chore: import upstream snapshot with attribution

samples/sampleOnnxMNIST/CMakeLists.txt

@@ -0,0 +1,25 @@
+#
+# SPDX-FileCopyrightText: Copyright (c) 1993-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+add_executable(sample_onnx_mnist sampleOnnxMNIST.cpp)
+target_link_libraries(sample_onnx_mnist PRIVATE trt_samples_common TRT_SAMPLES::tensorrt)
+add_dependencies(tensorrt_samples sample_onnx_mnist)
+
+installLibraries(
+    TARGETS sample_onnx_mnist
+    OPTIONAL
+    COMPONENT internal
+)

samples/sampleOnnxMNIST/README.md

@@ -0,0 +1,207 @@
+# “Hello World” For TensorRT From ONNX
+
+
+**Table Of Contents**
+- [Description](#description)
+- [How does this sample work?](#how-does-this-sample-work)
+	* [Converting the ONNX model to a TensorRT network](#converting-the-onnx-model-to-a-tensorrt-network)
+	* [Building the engine](#building-the-engine)
+	* [Running inference](#running-inference)
+	* [TensorRT API layers and ops](#tensorrt-api-layers-and-ops)
+- [Running the sample](#running-the-sample)
+	* [Sample `--help` options](#sample-help-options)
+- [Additional resources](#additional-resources)
+- [License](#license)
+- [Changelog](#changelog)
+- [Known issues](#known-issues)
+
+## Description
+
+This sample, sampleOnnxMNIST, converts a model trained on the MNIST dataset in Open Neural Network Exchange (ONNX) format to a TensorRT network and runs inference on the network.
+
+ONNX is a standard for representing deep learning models that enables models to be transferred between frameworks.
+
+## How does this sample work?
+
+This sample creates and runs the TensorRT engine from an ONNX model of the MNIST network. It demonstrates how TensorRT can consume an ONNX model as input to create a network.
+
+Specifically, this sample:
+- [Converts the ONNX model to a TensorRT network](#converting-the-onnx-model-to-a-tensorrt-network)
+- [Builds an engine](#building-an-engine)
+- [Runs inference using the generated TensorRT network](#running-inference)
+
+### Converting the ONNX model to a TensorRT network
+
+The model file can be converted to a TensorRT network using the ONNX parser. The parser can be initialized with the
+network definition that the parser will write to and the logger object.
+
+`auto parser = nvonnxparser::createParser(*network, sample::gLogger.getTRTLogger());`
+
+The ONNX model file is then passed onto the parser along with the logging level
+
+```
+if (!parser->parseFromFile(model_file, static_cast<int>(sample::gLogger.getReportableSeverity())))
+{
+	  string msg("failed to parse onnx file");
+	  sample::gLogger->log(nvinfer1::ILogger::Severity::kERROR, msg.c_str());
+	  exit(EXIT_FAILURE);
+}
+```
+
+After the TensorRT network is constructed by parsing the model, the TensorRT engine can be built to run inference.
+
+### Building the engine
+
+To build the engine, create the builder and pass a logger created for TensorRT which is used for reporting errors, warnings and informational messages in the network:
+`IBuilder* builder = createInferBuilder(sample::gLogger);`
+
+To build the engine from the generated TensorRT network, issue the following call:
+`std::unique_ptr<nvinfer1::IHostMemory> plan{builder->buildSerializedNetwork(*network, *config)};`
+
+After you build the engine, verify that the engine is running properly by confirming the output is what you expected. The output format of this sample should be the same as the output of sampleMNIST.
+
+### Running inference
+
+To run inference using the created engine, see [Performing Inference In C++](https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#perform_inference_c).
+
+**Note:** It’s important to preprocess the data and convert it to the format accepted by the network. In this example, the sample input is in PGM (portable graymap) format. The model expects an input of image `1x28x28` scaled to between `[0,1]`.
+
+### TensorRT API layers and ops
+
+In this sample, the following layers are used. For more information about these layers, see the [TensorRT Developer Guide: Layers](https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#layers) documentation.
