CarkusL

> @CarkusL, I have tried your steps on pointpillars with Waymo config. But I faced the error above! Can you please tell me what I am missing!. Thanks! [11/01/2021-20:06:29] [E]...

using docker is the most convenient way for me. If you install the tensorRT, you don't need docker.

Did you use -O3 flag when you compiled the program? https://github.com/CarkusL/CenterPoint/blob/9980cdb56fb928528e69937f415071613eedf028/tensorrt/samples/Makefile.config#L263

By the way, The post-processing runs on the CPU, and it is not accelerated with GPU. It will take a lot of time, when the model outputs many boxs

> > Did you use -O3 flag when you compiled the program? > > https://github.com/CarkusL/CenterPoint/blob/9980cdb56fb928528e69937f415071613eedf028/tensorrt/samples/Makefile.config#L263 > > i use -O3 flag  My biggest confusion is that why my result...

same question

same question

so am I

you can add `fd = fd.reshape(1,-1)` before ` pred = clf.predict(fd)` which is the line 69 of test-classifier.py https://github.com/yjl9122/object-detector-master/blob/5baa2d715b7c7a69a33328ef01f67d0af3c0b682/object-detector/test-classifier.py#L69