Add source code

Author: schmidt-ju

LICENSE

@@ -1,2 +1,62 @@
-# SCENE
-Source code will be published soon.
+# SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks
+
+Official repository of the paper:\
+**[SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks](https://arxiv.org/abs/2301.03512)**\
+Thomas Monninger*, Julian Schmidt*, Jan Rupprecht, David Raba, Julian Jordan, Daniel Frank, Steffen Staab and Klaus Dietmayer\
+*Thomas Monninger and Julian Schmidt are co-first authors. The order was determined alphabetically.\
+\
+IEEE Robotics and Automation Letters (RA-L), 2023
+
+<img src="images/overview.png" width="60%">
+
+The repository contains the source code of our graph convolution operator and our experiments on publicly available knowledge graph datasets.
+
+## Citation
+If you use our source code, please cite:
+```bibtex
+@Article{monningerschmidt2023scene,
+  author={Monninger, Thomas and Schmidt, Julian and Rupprecht, Jan and Raba, David and Jordan, Julian and Frank, Daniel and Staab, Steffen and Dietmayer, Klaus},
+  journal={IEEE Robotics and Automation Letters}, 
+  title={SCENE: Reasoning About Traffic Scenes Using Heterogeneous Graph Neural Networks}, 
+  year={2023},
+  volume={8},
+  number={3},
+  pages={1531--1538},
+  doi={10.1109/LRA.2023.3234771}}
+```
+
+## License
+<a rel="license" href="http://creativecommons.org/licenses/by-nc/4.0/">
+<img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by-nc/4.0/88x31.png"
+ /></a><br />SCENE is licensed under <a rel="license" href="http://creativecommons.org/licenses/by-nc/4.0/"
+ >Creative Commons Attribution-NonCommercial 4.0 International License</a>.
+ 
+Check [LICENSE](LICENSE) for more information.
+
+## Installation
+### Install Anaconda
+We recommend using Anaconda.
+The installation is described on the following page:\
+https://docs.anaconda.com/anaconda/install/linux/
+
+### Install Required Packages
+```sh
+conda env create -f environment.yml
+```
+
+### Activate Environment
+```sh
+conda activate scene
+```
+
+## Generate Results
+```sh
+python3 main.py --dataset=aifb
+```
+Options for `--dataset` are `aifb`, `mutag`, `bgs` and `am`.
+
+## Results
+Results are stored in the `results/` folder.
+By default, it contains the original results obtained on our test system.\
+Values are reported in [our paper](https://arxiv.org/abs/2301.03512).\
+Test system specifications: Intel Core i9-7920X, NVIDIA GeForce RTX 2080 Ti.

README.md

@@ -0,0 +1,7 @@
+epochs: 60
+dropout: 0.5
+weight_decay: 1e-4
+learning_rate: 3e-3
+degree_cutting: 10
+hidden_size: 128
+num_heads: 2

configs/aifb.yaml

@@ -0,0 +1,7 @@
+epochs: 120
+dropout: 0.3
+weight_decay: 0.0003
+learning_rate: 5e-5
+degree_cutting: 10
+hidden_size: 512
+num_heads: 8

configs/am.yaml

@@ -0,0 +1,7 @@
+epochs: 200
+dropout: 0.2
+weight_decay: 0.004
+learning_rate: 0.0004
+degree_cutting: 1
+hidden_size: 64
+num_heads: 4

configs/bgs.yaml

@@ -0,0 +1,7 @@
+epochs: 200
+dropout: 0.7
+weight_decay: 0.0002
+learning_rate: 5e-5
+degree_cutting: 2
+hidden_size: 512
+num_heads: 8

