midway

android平台运行NPU推理闪退问题

8

# 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): 使用arm64-v8a版本在mate 40 pro（麒麟9000，NPU vertion 100.511.020.100）手机安装MNN的NPU运行环境。 但是运行时cpu推理运行正常。npu推理时app出现闪退情况。 按照语雀的文档说明，将libMNN_NPU.so, libhiai_ir_build.so, libhiai_ir.so, libhiai.so动态加载。运行时提示缺少libhiai_om.so 以及libc++.so的动态库。动态加载这两个库后还是不能正常运行。 # 错误日志: 查看log的时候出现如下错误 ``` I/WZT_MNN: model path:/data/user/0/com.tencent.yolomnn/cache/inception.mnn I/WZT_MNN: Start...

How can I implement the mapping operations on CPU cores?

1

Dear authors: I want to execute torchsparse to analyze the performance of some operators on CPUs. However, I notice that the mapping operations like "F.build_kernel_map" can only be executed on...