densecap
densecap copied to clipboard
invalid pretrained model
I download the pertrained model and test it with imgs/elephant.jpg. Program can be run successfully but the results are not acceptable. The results are something like "a large brown and white and white and white and white and white and white". What I only change is that not using cudnn in run_model.lua. Does anyone meet the same problem?
Hey, Check this docker image I created for running dense cap in gpu! https://hub.docker.com/r/jainal09/densecap_gpu It runs successful in gpu