环境配置：

conda create -n neuralkg python=3.8
conda activate neuralkg
pip install torch==1.9.1+cu111 -f https://download.pytorch.org/whl/torch_stable.html
pip install dgl-cu111 dglgo -f https://data.dgl.ai/wheels/repo.html
pip install neuralkg

!

conda install cudatoolkit

git clone https://github.com/zjukg/NeuralKG.git
cd NeuralKG
python setup.py install

在main.py文件最上方添加：

import sys
sys.path.insert(0,"./src")

Training

# Use bash script
sh ./scripts/your-sh# Use config
python main.py --load_config --config_path <your-config>

以SEGNN为例：

修改配置文件

修改./scripts/FreeBase/SEGNN_FB.sh中NUM_WORKERS（如10->4）

vim ./scripts/FreeBase/SEGNN_FB.sh

运行

# Use bash script
sh ./scripts/FreeBase/SEGNN_FB.sh
# Use config
python main.py --load_config --config_path ./config/FreeBase/SEGNN_FB15K237.yaml

Evaluation

python main.py --test_only --checkpoint_dir <your-model-path>