+
+[Activation layer](https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#activation-layer)
+The Activation layer implements element-wise activation functions. Specifically, this sample uses the Activation layer with the type `kRELU`.
+
+[Convolution layer](https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#convolution-layer)
+The Convolution layer computes a 2D (channel, height, and width) convolution, with or without bias.
+
+[MatrixMultiplyLayer](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#matrixmultiply-layer)
+The MatrixMultiply layer implements a matrix multiplication operation.
+(The [FullyConnected layer](https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#fullyconnected-layer) is deprecated since 8.4.
+The bias of a FullyConnected layer can be added with an
+[ElementwiseLayer](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#elementwise-layer) of `SUM` operation.)
+
+[Pooling layer](https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#pooling-layer)
+The Pooling layer implements pooling within a channel. Supported pooling types are `maximum`, `average` and `maximum-average blend`.
+
+[Scale layer](https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#scale-layer)
+The Scale layer implements a per-tensor, per-channel, or per-element affine transformation and/or exponentiation by constant values.
+
+[Shuffle layer](https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#shuffle-layer)
+The Shuffle layer implements a reshape and transpose operator for tensors.
+
+## Prerequisites
+1. Preparing sample data
+
+See [Preparing sample data](../README.md#preparing-sample-data) in the main samples README.
+
+## Running the sample
+
+1. Compile the sample by following build instructions in [TensorRT README](https://github.com/NVIDIA/TensorRT/).
+
+2.  Run the sample to build and run the MNIST engine from the ONNX model.
+	```
+	./sample_onnx_mnist [-h or --help] [-d or --datadir=<path to data directory>] [--useDLACore=<int>]
+	```
+
+3.  Verify that the sample ran successfully. If the sample runs successfully you should see output similar to the following:
+	```
+	&&&& RUNNING TensorRT.sample_onnx_mnist # ./sample_onnx_mnist
+	----------------------------------------------------------------
+	Input filename: ../../../../../../data/samples/mnist/mnist.onnx
+	ONNX IR version: 0.0.3
+	Opset version: 1
+	Producer name: CNTK
+	Producer version: 2.4
+	Domain:
+	Model version: 1
+	Doc string:
+	----------------------------------------------------------------
+	[I] Input:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@@@@@@@@@@@*.  .*@@@@@@@@@@@
+	@@@@@@@@@@*.     +@@@@@@@@@@
+	@@@@@@@@@@. :#+   %@@@@@@@@@
+	@@@@@@@@@@.:@@@+  +@@@@@@@@@
+	@@@@@@@@@@.:@@@@:  +@@@@@@@@
+	@@@@@@@@@@=%@@@@:  +@@@@@@@@
+	@@@@@@@@@@@@@@@@#  +@@@@@@@@
+	@@@@@@@@@@@@@@@@*  +@@@@@@@@
+	@@@@@@@@@@@@@@@@:  +@@@@@@@@
+	@@@@@@@@@@@@@@@@:  +@@@@@@@@
+	@@@@@@@@@@@@@@@*  .@@@@@@@@@
+	@@@@@@@@@@%**%@.  *@@@@@@@@@
+	@@@@@@@@%+.  .:  .@@@@@@@@@@
+	@@@@@@@@=  ..    :@@@@@@@@@@
+	@@@@@@@@:  *@@:  :@@@@@@@@@@
+	@@@@@@@%   %@*    *@@@@@@@@@
+	@@@@@@@%   ++ ++  .%@@@@@@@@
+	@@@@@@@@-    +@@-  +@@@@@@@@
+	@@@@@@@@=  :*@@@#  .%@@@@@@@
+	@@@@@@@@@+*@@@@@%.   %@@@@@@
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+
+	[I] Output:
+	Prob 0 0.0000 Class 0:
+	Prob 1 0.0000 Class 1:
+	Prob 2 1.0000 Class 2: **********
+	Prob 3 0.0000 Class 3:
+	Prob 4 0.0000 Class 4:
+	Prob 5 0.0000 Class 5:
+	Prob 6 0.0000 Class 6:
+	Prob 7 0.0000 Class 7:
+	Prob 8 0.0000 Class 8:
+	Prob 9 0.0000 Class 9:
+
+	&&&& PASSED TensorRT.sample_onnx_mnist # ./sample_onnx_mnist
+	```
+
+	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.
