cgtuebingen / infomark-deprecated Goto Github PK

Hi, thank you so much for sharing your paper and code(https://github.com/cgtuebingen/will-people-like-your-image)! I have some questions and hope you could help me.
I try to run the demo/image_sorting/score.py and test some images, but I was puzzled to the scores results.For example,I test two images and score results is tmp1.jpg [923522.3] and
tmp2.jpg [315032.5], Wow, the score value was so big .Was the bigger the better?How to normalize to 0 to 1 ?
Besides, I found the score.py code load mean_bgr = pickle.load(hnd).transpose(1, 2, 0),but the Variable mean_bgr was never used,Why？
It will be great if you can help me, thank you a lot.

• initial docker-compose
• docker volumes for uploads
• clean up .env vars
• serve static files
• provide shell
• add workers
• add nginx reverse proxy for port 3000

start_worker.sh.zip

add Dockerfile for Submission testing to /config/containers/dockerfiles/submissions/Dockerfile

see branch dev

sudo docker-compose build
sudo docker-compose up

sudo docker-compose run web rake db:create
sudo docker-compose run web rake db:migrate
sudo docker-compose run web rake db:seed

see localhost:3000