A prototype implementation of EQUI-VOCAL, which is a system to automatically synthesize compositional queries over videos from limited user interactions. See the technical report and the website for more details.
Download training videos at Dataset → Training Videos
Create new folder equi_app/static/equi_app/clevrer and place downloaded videos in it
Download demo_queries_scene_graph and move to EQUI-VOCAL/inputs
in equi_app/views.py
line 11: change filepath in sys.path.append() to path to EQUI-VOCAL directory
line 12: comment out
line 67: change input_dir value to path to EQUI-VOCAL/inputs folder
brew services restart postgresql@14
pg_ctl -D /usr/local/var/postgresql@14 restart
brew services stop postgresql@14
The name of the database is equi_app
psql equi_app
compile (macOS):
cc -I /usr/local/Cellar/postgresql@14/14.6_1/include/postgresql@14/server -c functors.c
cc -bundle -flat_namespace -undefined suppress -o functors.so functors.o
source env/bin/activate
python manage.py runserver