Is there a way I could plug in my own set of images to generate predictions for the same?

mrwu-mac / DIFNet

This repository is for the paper ``DIFNet: Boosting Visual Information Flow for Image Captioning'' (CVPR 2022).

BSD 3-Clause "New" or "Revised" License

20 stars 7 forks source link

Is there a way I could plug in my own set of images to generate predictions for the same? #3

Closed atul1234anand closed 1 year ago

mrwu-mac commented 1 year ago

To run the code, the detection features and segmentation features are need to be extracted according to Data preparation. Then load the features by your favorite way and use generate_caption.py to generate predictions.