使用ResNet-50训练自己的数据集（花的种类）

鸿运齐天蛊

已于 2024-05-27 17:47:45 修改

阅读量437

点赞数 9

文章标签：人工智能机器学习深度学习

于 2024-05-27 17:46:54 首次发布

本文链接：https://blog.csdn.net/jingshi123456/article/details/139241571

版权

1.数据集处理

具体操作

1.把不同类别的花（或者自己数据集的不同类别）放在不同的文件夹下

2.文件夹名字是花朵类别

代码预处理

# 对数据集进行处理
import os
from shutil import copy
import random


def mkfile(file):
    if not os.path.exists(file):
        os.makedirs(file)


# 获取 photos 文件夹下除 .txt 文件以外所有文件夹名（即3种分类的类名）
file_path = 'flower_photos'
flower_class = [cla for cla in os.listdir(file_path) if ".txt" not in cla]

# 创建 训练集train 文件夹，并由3种类名在其目录下创建3个子目录
mkfile('flower_data/train')
for cla in flower_class:
    mkfile('flower_data/train/' + cla)

# 创建 验证集val 文件夹，并由3种类名在其目录下创建3个子目录
mkfile('flower_data/val')
for cla in flower_class:
    mkfile('flower_data/val/' + cla)

# 划分比例，训练集 : 验证集 = 9 : 1
split_rate = 0.1

# 遍历3种花的全部图像并按比例分成训练集和验证集
for cla in flower_class:
    cla_path = file_path + '/' + cla + '/'  # 某一类别动作的子目录
    images = os.listdir(cla_path)  # iamges 列表存储了该目录下所有图像的名称
    num = len(images)
    eval_index = random.sample(images, k=int(num * split_rate))  # 从images列表中随机抽取 k 个图像名称
    for index, image in enumerate(images):
        # eval_index 中保存验证集val的图像名称
        if image in eval_index:
            image_path = cla_path + image
            new_path = 'flower_data/val/' + cla
            copy(image_path, new_path)  # 将选中的图像复制到新路径

        # 其余的图像保存在训练集train中
        else:
            image_path = cla_path + image
            new_path = 'flower_data/train/' + cla
            copy(image_path, new_path)
        print("\r[{}] processing [{}/{}]".format(cla, index + 1, num), end="")  # processing bar
    print()

print("processing done!")

代码实现效果

2.模型训练以及结果可视化

# 模型训练

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import datasets, transforms, models
from torchvision.utils import make_grid
import numpy as np
import matplotlib.pyplot as plt
import os
# 定义数据转换
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

# 加载数据集
data_dir = 'flower_data'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train', 'val']}
dataloaders = {x: DataLoader(image_datasets[x], batch_size=4,
                             shuffle=True, num_workers=4)
               for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes

# 加载预训练的ResNet-50模型
model = models.resnet50(weights=models.ResNet50_Weights.IMAGENET1K_V1)

# 替换最后的全连接层以适配我们的分类问题
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, len(class_names))

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

# 训练模型
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = model.to(device)

def train_model(model, criterion, optimizer, num_epochs=25):
    for epoch in range(num_epochs):
        print(f'Epoch {epoch}/{num_epochs - 1}')
        print('-' * 10)

        # 每个epoch都有训练和验证阶段
        for phase in ['train', 'val']:
            if phase == 'train':
                model.train()  # 设置模型为训练模式
            else:
                model.eval()   # 设置模型为评估模式

            running_loss = 0.0
            running_corrects = 0

            # 遍历数据
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # 清零参数梯度
                optimizer.zero_grad()

                # 前向传播
                with torch.set_grad_enabled(phase == 'train'):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)

                    # 反向传播和优化
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # 统计
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]

            print(f'{phase} Loss: {epoch_loss:.4f} Acc: {epoch_acc:.4f}')

    print('Training complete')

# 调用训练函数
train_model(model, criterion, optimizer, num_epochs=10)


# 可视化一些预测结果
def visualize_model(model, num_images=6):
    was_training = model.training
    model.eval()
    images_so_far = 0
    fig = plt.figure()

    with torch.no_grad():
        for i, (inputs, labels) in enumerate(dataloaders['val']):
            inputs = inputs.to(device)
            labels = labels.to(device)

            outputs = model(inputs)
            _, preds = torch.max(outputs, 1)

            for j in range(inputs.size()[0]):
                images_so_far += 1
                ax = plt.subplot(num_images//2, 2, images_so_far)
                ax.axis('off')
                ax.set_title('predicted: {}'.format(class_names[preds[j]]))
                imshow(inputs.cpu().data[j])

                if images_so_far == num_images:
                    model.train(mode=was_training)
                    return
        model.train(mode=was_training)

def imshow(inp, title=None):
    """Imshow for Tensor."""
    inp = inp.numpy().transpose((1, 2, 0))
    mean = np.array([0.485, 0.456, 0.406])
    std = np.array([0.229, 0.224, 0.225])
    inp = std * inp + mean
    inp = np.clip(inp, 0, 1)
    plt.imshow(inp)
    if title is not None:
        plt.title(title)
    plt.pause(0.001)  # pause a bit so that plots are updated

# 可视化模型预测结果
visualize_model(model)

plt.ioff()
plt.show()

可视化效果

3.保存模型

# 保存模型
torch.save(model, 'resnet50_flowers_model.pth')

4.使用网上图片进行测试

from PIL import Image


model.eval()  # 确保模型处于评估模式

# 加载和预处理图片
def process_image(image_path):
    # 这里需要根据您的模型和数据集来定义图片的预处理步骤
    # 例如，调整大小、归一化等
    img = Image.open(image_path)
    transform = transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
    ])
    img_tensor = transform(img).unsqueeze(0)  # 添加batch维度
    return img_tensor

