About how to get the caption of a input pic with my own pretrained model. about rstnet HOT 3 CLOSED

I can get the output token through the variable caps_gen,but I don't know which image the caption corresponds to.
I also want to know how can i get the caption of a causal image instead of the coco image loaded by dataloader function.

from rstnet.

Hello, thanks for sharing your code! But I wonder how to get a image's caption like figure 1(b) or 6 in your artical Could you share me the code ? Thanks a lot!

Hello, you can refer to the function predict_captions() in test_transformer.py.

from rstnet.

I can get the output token through the variable caps_gen,but I don't know which image the caption corresponds to. I also want to know how can i get the caption of a causal image instead of the coco image loaded by dataloader function.

you can refer to the blow code in test_online.py.

from rstnet.