datasets.ImageFolder(DATA_DIR, transform=transforms_setting['train'])  
print(total_data)  
print(total_data.class_to_idx)  # 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])  
print(train_dataset, test_dataset)  train_dl = torch.utils.data.DataLoader(train_dataset, batch_size=opt.batch_size, shuffle=True)  
test_dl = torch.utils.data.DataLoader(test_dataset, batch_size=opt.batch_size, shuffle=True)  for X, y in train_dl:  print("Shape of X[N, C, H, W]：", X.shape)  print("Shape of y: ", y.shape, y.dtype)  break

# 加载VGG16模型  
model = VGG16(len(classes_name)).to(device)  
print(model)  # 统计模型参数量以及其他指标  
import torchsummary as summary  
summary.summary(model, (3, 224, 224))

# 正式训练  
import copy  
optimizer = torch.optim.Adam(model.parameters(), lr=opt.lr)  
loss_fn = torch.nn.CrossEntropyLoss() # 创建损失函数  train_loss, train_acc, test_loss, test_acc = [], [], [], []  
best_acc = 0    # 设置了一个最佳准确率，来用作为最佳模型的判别标准  for epoch in range(opt.epochs):  model.train()  epoch_train_acc, epoch_train_loss = train(train_dl, device, model, loss_fn, optimizer)  model.eval()  epoch_test_acc, epoch_test_loss = test(test_dl, device, model, loss_fn)  # 保存最佳模型  if epoch_test_acc > best_acc:  best_acc = epoch_test_acc  best_model = copy.deepcopy(model)  train_acc.append(epoch_train_acc)  test_acc.append(epoch_test_acc)  train_loss.append(epoch_train_loss)  test_loss.append(epoch_test_loss)  # 获取当前学习率  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 = './models/potato-model.pth'  
torch.save(model.state_dict(), PATH)  print("完成")

4. predict.py 预测单张图片

import torch  
from PIL import Image  
from Utils import predict_one_image, USE_GPU, get_transforms_setting  
from model import VGG16  classes = ['Early_blight','Late_blight', 'healthy']  transforms = get_transforms_setting([224,224])  device = USE_GPU()  
# 加载VGG16模型  
model = VGG16(3)  
model.load_state_dict(torch.load('./models/potato-model.pth', map_location=device))  
model.to(device)  img_path = "./data/PotatoPlants/Early_blight/0c4f6f72-c7a2-42e1-9671-41ab3bf37fe7___RS_Early.B 6752.JPG"  predict_one_image(img_path, device, model, transforms['train'], classes)