# 预测图片
def predict_image(image_path, model):
    img_tensor = process_image(image_path)
    img_tensor = img_tensor.to(device)  # 确保图片在正确的设备上
    with torch.no_grad():  # 确保在预测过程中不计算梯度
        output = model(img_tensor)
    _, pred = torch.max(output, 1)  # 获取最高分数的类别
    return class_names[pred[0]]

# 比较预测结果和实际标签
image_path ="D:/PyCharm 2024.1.1/pythonProject/data/2.jpg " # 替换为您的图片路径
true_label = 'meigui'  # 替换为实际的标签
predicted_label = predict_image(image_path, model)

print(f'Predicted: {predicted_label}, True: {true_label}')

全部源码

# 对数据集进行处理
import os
from shutil import copy
import random


def mkfile(file):
    if not os.path.exists(file):
        os.makedirs(file)


# 获取 photos 文件夹下除 .txt 文件以外所有文件夹名（即3种分类的类名）
file_path = 'flower_photos'
flower_class = [cla for cla in os.listdir(file_path) if ".txt" not in cla]

# 创建 训练集train 文件夹，并由3种类名在其目录下创建3个子目录
mkfile('flower_data/train')
for cla in flower_class:
    mkfile('flower_data/train/' + cla)

# 创建 验证集val 文件夹，并由3种类名在其目录下创建3个子目录
mkfile('flower_data/val')
for cla in flower_class:
    mkfile('flower_data/val/' + cla)

# 划分比例，训练集 : 验证集 = 9 : 1
split_rate = 0.1

# 遍历3种花的全部图像并按比例分成训练集和验证集
for cla in flower_class:
    cla_path = file_path + '/' + cla + '/'  # 某一类别动作的子目录
    images = os.listdir(cla_path)  # iamges 列表存储了该目录下所有图像的名称
    num = len(images)
    eval_index = random.sample(images, k=int(num * split_rate))  # 从images列表中随机抽取 k 个图像名称
    for index, image in enumerate(images):
        # eval_index 中保存验证集val的图像名称
        if image in eval_index:
            image_path = cla_path + image
            new_path = 'flower_data/val/' + cla
            copy(image_path, new_path)  # 将选中的图像复制到新路径

        # 其余的图像保存在训练集train中
        else:
            image_path = cla_path + image
            new_path = 'flower_data/train/' + cla
            copy(image_path, new_path)
        print("\r[{}] processing [{}/{}]".format(cla, index + 1, num), end="")  # processing bar
    print()

print("processing done!")
# 模型训练

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import datasets, transforms, models
from torchvision.utils import make_grid
import numpy as np
import matplotlib.pyplot as plt
import os
# 定义数据转换
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

# 加载数据集
data_dir = 'flower_data'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train', 'val']}
dataloaders = {x: DataLoader(image_datasets[x], batch_size=4,
                             shuffle=True, num_workers=4)
               for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes

# 加载预训练的ResNet-50模型
model = models.resnet50(weights=models.ResNet50_Weights.IMAGENET1K_V1)

# 替换最后的全连接层以适配我们的分类问题
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, len(class_names))

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

# 训练模型
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = model.to(device)

def train_model(model, criterion, optimizer, num_epochs=25):
    for epoch in range(num_epochs):
        print(f'Epoch {epoch}/{num_epochs - 1}')
        print('-' * 10)

        # 每个epoch都有训练和验证阶段
        for phase in ['train', 'val']:
            if phase == 'train':
                model.train()  # 设置模型为训练模式
            else:
                model.eval()   # 设置模型为评估模式

            running_loss = 0.0
            running_corrects = 0

            # 遍历数据
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # 清零参数梯度
                optimizer.zero_grad()

                # 前向传播
                with torch.set_grad_enabled(phase == 'train'):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)

                    # 反向传播和优化
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # 统计
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]

            print(f'{phase} Loss: {epoch_loss:.4f} Acc: {epoch_acc:.4f}')

    print('Training complete')

# 调用训练函数
train_model(model, criterion, optimizer, num_epochs=10)


# 可视化一些预测结果
def visualize_model(model, num_images=6):
    was_training = model.training
    model.eval()
    images_so_far = 0
    fig = plt.figure()

    with torch.no_grad():
        for i, (inputs, labels) in enumerate(dataloaders['val']):
            inputs = inputs.to(device)
            labels = labels.to(device)

            outputs = model(inputs)
            _, preds = torch.max(outputs, 1)

            for j in range(inputs.size()[0]):
                images_so_far += 1
                ax = plt.subplot(num_images//2, 2, images_so_far)
                ax.axis('off')
                ax.set_title('predicted: {}'.format(class_names[preds[j]]))
                imshow(inputs.cpu().data[j])

                if images_so_far == num_images:
                    model.train(mode=was_training)
                    return
        model.train(mode=was_training)

def imshow(inp, title=None):
    """Imshow for Tensor."""
    inp = inp.numpy().transpose((1, 2, 0))
    mean = np.array([0.485, 0.456, 0.406])
    std = np.array([0.229, 0.224, 0.225])
    inp = std * inp + mean
    inp = np.clip(inp, 0, 1)
    plt.imshow(inp)
    if title is not None:
        plt.title(title)
    plt.pause(0.001)  # pause a bit so that plots are updated

# 可视化模型预测结果
visualize_model(model)

plt.ioff()
plt.show()