ONNX::LayerNormalization Converted Failed

[ThisisBillhe]

平台(如果交叉编译请再附上交叉编译目标平台):

Platform(Include target platform as well if cross-compiling): x86-64

Github版本:

Github Version:

直接下载ZIP包请提供下载日期以及压缩包注释里的git版本(可通过7z l zip包路径命令并在输出信息中搜索Comment 获得，形如Comment = bc80b11110cd440aacdabbf59658d630527a7f2b)。 git clone请提供 git commit 第一行的commit id
Comment = d8266f9
Provide date (or better yet, git revision from the comment section of the zip. Obtainable using 7z l PATH/TO/ZIP and search for Comment in the output) if downloading source as zip,otherwise provide the first commit id from the output of git commit

编译方式:

Compiling Method

请在这里粘贴cmake参数或使用的cmake脚本路径以及完整输出
Paste cmake arguments or path of the build script used here as well as the full log of the cmake proess here or pastebin

mkdir build && cd build
cmake .. -DMNN_BUILD_CONVERTER=ON -DMNN_BUILD_TORCH=ON
make -j8

编译日志:

Build Log:

[100%] Built target TestPassManager

粘贴在这里
Paste log here or pastebin

基于部署ChatGLM的案例，通过onnx转换layernorm应该是支持的，请问如何解决？

[jxt1234]

layernorm 是 onnx 较新的算子，可以先在导出 onnx 时把 opset 设低些，比如 11 ，就不会产生 layernorm

[ThisisBillhe]

感谢！