data_loader.py 文件源码

def collate_fn(data):
    """Creates mini-batch tensors from the list of tuples (image, caption).

    We should build custom collate_fn rather than using default collate_fn, 
    because merging code (including padding) is not supported in default.

    Args:
        data: list of tuple (image, caption). 
            - image: torch tensor of shape (3, 256, 256).
            - caption: torch tensor of shape (?); variable length.

    Returns:
        images: torch tensor of shape (batch_size, 3, 256, 256).
        targets: torch tensor of shape (batch_size, padded_length).
        lengths: list; valid length for each padded caption.
    """
    # Sort a data list by code length (descending order).
    data.sort(key=lambda x: len(x[1]), reverse=True)
    images, captions = zip(*data)

    # Merge images (from tuple of 3D tensor to 4D tensor).
    images = torch.stack(images, 0)

    # Merge code (from tuple of 1D tensor to 2D tensor).
    lengths = [len(cap) for cap in captions]
    targets = torch.zeros(len(captions), max(lengths)).long()
    for i, cap in enumerate(captions):
        end = lengths[i]
        targets[i, :end] = cap[:end]        
    return images, targets, lengths