nihui
nihui
fixed in https://github.com/Tencent/ncnn/commit/8a2eab111478ded313d2e43dd5274144ec0a65f7
会发布到新版本中，着急测试的话可以试试 https://github.com/nihui/ncnn/releases/tag/20250912
https://github.com/nihui/opencv-mobile/pull/194 兼容
> The original ticket from https://gitlab.freedesktop.org/mesa/mesa/-/issues/13014 is actually a bug on your side (a Mesa/RADV developer here) > > Disabling VK_KHR_cooperative_matrix in RADV makes it work as expected. Though with...
https://github.com/nihui/waifu2x-ncnn-vulkan/releases/tag/20250802 test build
https://github.com/Tencent/ncnn/wiki/FAQ-ncnn-produce-wrong-result#disable-fp16 尝试禁用fp16测试下
@XingRay 是输入数据构造的问题，你的代码构造了个4d，实际应该构造3d，就ok了 ```cpp // mat_in = ncnn::Mat(3, 128, 128, 1, padded_float.data); mat_in = ncnn::Mat(3, 128, 128, padded_float.data); ```
> I am experiencing the same issue. CPU based inference is correct but vulkan is invalid output on all platforms: Mac, amd, and NVIDIA. I believe one of the ncnn...
针对onnx模型转换的各种问题，推荐使用最新的pnnx工具转换到ncnn In view of various problems in onnx model conversion, it is recommended to use the latest pnnx tool to convert your model to ncnn ```shell pip install pnnx pnnx...
Thanks for your contribution !