Runyu Lu comments

Results 17 comments of


                                            Runyu Lu

[feat] cuda graph support and refactor non-functional api

All Unit Test: ![image](https://github.com/hpcaitech/ColossalAI/assets/77330637/5f42271b-868e-4847-8d12-6d3176c85d8b)

[feat] cuda graph support and refactor non-functional api

* After Fix Conflicts with other PR, pass all unit test: ![image](https://github.com/hpcaitech/ColossalAI/assets/77330637/ef4406de-0536-4aef-94f2-5a00178d570b)

How to convert yolov5 to NCNN?

> I change the param like this Input images 0 1 images Exp focus 1 1 images 207 Convolution Conv_41 1 1 207 208 0=32 1=3 11=3 2=1 12=1 3=1...

音频可视化：采样、频率和傅里叶变换

谢谢您的文章分享🥳，本人感到十分受用，希望博主能够分享更多有关知识

请问怎么构建ncnn的3d mat输入？

插个眼，看源码好像目前确实不太支持？缺少d这个额外维度，不过如果这样的话，ncnn的3D卷积神经网络是如何部署的😢

请问怎么构建ncnn的3d mat输入？

或许你可以直接用这个mat来进行初始化： `NCNN_FORCEINLINE Mat::Mat(int _w, int _h, int _d, int _c, void* _data, size_t _elemsize, Allocator* _allocator)`

请问怎么构建ncnn的3d mat输入？

请问你的torch版本？pnnx目前支持的torch版本为1.8+ @Lin-sudo