+
+
+# Additional resources
+
+The following resources provide a deeper understanding about the ONNX project and MNIST model:
+
+**ONNX**
+- [GitHub: ONNX](https://github.com/onnx/onnx)
+- [Github: ONNX-TensorRT Open source parser](https://github.com/onnx/onnx-tensorrt)
+
+**Models**
+- [MNIST - Handwritten Digit Recognition](https://github.com/onnx/models/tree/main/validated/vision/classification/mnist)
+- [GitHub: ONNX Models](https://github.com/onnx/models)
+
+**Documentation**
+- [Introduction To NVIDIA’s TensorRT Samples](https://docs.nvidia.com/deeplearning/sdk/tensorrt-sample-support-guide/index.html#samples)
+- [Working With TensorRT Using The C++ API](https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#c_topics)
+- [NVIDIA’s TensorRT Documentation Library](https://docs.nvidia.com/deeplearning/sdk/tensorrt-archived/index.html)
+
+# License
+
+For terms and conditions for use, reproduction, and distribution, see the [TensorRT Software License Agreement](https://docs.nvidia.com/deeplearning/sdk/tensorrt-sla/index.html) documentation.
+
+
+# Changelog
+
+October 2025
+Migrate to strongly typed APIs.
+
+March 2019
+This `README.md` file was recreated, updated and reviewed.
+
+
+# Known issues
+
+There are no known issues in this sample.

samples/sampleOnnxMNIST/sampleOnnxMNIST.cpp

@@ -0,0 +1,419 @@
+/*
+ * SPDX-FileCopyrightText: Copyright (c) 1993-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ * SPDX-License-Identifier: Apache-2.0
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+//!
+//! sampleOnnxMNIST.cpp
+//! This file contains the implementation of the ONNX MNIST sample. It creates the network using
+//! the MNIST onnx model.
+//! It can be run with the following command line:
+//! Command: ./sample_onnx_mnist [-h or --help] [-d=/path/to/data/dir or --datadir=/path/to/data/dir]
+//! [--useDLACore=<int>]
+//!
+
+// Define TRT entrypoints used in common code
+#define DEFINE_TRT_ENTRYPOINTS 1
+
+#include "argsParser.h"
+#include "buffers.h"
+#include "common.h"
+#include "logger.h"
+#include "parserOnnxConfig.h"
+
+#include "NvInfer.h"
+#include <cuda_runtime_api.h>
+
+#include <cstdlib>
+#include <iostream>
+#include <random>
+using namespace nvinfer1;
+
+const std::string gSampleName = "TensorRT.sample_onnx_mnist";
+
+//! \brief  The SampleOnnxMNIST class implements the ONNX MNIST sample
+//!
+//! \details It creates the network using an ONNX model
+//!
+class SampleOnnxMNIST
+{
+public:
+    SampleOnnxMNIST(const samplesCommon::OnnxSampleParams& params)
+        : mParams(params)
+        , mRuntime(nullptr)
+        , mEngine(nullptr)
+    {
+    }
+
+    //!
+    //! \brief Function builds the network engine
+    //!
+    bool build();
+
+    //!
+    //! \brief Runs the TensorRT inference engine for this sample
+    //!
+    bool infer();
+
+private:
+    samplesCommon::OnnxSampleParams mParams; //!< The parameters for the sample.
+
+    nvinfer1::Dims mInputDims;  //!< The dimensions of the input to the network.
+    nvinfer1::Dims mOutputDims; //!< The dimensions of the output to the network.
+    int mNumber{0};             //!< The number to classify
+
+    std::shared_ptr<nvinfer1::IRuntime> mRuntime;   //!< The TensorRT runtime used to deserialize the engine
+    std::shared_ptr<nvinfer1::ICudaEngine> mEngine; //!< The TensorRT engine used to run the network
+
+    //!
