pkl文件相关问题

[Leng-bingo]

请问pkl每句话对应的图像的512维矩阵，是如何编码形成的，非常感谢！

[buxiangzhiren]

那个矩阵没有用在代码里面，可以不用管。

[Leng-bingo]

我想换成自己的数据集，这个pkl文件不需要生成么？

[buxiangzhiren]

需要，但是不需要里面512维的特征

[Leng-bingo]

那就是把每个图像的caption对应到自己数据集上，再把图像目录和对应json文件按照格式替换。

非常感谢，麻烦您了

[buxiangzhiren]

对的，不客气

[Leng-bingo]

我现在去试一试，感谢~

[Leng-bingo]

还有个小问题，您的json格式是下面这种，还是有带每个词语分词的那种

{"image_id": 133071,"id": 829693,"caption": "White Plate with a lot of guacamole and an extra large dollop of sour cream over meat"},{"image_id": 133071,"id": 829717,"caption": "A dinner plate has a lemon wedge garnishment."}

[buxiangzhiren]

还有一个可能的问题是，validation计算cider的时候，由于用的是coco那边的code，这里可能你还要改一下。或者你也可以自己写拿着生成的结果直接计算cider。

[Leng-bingo]

还没到那一步嘞(灬ꈍ ꈍ灬)，先跑起来！

[buxiangzhiren]

还有个小问题，您的json格式是下面这种，还是有带每个词语分词的那种

{"image_id": 133071,"id": 829693,"caption": "White Plate with a lot of guacamole and an extra large dollop of sour cream over meat"},{"image_id": 133071,"id": 829717,"caption": "A dinner plate has a lemon wedge garnishment."}

就是你发的这种

[Leng-bingo]

感谢！祝您再发一篇CVPR！

[rongtongxueya]

感谢！祝您再发一篇CVPR！ I met the same problem as you, but I don't know how to generate the pkl. I printed and saw that the pkl file has a clip_embedding more than the json file, I don't know how to get this embedding, can someone kind give me some advice？