TypeError：无法为火炬分配str.LongTensor pytoch

Question

我正在尝试将字符串列表转换为张量，但出现此错误

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]

Answer 1

您可以使用python的ord将字符转换为其unicode：

targets[i, :end] = torch.from_numpy(np.array(list(map(ord, cap[:end])))).to(torch.long)