search

zchoi / S2-Transformer

[IJCAI 2022] Official Pytorch code for paper “S2 Transformer for Image Captioning”
https://www.ijcai.org/proceedings/2022/0224.pdf
MIT License
80 stars 4 forks source link

使用自己的数据集 #12

Open Fredham opened 6 months ago

Fredham commented 6 months ago

请问如何使用自己的数据集制作hdf5文件？

zchoi commented 2 months ago

您好，可以参考这篇论文[1]，他的repo里面提供了特征抽取方案(hdf5 file): Link

[1] Jiang, H., Misra, I., Rohrbach, M., Learned-Miller, E., & Chen, X. (2020). In defense of grid features for visual question answering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.