Algorithm Selection API usage example based off sampleMNIST in TensorRT

Table Of Contents

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

Description

This sample, sampleAlgorithmSelector, shows an example of how to use the algorithm selection API based on sampleMNIST. sampleMNIST documentation

This sample demonstrates the usage of IAlgorithmSelector to deterministically build TRT engines. It also shows the usage of IAlgorithmSelector::selectAlgorithms to define heuristics for selection of algorithms.

How does this sample work?

This sample uses a Caffe model that was trained on the MNIST dataset.

Specifically, this sample performs the following steps:

• Performs the basic setup and initialization of TensorRT using the Caffe parser
• Imports a trained Caffe model using Caffe parser
• Preprocesses the input and stores the result in a managed buffer
• Sets up three instances of algorithm selector
• Builds three engines using the algorithm selectors
• Serializes and deserializes the engines
• Uses the engines to perform inference on an input image

To verify whether the engine is operating correctly, this sample picks a 28x28 image of a digit at random and runs inference on it using the engine it created. The output of the network is a probability distribution on the digit, showing which digit is likely to be that in the image.

Setup the algorithm selectors

1. AlgorithmCacheWriter - Uses IAlgorithmSelector::reportAlgorithms to write TensorRT's default algorithm choices to a file "AlgorithmChoices.txt".
2. AlgorithmCacheReader - Uses IAlgorithmSelector::selectAlgorithms to replicate algorithm choices from the file "AlgorithmChoices.txt" and verifies the choices using IAlgorithmSelector::reportAlgorithms.
3. MinimumWorkspaceAlgorithmSelector - Uses IAlgorithmSelector::selectAlgorithms to select algorithms with minimum workspace requirements.

Running the sample

1. Compile this sample by running make in the <TensorRT root directory>/samples/sampleAlgorithmSelector directory. The binary named sample_algorithm_selector will be created in the <TensorRT root directory>/bin directory. ``` cd <TensorRT root directory>/samples/sampleAlgorithmSelector make `` Where<TensorRT root directory>` is where you installed TensorRT.

2. Run the sample to perform inference on the digit: ``` ./sample_algorithm_selector [-h] [–datadir=/path/to/data/dir/] [–useDLA=N] [–fp16 or –int8] ``` This sample reads three Caffe files to build the network:

   • mnist.prototxt The prototxt file that contains the network design.
   • mnist.caffemodel The model file which contains the trained weights for the network.
   • mnist_mean.binaryproto The binaryproto file which contains the means.

   This sample can be run in FP16 and INT8 modes as well.

   Note: By default, the sample expects these files to be in either the data/samples/mnist/ or data/mnist/ directories. The list of default directories can be changed by adding one or more paths with --datadir=/new/path/ as a command line argument.

3. Verify that the sample ran successfully. If the sample runs successfully you should see output similar to the following; ASCII rendering of the input image with digit 3: ``` &&&& RUNNING TensorRT.sample_algorithm_selector # ./sample_algorithm_selector [I] Building and running a GPU inference engine for MNIST [I] Input: @@@@@@@@@@@@@@ @@@@@@@@@@@@@@ @@@@@@@@@@@@@@ @@@@@@@@@@@@@@ @@@@#-:.-=@@@@@@@ @@%= . @@@@@@@ @@% .:+%%% *@@@@@@@ @@+=#@@# @@@@@@@ @@@@@% @@@@@@@ @@@@@@: *@@@@@@@ @@@@@- .@@@@@@@@ @@@@@: #@@@@@@@@ @@@@: +%#@@@@@@ @@@% :+*@@@@ @@@@#*+–.:: +@@@ @@@@@@@@#=:. +@@@ @@@@@@@@@@ .@@@ @@@@@@@@@@#. #@@ @@@@@@@@@@# @@@ @@@@%@@@@@- +@@@ @@@@#-@@@@*. =@@@ @@@@ .+%%%%+=. =@@@@ @@@@ =@@@@ @@@@*=: :–*@@@@@ @@@@@@@@@@@@@@ @@@@@@@@@@@@@@ @@@@@@@@@@@@@@ @@@@@@@@@@@@@@

   [I] Output: 0: 1: 2: 3: ********** 4: 5: 6: 7: 8: 9:

   &&&& PASSED TensorRT.sample_algorithm_selector # ./sample_algorithm_selector ```

   This output shows that the sample ran successfully; PASSED.

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: ./sample_algorithm_selector [-h or --help] [-d or --datadir=<path to data directory>] [--useDLACore=<int>]
--help Display help information
--datadir Specify path to a data directory, overriding the default. This option can be used multiple times to add multiple directories. If no data directories are given, the default is to use (data/samples/mnist/, data/mnist/)
--useDLACore=N Specify a DLA engine for layers that support DLA. Value can range from 0 to n-1, where n is the number of DLA engines on the platform.
--int8 Run in Int8 mode.
--fp16 Run in FP16 mode.

Additional resources

The following resources provide a deeper understanding about sampleAlgorithmSelector:

MNIST

• MNIST dataset

Documentation

• Introduction To NVIDIA’s TensorRT Samples
• Working With TensorRT Using The C++ API
• NVIDIA’s TensorRT Documentation Library

License

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

Changelog

November 2019 This README.md file was recreated, updated and reviewed.

Known issues

There are no known issues in this sample.