Skip to content

Latest commit

 

History

History
16 lines (10 loc) · 629 Bytes

README.md

File metadata and controls

16 lines (10 loc) · 629 Bytes

Knowledge Retrieval

The noagarcia/context-art-classification is borrowed to predict artistic attributes.

The jwyang/faster-rcnn is borrowed to detect visual objects.

The facebookresearch/DrQA is responsible for knowledge retrieval based on the predicted and detected visual concept.

You should prepare these requirements, pre-trained models, and the database etc., according to their source repos.

Then,

python prepare_visual_concept.py
bash run_retrieve.sh