update REAME for more detailed instructions

README.md

@@ -2,6 +2,45 @@
 
 The aim of this module is to provide an export to [TensorRT SDK](https://developer.nvidia.com/tensorrt) via the Aidge framework.
 
+## Table of Contents
+
+- [Requirement](#Requirement)
+- [Install](#Install)
+- [Usage](#Usage)
+- [Known issue](#Known-issue)
+
+## Requirement
+
+In order to compile the export on your machine, please be sure to have one of these two conditions:
+- To have installed [Docker](https://docs.docker.com/get-docker/) (the export compilation chain is able to use docker)
+- To have installed the correct packages to support TensorRT 8.6
+  
+## Install
+
+To install `aidge_export_tensorrt` module you have to go in your `aidge/aidge/` directory, clone the module and then install it. 
+
+```
+git clone https://gitlab.eclipse.org/eclipse/aidge/aidge_export_tensorrt.git
+cd aidge_export_tensorrt/
+pip install .
+```
+
+## Usage
+
+To use `aidge_export_tensorrt` module, you have to import the module in python and call the export function. This function takes as argument the name of the export folder and the onnx file or the graphview of your model.
+
+```
+import aidge_export_tensorrt
+aidge_export_tensorrt.export("export_trt", "model.onnx")
+```
+
+The export povides a Makefile with several options to use the export on your machine. <br>
+You can generate a C++ export or a Python export.
+
+You also have the possibility to compile the export or/and the Python library by using Docker if your host machine doesn't have the correct packages. <br>
+In this tutorial, we generate the Python library of the export and use it a Python script.
+
+All of these options are resumed in the helper of the Makefile (run `make help` in the export folder for more details).
 
 ## Known issue