Zhouzhou

look like conv3x3s1_neon in troubles; I suggest writing unit tests directly to test this part； checkout tests/ which have convolution Layer unit test; or just use range data to test...

简单来说，以ncnn 编译出的include +lib 作为第三方库，在这个基础上你再编译一个yolcat 库以供调用； 1.如果你是以andorid为host，即在安卓上编译 执行，可以参考.github/workflow/ 下面的.yaml 配置文件； 2.如果你是以Ubuntu或者win为host，你需要使用ndk交叉编译，目标平台是你的android，系统版本等等你得参考ndk； 你可以考虑先在host 上用ncnn 实现yolact，再决定怎么封装成可以调用的库（动态或静态），通过什么方式调用（apk，可执行文件等等）

There have two ways to fix this error: 1. check if 'tile' operation is essential to CRNN。 remove tile operation and reconnect the tile input and the tile output; Test...

OK,Sir make sure what operation your net use; in sonme hardware operation like convolution, ncnn maybe use pack,which means Change memory layout to accommodate L1 cache of hardware,or other Acceleration...

I get same error on Jetson Orin AGX, I think maybe the trt version need 8.6.0 but for jetpack, trt only is 8.5.3, so when trtexec deal with the onnx...