+    //! \brief Parses an ONNX model for MNIST and creates a TensorRT network
+    //!
+    bool constructNetwork(std::unique_ptr<nvinfer1::IBuilder>& builder,
+        std::unique_ptr<nvinfer1::INetworkDefinition>& network, std::unique_ptr<nvinfer1::IBuilderConfig>& config,
+        std::unique_ptr<nvonnxparser::IParser>& parser, std::unique_ptr<nvinfer1::ITimingCache>& timingCache);
+
+    //!
+    //! \brief Reads the input  and stores the result in a managed buffer
+    //!
+    bool processInput(const samplesCommon::BufferManager& buffers);
+
+    //!
+    //! \brief Classifies digits and verify result
+    //!
+    bool verifyOutput(const samplesCommon::BufferManager& buffers);
+};
+
+//!
+//! \brief Creates the network, configures the builder and creates the network engine
+//!
+//! \details This function creates the Onnx MNIST network by parsing the Onnx model and builds
+//!          the engine that will be used to run MNIST (mEngine)
+//!
+//! \return true if the engine was created successfully and false otherwise
+//!
+bool SampleOnnxMNIST::build()
+{
+    auto builder = std::unique_ptr<nvinfer1::IBuilder>(nvinfer1::createInferBuilder(sample::gLogger.getTRTLogger()));
+    if (!builder)
+    {
+        return false;
+    }
+
+    auto network = std::unique_ptr<nvinfer1::INetworkDefinition>(
+        builder->createNetworkV2(1U << static_cast<uint32_t>(NetworkDefinitionCreationFlag::kSTRONGLY_TYPED)));
+    if (!network)
+    {
+        return false;
+    }
+
+    auto config = std::unique_ptr<nvinfer1::IBuilderConfig>(builder->createBuilderConfig());
+    if (!config)
+    {
+        return false;
+    }
+
+    auto parser
+        = std::unique_ptr<nvonnxparser::IParser>(nvonnxparser::createParser(*network, sample::gLogger.getTRTLogger()));
+    if (!parser)
+    {
+        return false;
+    }
+
+    auto timingCache = std::unique_ptr<nvinfer1::ITimingCache>();
+
+    auto constructed = constructNetwork(builder, network, config, parser, timingCache);
+    if (!constructed)
+    {
+        return false;
+    }
+
+    // CUDA stream used for profiling by the builder.
+    auto profileStream = samplesCommon::makeCudaStream();
+    if (!profileStream)
+    {
+        return false;
+    }
+    config->setProfileStream(*profileStream);
+
+    std::unique_ptr<IHostMemory> plan{builder->buildSerializedNetwork(*network, *config)};
+    if (!plan)
+    {
+        return false;
+    }
+
+    if (timingCache != nullptr && !mParams.timingCacheFile.empty())
+    {
+        samplesCommon::updateTimingCacheFile(
+            sample::gLogger.getTRTLogger(), mParams.timingCacheFile, timingCache.get(), *builder);
+    }
+
+    mRuntime = std::shared_ptr<nvinfer1::IRuntime>(createInferRuntime(sample::gLogger.getTRTLogger()));
+    if (!mRuntime)
+    {
+        return false;
+    }
+
+    mEngine = std::shared_ptr<nvinfer1::ICudaEngine>(mRuntime->deserializeCudaEngine(plan->data(), plan->size()));
+    if (!mEngine)
+    {
+        return false;
+    }
+
+    ASSERT(network->getNbInputs() == 1);
+    mInputDims = network->getInput(0)->getDimensions();
+    ASSERT(mInputDims.nbDims == 4);
+
+    ASSERT(network->getNbOutputs() == 1);
+    mOutputDims = network->getOutput(0)->getDimensions();
+    ASSERT(mOutputDims.nbDims == 2);
+
+    return true;
+}
+
+//!
+//! \brief Uses a ONNX parser to create the Onnx MNIST Network and marks the
+//!        output layers
+//!
