Datasets used in the experiments can be downloaded from the following link:
👉 [https://drive.google.com/file/d/1eYBPsOP9JJd7zVjpXUFnWhNIGfw-FZid/view?usp=drive_link]
⚠️ After downloading, make sure to place the extracted files in the following directories:
HybridANNS/data/Experiment/ HybridANNS/data/temp/
Each hybrid filtering algorithm is implemented under the algorithm/ directory.
To reproduce experiments for a specific algorithm, please refer to its respective README.md file:
algorithm/
├── SeRF/
│ └── README.md
├── iRange/
│ └── README.md
├── WinFilter/
│ └── README.md
...
If you want to quickly run the experiments, you can use the scripts provided under the script/ directory for one-click execution:
script/
└── DSG/
└── run.py
⚠️ Important Notes Before Running:
- Please carefully read the code beforehand to understand its logic.
- Many algorithms require proper environment setup.
It is strongly recommended to first read theREADME.mdfiles under each algorithm folder and complete the required environment configuration.- Make sure the dataset paths are correctly set as mentioned above.
If you encounter any problems, you can refer to the original code repository for more details.
1 commits
C
32.0%
Fortran
15.6%
Jupyter Notebook
12.9%
Python
11.6%
Assembly
9.1%
C++
8.1%
Makefile
6.1%
CMake
3.4%
Datasets used in the experiments can be downloaded from the following link:
👉 [https://drive.google.com/file/d/1eYBPsOP9JJd7zVjpXUFnWhNIGfw-FZid/view?usp=drive_link]
⚠️ After downloading, make sure to place the extracted files in the following directories:
HybridANNS/data/Experiment/ HybridANNS/data/temp/
Each hybrid filtering algorithm is implemented under the algorithm/ directory.
To reproduce experiments for a specific algorithm, please refer to its respective README.md file:
algorithm/
├── SeRF/
│ └── README.md
├── iRange/
│ └── README.md
├── WinFilter/
│ └── README.md
...
If you want to quickly run the experiments, you can use the scripts provided under the script/ directory for one-click execution:
script/
└── DSG/
└── run.py
⚠️ Important Notes Before Running:
- Please carefully read the code beforehand to understand its logic.
- Many algorithms require proper environment setup.
It is strongly recommended to first read theREADME.mdfiles under each algorithm folder and complete the required environment configuration.- Make sure the dataset paths are correctly set as mentioned above.
If you encounter any problems, you can refer to the original code repository for more details.
1 commits
C
32.0%
Fortran
15.6%
Jupyter Notebook
12.9%
Python
11.6%
Assembly
9.1%
C++
8.1%
Makefile
6.1%
CMake
3.4%