Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
jiaqi bc0807f899 | 1 year ago | |
---|---|---|
.. | ||
output | 1 year ago | |
util | 2 years ago | |
Client_pretrain_A.py | 2 years ago | |
Client_pretrain_B.py | 2 years ago | |
README.md | 2 years ago | |
Server.py | 2 years ago | |
engine_pretrain.py | 2 years ago | |
models_mae.py | 2 years ago | |
models_mae_3chans.py | 2 years ago |
本示例场景为Fed-Dropout算法在MAE预训练模型上的应用实例。Fed-Dropout是一种采用随机Dropout思想的联邦学习参数优化算法,可以有效降低Client端通信及计算量负担,减轻Client端参与联邦学习的压力。
数据集:先天性心脏病医学图像,训练图像总量:4946,Client 1:2500,Client 2:2446
基础模型:MAE
Dropout Rate: 20%
python Server.py
python Client_pretrain_A.py
python Client_pretrain_B.py
鹏城众智AI协同计算平台AISynergy是一个分布式智能协同计算平台。该平台的目标是通过智算网络基础设施使能数据、算力、模型、网络和服务,完成跨多个智算中心的协同计算作业,进而实现全新计算范式和业务场景,如大模型跨域协同计算、多中心模型聚合、多中心联邦学习等。
Java Vue Python JavaScript Go other
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》