TensorRT  7.2.1.6
NVIDIA TensorRT
Looking for a C++ dev who knows TensorRT?
I'm looking for work. Hire me!
nvinfer1::IOptimizationProfile Class Referenceabstract

Optimization profile for dynamic input dimensions and shape tensors. More...

Public Member Functions

virtual bool setDimensions (const char *inputName, OptProfileSelector select, Dims dims) noexcept=0
 Set the minimum / optimum / maximum dimensions for a dynamic input tensor. More...
 
virtual Dims getDimensions (const char *inputName, OptProfileSelector select) const noexcept=0
 Get the minimum / optimum / maximum dimensions for a dynamic input tensor. More...
 
virtual bool setShapeValues (const char *inputName, OptProfileSelector select, const int32_t *values, int32_t nbValues) noexcept=0
 Set the minimum / optimum / maximum values for an input shape tensor. More...
 
virtual int32_t getNbShapeValues (const char *inputName) const noexcept=0
 Get the number of values for an input shape tensor. More...
 
virtual const int32_t * getShapeValues (const char *inputName, OptProfileSelector select) const noexcept=0
 Get the minimum / optimum / maximum values for an input shape tensor. More...
 
virtual bool setExtraMemoryTarget (float target) noexcept=0
 Set a target for extra GPU memory that may be used by this profile. More...
 
virtual float getExtraMemoryTarget () const noexcept=0
 Get the extra memory target that has been defined for this profile. More...
 
virtual bool isValid () const noexcept=0
 Check whether the optimization profile can be passed to an IBuilderConfig object. More...
 

Protected Member Functions

 ~IOptimizationProfile () noexcept=default
 

Detailed Description

Optimization profile for dynamic input dimensions and shape tensors.

When building an ICudaEngine from an INetworkDefinition that has dynamically resizable inputs (at least one input tensor has one or more of its dimensions specified as -1) or shape input tensors, users need to specify at least one optimization profile. Optimization profiles are numbered 0, 1, ... The first optimization profile that has been defined (with index 0) will be used by the ICudaEngine whenever no optimization profile has been selected explicitly. If none of the inputs are dynamic, the default optimization profile will be generated automatically unless it is explicitly provided by the user (this is possible but not required in this case). If more than a single optimization profile is defined, users may set a target how much additional weight space should be maximally allocated to each additional profile (as a fraction of the maximum, unconstrained memory).

Users set optimum input tensor dimensions, as well as minimum and maximum input tensor dimensions. The builder selects the kernels that result in the lowest runtime for the optimum input tensor dimensions, and are valid for all input tensor sizes in the valid range between minimum and maximum dimensions. A runtime error will be raised if the input tensor dimensions fall outside the valid range for this profile. Likewise, users provide minimum, optimum, and maximum values for all shape tensor input values.

See also
IBuilderConfig::addOptimizationProfile()

Constructor & Destructor Documentation

◆ ~IOptimizationProfile()

nvinfer1::IOptimizationProfile::~IOptimizationProfile ( )
protecteddefaultnoexcept

Member Function Documentation

◆ setDimensions()

virtual bool nvinfer1::IOptimizationProfile::setDimensions ( const char *  inputName,
OptProfileSelector  select,
Dims  dims 
)
pure virtualnoexcept

Set the minimum / optimum / maximum dimensions for a dynamic input tensor.

This function must be called three times (for the minimum, optimum, and maximum) for any network input tensor that has dynamic dimensions. If minDims, optDims, and maxDims are the minimum, optimum, and maximum dimensions, and networkDims are the dimensions for this input tensor that are provided to the INetworkDefinition object, then the following conditions must all hold:

(1) minDims.nbDims == optDims.nbDims == maxDims.nbDims == networkDims.nbDims (2) 0 <= minDims.d[i] <= optDims.d[i] <= maxDims.d[i] for i = 0, ..., networkDims.nbDims-1 (3) if networkDims.d[i] != -1, then minDims.d[i] == optDims.d[i] == maxDims.d[i] == networkDims.d[i]

This function may (but need not be) called for an input tensor that does not have dynamic dimensions. In this case, the third argument must always equal networkDims.

