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>>>
godsayyou
/
MegEngine
forked from OpenI/MegEngine
Not watched
1
4
Fork 6
Code
Releases 0 Wiki Activity
Issues 0 Pull Requests 0 Datasets 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.
1169 Commits
8 Branches
29 MiB
33 Download
 
 
 
 
 
 
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
MegEngine/sdk/xor-deploy
Megvii Engine Team b310f2615b feat(mge/imperative): implement trace and dump under new core implementation 3 years ago
..
README.md fix(mge/sdk): fix README.md and add missed example 4 years ago
xor_deploy.cpp MegEngine: Initial commit of MegEngine. 4 years ago
xornet.py feat(mge/imperative): implement trace and dump under new core implementation 3 years ago

README.md

Example to deploy a MegEngine model using C++

  • Step 1: compile MegEngine for deployment following README.md

  • Step 2: compile the example by

    $CXX -o xor_deploy -I$MGE_INSTALL_PATH/include  xor_deploy.cpp -L$MGE_INSTALL_PATH/lib64/ -lmegengine

    where $CXX is the C++ compiler and $MGE_INSTALL_PATH is the MegEngine install path.

  • Step 3: run with dumped model

    The dumped model can be obtained by running xornet.py

    LD_LIBRARY_PATH=$MGE_INSTALL_PATH/lib64:$LD_LIBRARY_PATH ./xor_deploy xornet_deploy.mge 0.6 0.9

    Sample output:

    Predicted: 0.999988 1.2095e-05
Delete task

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

cancel
confirm

天元（MegEngine）是旷视自主研发的开源深度学习框架，于2020年3月正式在 OpenI 启智社区开源，天元能够帮助开发者高效的完成深度学习算法的设计、训练、部署，有效提升AI研发工作效率。

C++ Cuda Python C CMake other

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