caption.py:IndexError: tensors used as indices must be long, byte or bool tensors

[AndreSun98]

When I run caption.py,I got the following error: Traceback (most recent call last): File "D:/2021/sjt/code/a-PyTorch-Tutorial-to-Image-Captioning-master/caption.py", line 217, in seq, alphas = caption_image_beam_search(encoder, decoder, args.img, word_map, args.beam_size) File "D:/2021/sjt/code/a-PyTorch-Tutorial-to-Image-Captioning-master/caption.py", line 113, in caption_image_beam_search seqs_alpha = torch.cat([seqs_alpha[prev_word_inds.long()], alpha[prev_word_inds].unsqueeze(1)], IndexError: tensors used as indices must be long, byte or bool tensors

[zhongchaotie]

I had the same problem

[vernal0]

I have the same problem. Have you solved it？

[HackInSouth]

    prev_word_inds = top_k_words / vocab_size

You can try changing the "/" in the above code to "//".

[wenshihao1]

你好，解决了没

[01620syf]

我也遇到了同样的问题，请问怎么解决