Awesome
Hierarchical Object-to-Zone Graph for Object Navigation
Sixian Zhang, Xinhang Song, Yubing Bai, Weijie Li, Yakui Chu, Shuqiang Jiang (Accepted by ICCV 2021)
ICCV 2021 Paper | Arxiv Paper | Video demo
Setup
- Clone the repository
git clone https://github.com/sx-zhang/HOZ.git
and move into the top-level directorycd HOZ
- Create conda environment.
conda env create -f environment.yml
- Activate the environment.
conda activate ng
- We provide pre-trained model of hoz and hoztpn. For evaluation and fine-tuning training, you can download them to the
trained_models
directory. - Download the dataset, which refers to ECCV-VN. The offline data is discretized from AI2THOR simulator.
Thedata
folder should look like this
data/
└── Scene_Data/
├── FloorPlan1/
│ ├── resnet18_featuremap.hdf5
│ ├── graph.json
│ ├── visible_object_map_1.5.json
│ ├── det_feature_categories.hdf5
│ ├── grid.json
│ └── optimal_action.json
├── FloorPlan2/
└── ...
HOZ graph Construction (Updating)
Training and Evaluation
Train the baseline model
python main.py --title Basemodel --model BaseModel --workers 12 -–gpu-ids 0
Train our HOZ model
python main.py --title HOZ --model HOZ --workers 12 -–gpu-ids 0
Evaluate our HOZ model
python full_eval.py --title HOZ --model HOZ --results-json HOZ.json --gpu-ids 0
Evaluate our HOZ-TPN model
python full_eval.py --title TPNHOZ --model MetaMemoryHOZ --results-json HOZTPN.json --gpu-ids 0
Citing
If you find this project useful in your research, please consider citing:
@InProceedings{Zhang_2021_ICCV,
author = {Zhang, Sixian and Song, Xinhang and Bai, Yubing and Li, Weijie and Chu, Yakui and Jiang, Shuqiang},
title = {Hierarchical Object-to-Zone Graph for Object Navigation},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2021},
pages = {15130-15140}
}