simple_progress_monitor

Introduction To IProgressMonitor Callbacks Using Python

Table Of Contents

• Description
• How does this sample work?
  • simple_progress_monitor
• Prerequisites
• Running the sample
  • Sample --help options
• Additional resources
• License
• Changelog
• Known issues

Description

This sample, simple_progress_reporter, is a Python sample which uses TensorRT and its included ONNX parser, to perform inference with ResNet-50 models saved in ONNX format. It displays animated progress bars while TensorRT builds the engine.

How does this sample work?

simple_progress_monitor

This sample demonstrates how to build an engine from an ONNX model file using the open-source ONNX parser and then run inference. The ONNX parser can be used with any framework that supports the ONNX format (typically .onnx files). An IProgressMonitor object receives updates on the progress of the build, and displays them as ASCII progress bars on stdout.

Prerequisites

1. Install the dependencies for Python.

pip3 install -r requirements.txt

Running the sample

1. Run the sample from a terminal to create a TensorRT inference engine and run inference: python3 simple_progress_monitor.py

   Note: If the TensorRT sample data is not installed in the default location, for example /usr/src/tensorrt/data/, the data directory must be specified. For example: python3 simple_progress_monitor.py -d /path/to/my/data/

   Note: Do not redirect the output of this script to a file or pipe.

2. Verify that the sample ran successfully. If the sample runs successfully you should see output similar to the following: Correctly recognized data/samples/resnet50/reflex_camera.jpeg as reflex camera

Sample --help options

To see the full list of available options and their descriptions, use the -h or --help command line option. For example:

usage: simple_progress_monitor.py [-h] [-d DATADIR]

Runs a ResNet50 network with a TensorRT inference engine. Displays intermediate build progress.

optional arguments:
 -h, --help            show this help message and exit
 -d DATADIR, --datadir DATADIR
                       Location of the TensorRT sample data directory.
                       (default: /usr/src/tensorrt/data)

Additional resources

The following resources provide a deeper understanding about importing a model into TensorRT using Python:

ResNet-50

• Deep Residual Learning for Image Recognition

Parsers

• ONNX Parser

Documentation

• Introduction To NVIDIA’s TensorRT Samples
• Working With TensorRT Using The Python API
• Importing A Model Using A Parser In Python
• NVIDIA’s TensorRT Documentation Library

Terminal Escape Sequences

• Linux: XTerm Control Sequences
• Windows: Console Virtual Terminal Sequences

License

For terms and conditions for use, reproduction, and distribution, see the TensorRT Software License Agreement documentation.

Changelog

August 2023 Removed support for Python versions < 3.8.

June 2023 This README.md file was created and reviewed.

Known issues

There are no known issues in this sample