Pytorch自定义数据集

自定义数据集的代码如下：

import os
import pandas as pd
from torchvision.io import read_image

class CustomImageDataset(Dataset):
    def __init__(self, annotations_file, img_dir, transform=None, target_transform=None):
        self.img_labels = pd.read_csv(annotations_file)
        self.img_dir = img_dir
        self.transform = transform
        self.target_transform = target_transform

    def __len__(self):
        return len(self.img_labels)

    def __getitem__(self, idx):
        img_path = os.path.join(self.img_dir, self.img_labels.iloc[idx, 0])
        image = read_image(img_path)
        label = self.img_labels.iloc[idx, 1]
　　　　　#如果需要transform。则这里传入class当中的transform函数进行transform
        if self.transform:
            image = self.transform(image)
　　　　　#另一种transform
        if self.target_transform:
            label = self.target_transform(label)
　　　　　　#先返回每一张图片，然后再返回当前图片的label
        return image, label

现在我们的自定义数据集即将做好了，然后使用dataloader模块打包数据集：

from torch.utils.data import DataLoader

train_dataloader = DataLoader(CustomImageDataset(annotations_file, img_dir, transform=None, target_transform=None), batch_size=64, shuffle=True) 

test_dataloader = DataLoader(CustomImageDataset(annotations_file, img_dir, transform=None, target_transform=None) batch_size=64, shuffle=True)

接下来就可以开始训练啦！！！

train fuction的代码：

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    model.train()
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)

        # Compute prediction error
        pred = model(X)
        loss = loss_fn(pred, y)

        # Backpropagation
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")

test function的代码：

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    model.eval()
    test_loss, correct = 0, 0
    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()
    test_loss /= num_batches
    correct /= size
    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")

一共使用5个epoch。因此代码如下：

epochs = 5
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train(train_dataloader, model, loss_fn, optimizer)
    test(test_dataloader, model, loss_fn)
print("Done!")