configs/mutag.yaml

@@ -0,0 +1,134 @@
+name: scene
+channels:
+  - pytorch
+  - dglteam
+  - conda-forge
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - absl-py=1.4.0=pyhd8ed1ab_0
+  - aiohttp=3.7.0=py37h8f50634_0
+  - async-timeout=3.0.1=py_1000
+  - attrs=22.2.0=pyh71513ae_0
+  - blas=1.0=mkl
+  - blinker=1.5=pyhd8ed1ab_0
+  - bottleneck=1.3.5=py37h7deecbd_0
+  - brotlipy=0.7.0=py37h540881e_1004
+  - bzip2=1.0.8=h7b6447c_0
+  - c-ares=1.18.1=h7f98852_0
+  - ca-certificates=2022.12.7=ha878542_0
+  - cachetools=5.3.0=pyhd8ed1ab_0
+  - certifi=2022.12.7=pyhd8ed1ab_0
+  - cffi=1.15.0=py37h036bc23_0
+  - chardet=3.0.4=py37he5f6b98_1008
+  - charset-normalizer=2.1.1=pyhd8ed1ab_0
+  - click=8.1.3=py37h89c1867_0
+  - colorama=0.4.6=pyhd8ed1ab_0
+  - cryptography=37.0.2=py37h38fbfac_0
+  - cudatoolkit=10.2.89=hfd86e86_1
+  - decorator=5.1.1=pyhd3eb1b0_0
+  - dgl-cuda10.2=0.7.1=py37_0
+  - ffmpeg=4.3=hf484d3e_0
+  - fftw=3.3.9=h27cfd23_1
+  - flit-core=3.6.0=pyhd3eb1b0_0
+  - freetype=2.12.1=h4a9f257_0
+  - fsspec=2023.1.0=pyhd8ed1ab_0
+  - future=0.18.2=py37h89c1867_5
+  - giflib=5.2.1=h5eee18b_1
+  - gmp=6.2.1=h295c915_3
+  - gnutls=3.6.15=he1e5248_0
+  - google-auth=2.16.0=pyh1a96a4e_1
+  - google-auth-oauthlib=0.4.6=pyhd8ed1ab_0
+  - grpcio=1.38.1=py37hb27c1af_0
+  - idna=3.4=pyhd8ed1ab_0
+  - importlib-metadata=4.11.4=py37h89c1867_0
+  - intel-openmp=2021.4.0=h06a4308_3561
+  - jpeg=9b=h024ee3a_2
+  - lame=3.100=h7b6447c_0
+  - lcms2=2.12=h3be6417_0
+  - ld_impl_linux-64=2.38=h1181459_1
+  - libffi=3.4.2=h6a678d5_6
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgfortran-ng=11.2.0=h00389a5_1
+  - libgfortran5=11.2.0=h1234567_1
+  - libgomp=11.2.0=h1234567_1
+  - libiconv=1.16=h7f8727e_2
+  - libidn2=2.3.2=h7f8727e_0
+  - libpng=1.6.37=hbc83047_0
+  - libprotobuf=3.18.0=h780b84a_1
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libtasn1=4.16.0=h27cfd23_0
+  - libtiff=4.1.0=h2733197_1
+  - libunistring=0.9.10=h27cfd23_0
+  - libuv=1.40.0=h7b6447c_0
+  - libwebp=1.2.0=h89dd481_0
+  - lz4-c=1.9.4=h6a678d5_0
+  - markdown=3.4.1=pyhd8ed1ab_0
+  - markupsafe=2.1.1=py37h540881e_1
+  - mkl=2021.4.0=h06a4308_640
+  - mkl-service=2.4.0=py37h7f8727e_0
+  - mkl_fft=1.3.1=py37hd3c417c_0
+  - mkl_random=1.2.2=py37h51133e4_0
+  - multidict=6.0.2=py37h540881e_1
+  - ncurses=6.4=h6a678d5_0
+  - nettle=3.7.3=hbbd107a_1
+  - networkx=2.2=py37_1
+  - ninja=1.10.2=h06a4308_5
+  - ninja-base=1.10.2=hd09550d_5
+  - numexpr=2.8.4=py37he184ba9_0
+  - numpy=1.21.5=py37h6c91a56_3
+  - numpy-base=1.21.5=py37ha15fc14_3
+  - oauthlib=3.2.2=pyhd8ed1ab_0
+  - openh264=2.1.1=h4ff587b_0
+  - openssl=1.1.1s=h7f8727e_0
+  - packaging=23.0=pyhd8ed1ab_0
+  - pandas=1.3.5=py37h8c16a72_0
+  - pillow=9.3.0=py37hace64e9_1
+  - pip=22.3.1=py37h06a4308_0
+  - protobuf=3.18.0=py37hcd2ae1e_0
+  - pyasn1=0.4.8=py_0
+  - pyasn1-modules=0.2.7=py_0
+  - pycparser=2.21=pyhd8ed1ab_0
+  - pydeprecate=0.3.1=pyhd8ed1ab_0
+  - pyjwt=2.6.0=pyhd8ed1ab_0
+  - pyopenssl=22.0.0=pyhd8ed1ab_1
+  - pysocks=1.7.1=py37h89c1867_5
+  - python=3.7.16=h7a1cb2a_0
+  - python-dateutil=2.8.2=pyhd3eb1b0_0
+  - python_abi=3.7=2_cp37m
+  - pytorch=1.9.0=py3.7_cuda10.2_cudnn7.6.5_0
+  - pytorch-lightning=1.4.9=pyhd8ed1ab_0
+  - pytz=2022.7=py37h06a4308_0
+  - pyu2f=0.1.5=pyhd8ed1ab_0
+  - pyyaml=6.0=py37h540881e_4
+  - readline=8.2=h5eee18b_0
+  - requests=2.28.2=pyhd8ed1ab_0
+  - requests-oauthlib=1.3.1=pyhd8ed1ab_0
+  - rsa=4.9=pyhd8ed1ab_0
+  - scipy=1.7.3=py37h6c91a56_2
+  - setuptools=65.6.3=py37h06a4308_0
+  - six=1.16.0=pyhd3eb1b0_1
+  - sqlite=3.40.1=h5082296_0
+  - tensorboard=2.11.2=pyhd8ed1ab_0
+  - tensorboard-data-server=0.6.0=py37h38fbfac_2
+  - tensorboard-plugin-wit=1.8.1=pyhd8ed1ab_0
+  - tk=8.6.12=h1ccaba5_0
+  - torchaudio=0.9.0=py37
+  - torchmetrics=0.5.1=pyhd8ed1ab_0
+  - torchvision=0.10.0=py37_cu102
+  - tqdm=4.64.1=pyhd8ed1ab_0
+  - typing_extensions=4.4.0=py37h06a4308_0
+  - urllib3=1.26.14=pyhd8ed1ab_0
+  - werkzeug=2.2.2=pyhd8ed1ab_0
+  - wheel=0.37.1=pyhd3eb1b0_0
+  - xz=5.2.10=h5eee18b_1
+  - yaml=0.2.5=h7f98852_2
+  - yarl=1.6.0=py37h8f50634_0
+  - zipp=3.12.1=pyhd8ed1ab_0
+  - zlib=1.2.13=h5eee18b_0
+  - zstd=1.4.9=haebb681_0
+  - pip:
+    - isodate==0.6.1
+    - pyparsing==3.0.9
+    - rdflib==6.0.2