- Clone the repository
git clone https://github.com/sx-zhang/GMAN.git
and move into the top-level directorycd GMAN
- Create conda environment.
conda env create -f environment.yml
- Activate the environment.
conda activate ng
- We provide pre-trained model of our GMAN in the
trained_models
directory. - Download our dataset.
- Then extract files in
data
bytar -zxvf ai2thor_GMAN.tar.gz
- The
data
folder should look like this
data/
└── ai2thor//
├── FloorPlan1/
│ ├── resnet18_featuremap.hdf5
│ ├── graph.json
│ ├── visible_object_map.json
│ ├── att_in_view_v2.hdf5
│ ├── grid.json
├── FloorPlan2/
└── ...
python main.py --title Basemodel --model BaseModel --workers 12 -–gpu-ids 0
python main.py --title GMAN --model GMAN --workers 12 -–gpu-ids 0 --num_steps 20
python full_eval.py \
--title GMAN \
--model GMAN \
--results-json GMAN_seen.json \
--gpu-ids 0 \
--num_steps 20 \
--seen seen
python full_eval.py \
--title GMAN \
--model GMAN \
--results-json GMAN_unseen.json \
--gpu-ids 0 \
--num_steps 20 \
--seen unseen