resnet50 分类 训练自己的数据集 测试 代码

下面是使用PyTorch实现在自己的数据集上训练和测试ResNet50模型的代码示例：

import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
from torch.utils.data import DataLoader
from torchvision import datasets, models, transforms

# 定义数据预处理
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 = '/path/to/dataset'
image_datasets = {x: datasets.ImageFolder(root=data_dir + '/' + x, transform=data_transforms[x]) for x in ['train', 'val']}
dataloaders = {x: DataLoader(image_datasets[x], batch_size=16, 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

# 定义模型
model = models.resnet50(pretrained=True)
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)

# 定义学习率调整策略
scheduler = lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)

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

best_model_wts = model.state_dict()
best_acc = 0.0

for epoch in range(25):
    print('Epoch {}/{}'.format(epoch+1, 25))
    print('-' * 10)

    for phase in ['train', 'val']:
        if phase == 'train':
            model.train()
        else:
            model.eval()

        running_loss = 0.0
        running_corrects = 0

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

            optimizer.zero_grad()

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

                if phase == 'train':
                    loss.backward()
                    optimizer.step()

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

        if phase == 'train':
            scheduler.step()

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

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

        if phase == 'val' and epoch_acc > best_acc:
            best_acc = epoch_acc
            best_model_wts = model.state_dict()

# 测试模型
model.load_state_dict(best_model_wts)

model.eval()
running_corrects = 0

for inputs, labels in dataloaders['val']:
    inputs = inputs.to(device)
    labels = labels.to(device)

    with torch.set_grad_enabled(False):
        outputs = model(inputs)
        _, preds = torch.max(outputs, 1)

    running_corrects += torch.sum(preds == labels.data)

test_acc = running_corrects.double() / dataset_sizes['val']

print('Test Acc: {:.4f}'.format(test_acc))

注：代码中的 `data_dir` 需要替换成你自己的数据集路径。