Tensorrt with dynamic input

fengweizhong · June 8, 2020, 9:57am

Tensorrt7 support dynamic input.
I am confused with how to to use this feature.

NVIDIA/TensorRT/blob/f5e8b8c55060447c4d3a45e7379bc25374edc93f/samples/opensource/sampleDynamicReshape/sampleDynamicReshape.cpp#L129


//!
//! \brief Builds an engine for preprocessing (mPreprocessorEngine).
//!
void SampleDynamicReshape::buildPreprocessorEngine(const SampleUniquePtr<nvinfer1::IBuilder>& builder)
{
    // Create the preprocessor engine using a network that supports full dimensions (createNetworkV2).
    auto preprocessorNetwork = makeUnique(
        builder->createNetworkV2(1U << static_cast<uint32_t>(NetworkDefinitionCreationFlag::kEXPLICIT_BATCH)));

    // Reshape a dynamically shaped input to the size expected by the model, (1, 1, 28, 28).
    auto input = preprocessorNetwork->addInput("input", nvinfer1::DataType::kFLOAT, Dims4{1, 1, -1, -1});
    auto resizeLayer = preprocessorNetwork->addResize(*input);
    resizeLayer->setOutputDimensions(mPredictionInputDims);
    preprocessorNetwork->markOutput(*resizeLayer->getOutput(0));

    // Finally, configure and build the preprocessor engine.
    auto preprocessorConfig = makeUnique(builder->createBuilderConfig());

    // Create an optimization profile so that we can specify a range of input dimensions.
    auto profile = builder->createOptimizationProfile();

In this sample, if I addInput with some dimensions with -1, createNetworkV2 with kEXPLICIT_BATCH is required？And create an optimization profile is required？