From NVIDIA tensorRT documentation I have completed the first 4 steps for zip file for windows.But Now I can't really understand the 5th and 6th step specially where I have to 3 things to get it work for "tensorFlow". I can't understand how to execute this line
python3 -m pip install <installpath>\graphsurgeon\graphsurgeon-0.4.5-py2.py3-none-any.whl
Here is the link: https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html#installing-zip
P.S:I am very new to this world of machine learning and TensorFlow.
You need to open a terminal with a python environment.
Press Ctrl+r and type cmd
+Enter to open a terminal. You can check if you have the correct Python version by running python --version
.
More information about package installing can be found here: https://packaging.python.org/tutorials/installing-packages/#requirements-for-installing-packages
For install command execution, replace <installpath>
by the location, where you installed TensorRT, e.g., if you installed it in C:\Program Files\TensorRT
use:
python3 -m pip install "C:\Program Files"\TensorRT\graphsurgeon\graphsurgeon-0.4.5-py2.py3-none-any.whl
This is described in 2) from your link:
Choose where you want to install TensorRT. The zip file will install everything into a subdirectory called TensorRT-7.x.x.x. This new subdirectory will be referred to as
<installpath>
in the steps below.