search

JDAI-CV / image-captioning

Implementation of 'X-Linear Attention Networks for Image Captioning' [CVPR 2020]
268 stars 52 forks source link

How to train new datasets?Can you release some code to extract features for new image? #18

Closed YJsing closed 3 years ago

YJsing commented 4 years ago

I want to train some new images.Can this code achieve? If not ,can you release some code to extract features for new image?

YehLi commented 3 years ago

Please refer to https://github.com/peteanderson80/bottom-up-attention for feature extraction.