关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
JDOpenISCT
/
CM-NAS
mirror of https://github.com/JDAI-CV/CM-NAS
Not watched
7
19
Fork 7
Code
Releases 0 Wiki Activity
Issues 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
5 Commits
1 Branch
57 KiB
11 Download
 
 
Branch: main
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'main'
${ noResults }
CM-NAS/models
Aber Hu aa58897bb7 CM-NAS 2 years ago
..
__init__.py CM-NAS 2 years ago
model_base.py CM-NAS 2 years ago
model_eval_op.py CM-NAS 2 years ago
resnet.py CM-NAS 2 years ago
utils.py CM-NAS 2 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

CM-NAS算法旨在对跨模态识别网络中逐层的批归一化（Batch Norm）进行自动化地搜索，选择出最优的拆分和共享批归一化组合，分别统计模态拆分和模态共享的统计量，减少模态差异，进而提升跨模态识别性能。

Python Shell

Please read the following content carefully:

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》

Agree and continue
Disagree, exit