Parameters
inputNameThe input tensor name
selectWhether to set the minimum, optimum, or maximum dimensions
dimsThe minimum, optimum, or maximum dimensions for this input tensor
Returns
false if an inconsistency was detected (e.g. the rank does not match another dimension that was previously set for the same input), true if no inconsistency was detected. Note that inputs can be validated only partially; a full validation is performed at engine build time.
Warning
If run on DLA, minimum, optimum, and maximum dimensions must to be the same.

◆ getDimensions()

virtual Dims nvinfer1::IOptimizationProfile::getDimensions ( const char *  inputName,
OptProfileSelector  select 
) const
pure virtualnoexcept

Get the minimum / optimum / maximum dimensions for a dynamic input tensor.

If the dimensions have not been previously set via setDimensions(), return an invalid Dims with nbDims == -1.

◆ setShapeValues()

virtual bool nvinfer1::IOptimizationProfile::setShapeValues ( const char *  inputName,
OptProfileSelector  select,
const int32_t *  values,
int32_t  nbValues 
)
pure virtualnoexcept

Set the minimum / optimum / maximum values for an input shape tensor.

This function must be called three times for every input tensor t that is a shape tensor (t.isShape() == true). This implies that the datatype of t is DataType::kINT32, the rank is either 0 or 1, and the dimensions of t are fixed at network definition time. This function must not be called for any input tensor that is not a shape tensor. Each time this function is called for the same input tensor, the same nbValues must be supplied (either 1 if the tensor rank is 0, or dims.d[0] if the rank is 1). Furthermore, if minVals, optVals, maxVals are the minimum, optimum, and maximum values, it must be true that minVals[i] <= optVals[i] <= maxVals[i] for i = 0, ..., nbValues - 1.

Parameters
inputNameThe input tensor name
selectWhether to set the minimum, optimum, or maximum input values.
valuesAn array of length nbValues containing the minimum, optimum, or maximum shape tensor elements.
nbValuesThe length of the value array, which must equal the number of shape tensor elements (>= 1)
Returns
false if an inconsistency was detected (e.g. nbValues does not match a previous call for the same tensor), else true. As for setDimensions(), a full validation can only be performed at engine build time.
Warning
If run on DLA, minimum, optimum, and maximum shape values must to be the same.

◆ getNbShapeValues()

virtual int32_t nvinfer1::IOptimizationProfile::getNbShapeValues ( const char *  inputName) const
pure virtualnoexcept

Get the number of values for an input shape tensor.

This will return the number of shape values if setShapeValues() has been called before for this input tensor. Otherwise, return -1.

◆ getShapeValues()

virtual const int32_t* nvinfer1::IOptimizationProfile::getShapeValues ( const char *  inputName,
OptProfileSelector  select 
) const
pure virtualnoexcept

Get the minimum / optimum / maximum values for an input shape tensor.

If the shape values have not been set previously with setShapeValues(), this returns nullptr.

◆ setExtraMemoryTarget()

virtual bool nvinfer1::IOptimizationProfile::setExtraMemoryTarget ( float  target)
pure virtualnoexcept

Set a target for extra GPU memory that may be used by this profile.

Parameters
targetAdditional memory that the builder should aim to maximally allocate for this profile, as a fraction of the memory it would use if the user did not impose any constraints on memory. This unconstrained case is the default; it corresponds to target == 1.0. If target == 0.0, the builder aims to create the new optimization profile without allocating any additional weight memory. Valid inputs lie between 0.0 and 1.0. This parameter is only a hint, and TensorRT does not guarantee that the target will be reached. This parameter is ignored for the first (default) optimization profile that is defined.
Returns
true if the input is in the valid range (between 0 and 1 inclusive), else false

◆ getExtraMemoryTarget()

virtual float nvinfer1::IOptimizationProfile::getExtraMemoryTarget ( ) const
pure virtualnoexcept

Get the extra memory target that has been defined for this profile.

◆ isValid()

virtual bool nvinfer1::IOptimizationProfile::isValid ( ) const
pure virtualnoexcept

Check whether the optimization profile can be passed to an IBuilderConfig object.

This function performs partial validation, by e.g. checking that whenever one of the minimum, optimum, or maximum dimensions of a tensor have been set, the others have also been set and have the same rank, as well as checking that the optimum dimensions are always as least as large as the minimum dimensions, and that the maximum dimensions are at least as large as the optimum dimensions. Some validation steps require knowledge of the network definition and are deferred to engine build time.

Returns
true if the optimization profile is valid and may be passed to an IBuilderConfig, else false

The documentation for this class was generated from the following file: