################################################################################
# Copyright (c) 2018-2019, NVIDIA CORPORATION.  All rights reserved.
#
# NVIDIA Corporation and its licensors retain all intellectual property
# and proprietary rights in and to this software, related documentation
# and any modifications thereto.  Any use, reproduction, disclosure or
# distribution of this software and related documentation without an express
# license agreement from NVIDIA Corporation is strictly prohibited.
#
################################################################################

Refer to the DeepStream SDK documentation for a description of the library.

--------------------------------------------------------------------------------
Pre-requisites:
- TensorRT 5.0

--------------------------------------------------------------------------------
Compile the library using:
  make

--------------------------------------------------------------------------------
This source has been written to parse the output layers of the resnet10 detector
and the resnet18 vehicle type classifier model provided with the SDK. To use this
library for bounding box / classifier output parsing instead of the inbuilt
parsing function, modify the following parameters in [property] section of
primary/secondary vehicle type infer configuration file (config_infer_primary.txt/
config_infer_secondary_vehicletypes.txt) provided with the SDK:

# For resnet10 detector
parse-bbox-func-name=NvDsInferParseCustomResnet
custom-lib-path=/path/to/this/directory/libnvds_infercustomparser.so

# For resnet18 vehicle type classifier
parse-classifier-func-name=NvDsInferClassiferParseCustomSoftmax
custom-lib-path=/path/to/this/directory/libnvds_infercustomparser.so