+//! \param network Pointer to the network that will be populated with the Onnx MNIST network
+//!
+//! \param builder Pointer to the engine builder
+//!
+bool SampleOnnxMNIST::constructNetwork(std::unique_ptr<nvinfer1::IBuilder>& builder,
+    std::unique_ptr<nvinfer1::INetworkDefinition>& network, std::unique_ptr<nvinfer1::IBuilderConfig>& config,
+    std::unique_ptr<nvonnxparser::IParser>& parser, std::unique_ptr<nvinfer1::ITimingCache>& timingCache)
+{
+    auto parsed = parser->parseFromFile(samplesCommon::locateFile(mParams.onnxFileName, mParams.dataDirs).c_str(),
+        static_cast<int>(sample::gLogger.getReportableSeverity()));
+    if (!parsed)
+    {
+        return false;
+    }
+
+    if (mParams.timingCacheFile.size())
+    {
+        timingCache
+            = samplesCommon::buildTimingCacheFromFile(sample::gLogger.getTRTLogger(), *config, mParams.timingCacheFile);
+    }
+
+    samplesCommon::enableDLA(builder.get(), config.get(), mParams.dlaCore);
+
+    return true;
+}
+
+//!
+//! \brief Runs the TensorRT inference engine for this sample
+//!
+//! \details This function is the main execution function of the sample. It allocates the buffer,
+//!          sets inputs and executes the engine.
+//!
+bool SampleOnnxMNIST::infer()
+{
+    // Create RAII buffer manager object
+    samplesCommon::BufferManager buffers(mEngine);
+
+    auto context = std::unique_ptr<nvinfer1::IExecutionContext>(mEngine->createExecutionContext());
+    if (!context)
+    {
+        return false;
+    }
+
+    for (int32_t i = 0, e = mEngine->getNbIOTensors(); i < e; i++)
+    {
+        auto const name = mEngine->getIOTensorName(i);
+        context->setTensorAddress(name, buffers.getDeviceBuffer(name));
+    }
+
+    // Read the input data into the managed buffers
+    ASSERT(mParams.inputTensorNames.size() == 1);
+    if (!processInput(buffers))
+    {
+        return false;
+    }
+
+    // Memcpy from host input buffers to device input buffers
+    buffers.copyInputToDevice();
+
+    bool status = context->executeV2(buffers.getDeviceBindings().data());
+    if (!status)
+    {
+        return false;
+    }
+
+    // Memcpy from device output buffers to host output buffers
+    buffers.copyOutputToHost();
+
+    // Verify results
+    if (!verifyOutput(buffers))
+    {
+        return false;
+    }
+
+    return true;
+}
+
+//!
+//! \brief Reads the input and stores the result in a managed buffer
+//!
+bool SampleOnnxMNIST::processInput(const samplesCommon::BufferManager& buffers)
+{
+    const int inputH = mInputDims.d[2];
+    const int inputW = mInputDims.d[3];
+
+    // Read a random digit file
+    std::vector<uint8_t> fileData(inputH * inputW);
+    mNumber = std::invoke([] {
+        auto dist = std::uniform_int_distribution<int>{0, 9};
+        auto gen = std::mt19937{std::random_device{}()};
+        return dist(gen);
+    });
+    samplesCommon::readPGMFile(
+        samplesCommon::locateFile(std::to_string(mNumber) + ".pgm", mParams.dataDirs), fileData.data(), inputH, inputW);
+
+    // Print an ascii representation
+    sample::gLogInfo << "Input:" << std::endl;
+    for (int i = 0; i < inputH * inputW; i++)
+    {
+        sample::gLogInfo << (" .:-=+*#%@"[fileData[i] / 26]) << (((i + 1) % inputW) ? "" : "\n");
+    }
+    sample::gLogInfo << std::endl;
+
+    float* hostDataBuffer = static_cast<float*>(buffers.getHostBuffer(mParams.inputTensorNames[0]));
+    for (int i = 0; i < inputH * inputW; i++)
+    {
+        hostDataBuffer[i] = 1.0 - float(fileData[i] / 255.0);
+    }
+
+    return true;
+}
+
+//!
