数据加载器 shuffle=False，但图像顺序在每个时期都会改变

Question

即使我使用

'shuffle=False'

，图像也会随机化每个时期。

这是创建加载器的代码：

data_set = dset.CIFAR10(root='./data/cifar10', train=True, transform=transform, download=True)
train_loader, test_loader = create_loader_from_data_set(data_set, n_samples, batch_size, num_workers)

def create_loader_from_data_set(data_set, n_samples, batch_size, num_workers, test_size=0.2):
    indices = list(range(len(data_set)))
    selected_indices = random.sample(indices, n_samples)

    train_indices, test_indices = train_test_split(selected_indices, test_size=test_size, random_state=42)

    train_sampler = SubsetRandomSampler(train_indices)
    test_sampler = SubsetRandomSampler(test_indices)

    train_loader = DataLoader(data_set, batch_size=batch_size, num_workers=num_workers, sampler=train_sampler, shuffle=False)
    test_loader = DataLoader(data_set, batch_size=batch_size, num_workers=num_workers, sampler=test_sampler, shuffle=False)
    return train_loader, test_loader

这是训练循环：

def train_epoch(epoch, network, loader, optimizer, batch_size):
    network.train()
    for batch_index, sample_tensor in enumerate(loader):
        batch_images, _ = sample_tensor 

我在每个时期得到不同的图像顺序（也不是相同的批次）。 shuffle=False 不应该保持顺序相同吗？

谢谢！

我也尝试过使用发电机，但它不起作用：

gen = torch.Generator()

train_loader = DataLoader(data_set, batch_size=batch_size, num_workers=num_workers, sampler=train_sampler, generator=gen)

Answer 1

您应该尝试

train_test_split(..., shuffle = False)

，因为此函数的默认值为 True。

参考 -> https://scikit-learn.org/stable/modules/ generated/sklearn.model_selection.train_test_split.html#sklearn.model_selection.train_test_split