nihui
nihui
call `vkdev->reclaim_blob_allocator()` after uses In fact, I don't recommend manually managing GPU memory settings, as you would need to handle the lifecycle of all memory allocations. The default options should...
ref yolov8 sample project https://github.com/nihui/ncnn-android-yolov8
pnnx 转换 trace 出来的 torchscript，不支持scripting，输出信息中大量 inline function 是有问题的 标量输入需要修改模型 forward 接口，改为传入 tensor，如果标量是固定的，那么写死参数，模型不输入这个标量
感谢你的工作，请将你在实现中的笔记和心得，遇到的困难和解决方法等，记录成文章，发表在discussion分区，这将作为知识总结 https://github.com/Tencent/ncnn/discussions Thank you for your work. Please record your notes and experience in the implementation, difficulties encountered and solutions, etc. into an article and publish it in the discussion...
感谢你的工作，请将你在实现中的笔记和心得，遇到的困难和解决方法等，记录成文章，发表在discussion分区，这将作为知识总结 https://github.com/Tencent/ncnn/discussions Thank you for your work. Please record your notes and experience in the implementation, difficulties encountered and solutions, etc. into an article and publish it in the discussion...
感谢你的工作，请将你在实现中的笔记和心得，遇到的困难和解决方法等，记录成文章，发表在discussion分区，这将作为知识总结 https://github.com/Tencent/ncnn/discussions Thank you for your work. Please record your notes and experience in the implementation, difficulties encountered and solutions, etc. into an article and publish it in the discussion...
感谢你的工作，请将你在实现中的笔记和心得，遇到的困难和解决方法等，记录成文章，发表在discussion分区，这将作为知识总结 https://github.com/Tencent/ncnn/discussions Thank you for your work. Please record your notes and experience in the implementation, difficulties encountered and solutions, etc. into an article and publish it in the discussion...
It is difficult to find the corresponding compilation kit and test method for the target configuration you mentioned. opencv-mobile directly uses the original opencv source code for simplification. You may...
更新 ndk r27
> > 使用param的文件是不是有 Reshape Tensor.view_6 2 1 141 128 142 6="1w,1h,128" 它的具体实现为 v_106 = v_105.view(1, 128, v_95.size(2), v_95.size(3)) 但是我参考[官方的文档](https://github.com/Tencent/ncnn/wiki/operation-param-weight-table)，Reshape并没有6个这个参数，我用ncnn2mem导出后调试是在这个行空预测的 猜测参数支持了动态的参数，但是ncnn2mem导出的方式不支持动态参数 > > 对，有一行Reshape Tensor.view_6 2 1 141 128 142 6="1w,1h,128"...