apollo-model-centerpoint
apollo-model-centerpoint copied to clipboard
Great work and thanks for sharing! I have run the infer.py successfully, but the output is plain text, is there a out-of-the-box visualization tool that I can show the pointcloud...
你好,请问下有没有centerpoint int8部署在c++ tensorrt上的耗时对比指标?想看下对比与fp16,int8能减少多少耗时,同时下降多少精度。谢谢
C++部署问题
**环境:** - GCC==gcc (Ubuntu 8.4.0-3ubuntu2) 8.4.0 - Cmake==cmake version 3.27.7 - Ubuntu 20.04 - CUDA 11.7 - cuDNN==8.9 - Paddle Inferece==2.5.2 from https://www.paddlepaddle.org.cn/inference/v2.5/guides/install/download_lib.html GPU 是 MKL 8.2 CUDA11.7/cuDNN8.4/TensorRT8.4 [paddle_inference.tgz](https://paddle-inference-lib.bj.bcebos.com/2.5.2/cxx_c/Linux/GPU/x86-64_gcc8.2_avx_mkl_cuda11.7_cudnn8.4.1-trt8.4.2.4/paddle_inference.tgz) **compile.sh:**...
 