Installation instructions:


This document captures simple instructions to run the TLT converter for the Jetson platform. 


1. Copy the executable to the target device 
2. Install openssl library using the following command.
   1. $ sudo apt-get install libssl-dev
3. Export the following environment variables
   1. $ export TRT_LIB_PATH=”/usr/lib/aarch64-linux-gnu”
   2. $ export TRT_INC_PATH=”/usr/include/aarch64-linux-gnu”
4. Run the converter


Note: 

In Int8 mode, when using calibration table generated from the TLT v1.0 GA docker, if the version of the tensorrt on the deployment device is 5.x/6.x, please make sure to update the version number in the TensorRT calibration table file. Inorder to do so, 
1. Open the `calibration.bin` or `calibration.txt` file as generated by `tlt-export` using a simple text editor
2. Update the first line in calibration file from `TRT-5105-EntropyCalibration2` or `TRT-6001-EntropyCalibration2` to `TRT-7000-EntropyCalibration2`.
3. Save the edited file with the new changes. 
4. Use this file with `tlt-converter` to generate the engine.

Sample usage:


        ./tlt-converter -h