# clone the repository
git clone https://github.com/cshizhe/asg2cap.git
cd asg2cap
# clone caption evaluation codes
git clone https://github.com/cshizhe/eval_cap.git
export PYTHONPATH=$(pwd):${PYTHONPATH}

cd controlimcap/driver

# support caption models: [node, node.role, 
# rgcn, rgcn.flow, rgcn.memory, rgcn.flow.memory]
# see our paper for details
mtype=rgcn.flow.memory 

# setup config files
# you should modify data paths in configs/prepare_*_imgsg_config.py
python configs/prepare_coco_imgsg_config.py $mtype
resdir='' # copy the output string of the previous step

# training
python asg2caption.py $resdir/model.json $resdir/path.json $mtype --eval_loss --is_train --num_workers 8

# inference
python asg2caption.py $resdir/model.json $resdir/path.json $mtype --eval_set tst --num_workers 8

JSON Format:
{
	"region_id": {
		"objects":[
			{
	     		"object_id": int, 
	     		"name": str, 
	     		"attributes": [str],
				"x": int,
				"y": int, 
				"w": int, 
				"h": int
			}],
  	  "relationships": [
			{
				"relationship_id": int,
				"subject_id": int,
				"object_id": int,
				"name": str
			}],
  	  "phrase": str,
  }
}

@article{chen2020say,
  title={Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs},
  author={Chen, Shizhe and Jin, Qin and Wang, Peng and Wu, Qi},
  journal={CVPR},
  year={2020}
}