Tensorrt環境搭建
環境安裝
python 3.6
TensorRT 7.0.0.1
https://developer.nvidia.com/nvidia-tensorrt-7x-download
cd /path/to/TensorRT7.0.0.1
pip install tensorrt-7.0.0.11-cp36-none-linux_x86_64.whl
pytorch 1.6
根據機器需求,下載匹配的pytorch
cudnn 7.6
https://developer.nvidia.com/rdp/cudnn-archive
下載後,將其解壓,放置cuda安裝的位置即可
cuda 10.2
https://developer.nvidia.com/cuda-toolkit-archive
wget http://developer.download.nvidia.com/compute/cuda/10.2/Prod/local_installers/cuda_10.2.89_440.33.01_linux.run
sudo sh cuda_10.2.89_440.33.01_linux.run
編輯~/.bashrc
export PATH=$PATH:/usr/local/cuda-10.2/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda-10.2.0/lib64
cuda安裝注意事項 一定不要安裝默認的驅動,而且options裏面也不需要編譯opengl的庫
nvidia驅動安裝
搜索適合的驅動,然後下載
https://www.nvidia.cn/Download/index.aspx?lang=cn
pycuda
pip install pycuda -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
options
pycharm
https://www.jetbrains.com/pycharm/download/#section=linux
opencv
pip install opencv-python==3.4.2.17 -i http://mrrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
nvidia-docker安裝
https://www.jianshu.com/p/ef8b0e6c6f5c
trubble-shooting
- src/cpp/cuda.hpp:14:18: fatal error: cuda.h: No such file or directory
可能是沒有安裝cuda或者是安裝cuda後include沒有加入PATH - pycharm服務器運行沒有圖形界面,加入-X
ssh -X [email protected]
- pip install老是安裝到其他路徑了,可以指定安裝的位置
sudo ~/anaconda3/bin/python setup.py install
4.查看顯卡使用情況
watch nvidia-smi
其他
CUDA GPU算力對照表:
https://developer.nvidia.com/cuda-gpus#collapseOne
Tensorrt C++源碼庫地址
https://github.com/NVIDIA/TensorRT
sudo cmake .. -DTRT_LIB_DIR=$TRT_RELEASE/lib -DTRT_BIN_DIR=`pwd`/out -DCMAKE_CUDA_COMPILER:PATH=/usr/local/cuda/bin/nvcc