torch.utils.data.DataLoader

collate_fn, 可以通过它来决定如何对数据进行批处理。但是绝大多数情况下默认值就能运行良好。

dataloader = DataLoader(transformed_dataset, batch_size=4,
                        shuffle=True, num_workers=4)


# 辅助功能：显示批次
def show_landmarks_batch(sample_batched):
    """Show image with landmarks for a batch of samples."""
    images_batch, landmarks_batch = \
            sample_batched['image'], sample_batched['landmarks']
    batch_size = len(images_batch)
    im_size = images_batch.size(2)
    grid_border_size = 2

    grid = utils.make_grid(images_batch)
    plt.imshow(grid.numpy().transpose((1, 2, 0)))

    for i in range(batch_size):
        plt.scatter(landmarks_batch[i, :, 0].numpy() + i * im_size + (i + 1) * grid_border_size,
                    landmarks_batch[i, :, 1].numpy() + grid_border_size,
                    s=10, marker='.', c='r')

        plt.title('Batch from dataloader')

for i_batch, sample_batched in enumerate(dataloader):
    print(i_batch, sample_batched['image'].size(),
          sample_batched['landmarks'].size())

    # 观察第4批次并停止。
    if i_batch == 3:
        plt.figure()
        show_landmarks_batch(sample_batched)
        plt.axis('off')
        plt.ioff()
        plt.show()
        break