+//! \brief Classifies digits and verify result
+//!
+//! \return whether the classification output matches expectations
+//!
+bool SampleOnnxMNIST::verifyOutput(const samplesCommon::BufferManager& buffers)
+{
+    const int outputSize = mOutputDims.d[1];
+    float* output = static_cast<float*>(buffers.getHostBuffer(mParams.outputTensorNames[0]));
+    float val{0.0F};
+    int idx{0};
+
+    // Calculate Softmax
+    float sum{0.0F};
+    for (int i = 0; i < outputSize; i++)
+    {
+        output[i] = exp(output[i]);
+        sum += output[i];
+    }
+
+    sample::gLogInfo << "Output:" << std::endl;
+    for (int i = 0; i < outputSize; i++)
+    {
+        output[i] /= sum;
+        val = std::max(val, output[i]);
+        if (val == output[i])
+        {
+            idx = i;
+        }
+
+        sample::gLogInfo << " Prob " << i << "  " << std::fixed << std::setw(5) << std::setprecision(4) << output[i]
+                         << " "
+                         << "Class " << i << ": " << std::string(int(std::floor(output[i] * 10 + 0.5F)), '*')
+                         << std::endl;
+    }
+    sample::gLogInfo << std::endl;
+
+    return idx == mNumber && val > 0.9F;
+}
+
+//!
+//! \brief Initializes members of the params struct using the command line args
+//!
+samplesCommon::OnnxSampleParams initializeSampleParams(const samplesCommon::Args& args)
+{
+    samplesCommon::OnnxSampleParams params;
+    if (args.dataDirs.empty()) // Use default directories if user hasn't provided directory paths
+    {
+        params.dataDirs.push_back("data/mnist/");
+        params.dataDirs.push_back("data/samples/mnist/");
+    }
+    else // Use the data directory provided by the user
+    {
+        params.dataDirs = args.dataDirs;
+    }
+    params.onnxFileName = "mnist.onnx";
+    params.inputTensorNames.push_back("Input3");
+    params.outputTensorNames.push_back("Plus214_Output_0");
+    params.dlaCore = args.useDLACore;
+    params.timingCacheFile = args.timingCacheFile;
+
+    return params;
+}
+
+//!
+//! \brief Prints the help information for running this sample
+//!
+void printHelpInfo()
+{
+    std::cout
+        << "Usage: ./sample_onnx_mnist [-h or --help] [-d or --datadir=<path to data directory>] [--useDLACore=<int>]"
+        << "[-t or --timingCacheFile=<path to timing cache file]" << std::endl;
+    std::cout << "--help             Display help information" << std::endl;
+    std::cout << "--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/)"
+              << std::endl;
+    std::cout << "--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."
+              << std::endl;
+    std::cout << "--timingCacheFile  Specify path to a timing cache file. If it does not already exist, it will be "
+              << "created." << std::endl;
+}
+
+int main(int argc, char** argv)
+{
+    samplesCommon::Args args;
+    bool argsOK = samplesCommon::parseArgs(args, argc, argv);
+    if (!argsOK)
+    {
+        sample::gLogError << "Invalid arguments" << std::endl;
+        printHelpInfo();
+        return EXIT_FAILURE;
+    }
+    if (args.help)
+    {
+        printHelpInfo();
+        return EXIT_SUCCESS;
+    }
+
+    auto sampleTest = sample::gLogger.defineTest(gSampleName, argc, argv);
+
+    sample::gLogger.reportTestStart(sampleTest);
+
+    SampleOnnxMNIST sample(initializeSampleParams(args));
+
+    sample::gLogInfo << "Building and running a GPU inference engine for Onnx MNIST" << std::endl;
+
+    if (!sample.build())
+    {
+        return sample::gLogger.reportFail(sampleTest);
+    }
+    if (!sample.infer())
+    {
+        return sample::gLogger.reportFail(sampleTest);
+    }
+
+    return sample::gLogger.reportPass(sampleTest);
+}