更换数据集问题

[Leng-bingo]

如果想更换自己的其他数据集，只需要对应以下格式即可么。

│MSCOCO_Caption/
├──annotations/
│  ├── captions_train2014.json
│  ├── captions_val2014.json
├──train2014/
│  ├── COCO_train2014_000000000009.jpg
│  ├── ......
├──val2014/ 
│  ├── COCO_val2014_000000000042.jpg
│  ├── ......

[Leng-bingo]

还有就是下面的json文件切分好的哪里可以下载呢，里面的格式是什么样子的，再次感谢

├──annotations/
│  ├── captions_train2014.json
│  ├── captions_val2014.json

[buxiangzhiren]

你需要自己生成.pkl文件，只要是image和text一对的那种就行。然后json文件你可以自己用加载了看一下

[buxiangzhiren]

json文件是coco数据集自己提供的

[rongtongxueya]

hi，dude.I met the same problem as this 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