Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
zhounuoyan ea0043649b | 5 months ago | |
---|---|---|
models | 5 months ago | |
README.md | 5 months ago | |
dataprocessing.py | 5 months ago | |
layers.py | 5 months ago | |
loss.py | 5 months ago | |
main.py | 5 months ago | |
metrics.py | 5 months ago | |
models.py | 5 months ago | |
requirements.txt | 5 months ago | |
utils.py | 5 months ago |
The manuscript titled "Deep Multiview Clustering by Contrasting Cluster Assignments" is accepted by ICCV 2023. Please feel free to contact me if you have any prbolem.
You may reproduce the experimental results presented in the paper if setting the following parameter "load_model" to True. This means that the program will load the trained model provided by the authors for clustering tasks.
parser.add_argument('--load_model', default=False, help='Testing if True or training.')
You may consult the commented code in the file “main.py” for guidance on selecting the proper parameters if the trained model is unavailable for additional datasets.
Thank you.
--Prerequisites
Linux
--Required Python Packages
python>=3.9.7
pytorch>=1.7.1
numpy>=1.21.5
scikit-learn>=1.0.1
scipy>=1.7.3
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》