YinggangLi

How to build mixed precision engine ? Can you provide an example ?

How can you set different precision in different part when creating engine? Can you show me a code example? @HaisongDing

> > How can you set different precision in different part when creating engine? Can you show me a code example? @HaisongDing > > For example, in the [detectron2 example](https://github.com/NVIDIA/TensorRT/blob/5f422623e7f5bdc593b781695cbddda99124c9b8/samples/python/detectron2/build_engine.py#L169)....

@HaisongDing Yes, I have used torch-1.13.1, opset17, tensorrt-8.6.1. The layernorm nodes in onnx are still described as 'Sub, Add, ReduceMean...'. Should it be a whole INormalization node if used properly?

从提供的代码上看上去，有可能是inBuf.strides[0]计算出来的内存字节数，和CalcRequirements计算出的inReqs的strides不一致，建议把inBuf和inReqs的strides属性打印出来看一下

另外我之前实验时记得 CVCUDA上image tensor的内存是按照width \times 3，以32字节对齐的， 经过CVCUDA OP的操作后，width \times 3是32的整数倍

I am not really using this stateful model, just in the process of reading the source code had a question, thank you for reply. ---Original--- From: "Slyne ***@***.***> Date: Wed,...