search

JDAI-CV / image-captioning

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

about testing on raw image #9

Closed wanboyang closed 4 years ago

wanboyang commented 4 years ago

Thank you for your brilliant work. I don't find a way to test pretrained model on the raw images in this source code. Could you provide the feature extraction code or relative code link for testing raw images? Thanks

Panda-Peter commented 4 years ago

With regard to raw images, you can refer the instructions in https://github.com/peteanderson80/bottom-up-attention for bottom-up feature extraction.