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

A fully connected layer in a network definition. This layer expects an input tensor of three or more non-batch dimensions. The input is automatically reshaped into an MxV tensor X, where V is a product of the last three dimensions and M is a product of the remaining dimensions (where the product over 0 dimensions is defined as 1). For example: More...

Inheritance diagram for nvinfer1::IFullyConnectedLayer:
Collaboration diagram for nvinfer1::IFullyConnectedLayer:

Public Member Functions

virtual void setNbOutputChannels (int32_t nbOutputs)=0
 Set the number of output channels K from the fully connected layer. More...
 
virtual int32_t getNbOutputChannels () const =0
 Get the number of output channels K from the fully connected layer. More...
 
virtual void setKernelWeights (Weights weights)=0
 Set the kernel weights, given as a KxC matrix in row-major order. More...
 
virtual Weights getKernelWeights () const =0
 Get the kernel weights. More...
 
virtual void setBiasWeights (Weights weights)=0
 Set the bias weights. More...
 
virtual Weights getBiasWeights () const =0
 Get the bias weights. More...
 
void setInput (int32_t index, ITensor &tensor)=0
 Append or replace an input of this layer with a specific tensor. More...
 
virtual LayerType getType () const =0
 Return the type of a layer. More...
 
virtual void setName (const char *name)=0
 Set the name of a layer. More...
 
virtual const char * getName () const =0
 Return the name of a layer. More...
 
virtual int32_t getNbInputs () const =0
 Get the number of inputs of a layer. More...
 
virtual ITensorgetInput (int32_t index) const =0
 Get the layer input corresponding to the given index. More...
 
virtual int32_t getNbOutputs () const =0
 Get the number of outputs of a layer. More...
 
virtual ITensorgetOutput (int32_t index) const =0
 Get the layer output corresponding to the given index. More...
 
virtual void setPrecision (DataType dataType)=0
 Set the computational precision of this layer. More...
 
virtual DataType getPrecision () const =0
 get the computational precision of this layer More...
 
virtual bool precisionIsSet () const =0
 whether the computational precision has been set for this layer More...
 
virtual void resetPrecision ()=0
 reset the computational precision for this layer More...
 
virtual void setOutputType (int32_t index, DataType dataType)=0
 Set the output type of this layer. More...
 
virtual DataType getOutputType (int32_t index) const =0
 get the output type of this layer More...
 
virtual bool outputTypeIsSet (int32_t index) const =0
 whether the output type has been set for this layer More...
 
virtual void resetOutputType (int32_t index)=0
 reset the output type for this layer More...
 

Protected Member Functions

virtual ~IFullyConnectedLayer ()
 

Detailed Description

A fully connected layer in a network definition. This layer expects an input tensor of three or more non-batch dimensions. The input is automatically reshaped into an MxV tensor X, where V is a product of the last three dimensions and M is a product of the remaining dimensions (where the product over 0 dimensions is defined as 1). For example:

  • If the input tensor has shape {C, H, W}, then the tensor is reshaped into {1, C*H*W}.
  • If the input tensor has shape {P, C, H, W}, then the tensor is reshaped into {P, C*H*W}.

The layer then performs the following operation:

Y := matmul(X, W^T) + bias

Where X is the MxV tensor defined above, W is the KxV weight tensor of the layer, and bias is a row vector size K that is broadcasted to MxK. K is the number of output channels, and configurable via setNbOutputChannels(). If bias is not specified, it is implicitly 0.

The MxK result Y is then reshaped such that the last three dimensions are {K, 1, 1} and the remaining dimensions match the dimensions of the input tensor. For example:

  • If the input tensor has shape {C, H, W}, then the output tensor will have shape {K, 1, 1}.
  • If the input tensor has shape {P, C, H, W}, then the output tensor will have shape {P, K, 1, 1}.
Warning
Do not inherit from this class, as doing so will break forward-compatibility of the API and ABI.

Constructor & Destructor Documentation

◆ ~IFullyConnectedLayer()

virtual nvinfer1::IFullyConnectedLayer::~IFullyConnectedLayer ( )
inlineprotectedvirtual

Member Function Documentation

◆ setNbOutputChannels()

virtual void nvinfer1::IFullyConnectedLayer::setNbOutputChannels ( int32_t  nbOutputs)
pure virtual

Set the number of output channels K from the fully connected layer.

If executing this layer on DLA, number of output channels must in the range [1,8192].

See also
getNbOutputChannels()

◆ getNbOutputChannels()

virtual int32_t nvinfer1::IFullyConnectedLayer::getNbOutputChannels ( ) const
pure virtual

Get the number of output channels K from the fully connected layer.

See also
setNbOutputChannels()

◆ setKernelWeights()

virtual void nvinfer1::IFullyConnectedLayer::setKernelWeights ( Weights  weights)
pure virtual

Set the kernel weights, given as a KxC matrix in row-major order.

See also
getKernelWeights()

◆ getKernelWeights()

virtual Weights nvinfer1::IFullyConnectedLayer::getKernelWeights ( ) const
pure virtual

Get the kernel weights.

See also
setKernelWeights()

◆ setBiasWeights()

virtual void nvinfer1::IFullyConnectedLayer::setBiasWeights ( Weights  weights)
pure virtual

Set the bias weights.

Bias is optional. To omit bias, set the count value in the weights structure to zero.

See also
getBiasWeightsWeights()

◆ getBiasWeights()

virtual Weights nvinfer1::IFullyConnectedLayer::getBiasWeights ( ) const
pure virtual

Get the bias weights.

See also
setBiasWeightsWeights()

◆ setInput()

void nvinfer1::IFullyConnectedLayer::setInput ( int32_t  index,
ITensor tensor 
)
pure virtual

Append or replace an input of this layer with a specific tensor.

Parameters
indexthe index of the input to modify.
tensorthe new input tensor

For a IFullyConnectedLayer, only index 0 is valid unless explicit precision mode is enabled. With explicit precision mode, values 0-1 are valid where value 1 overrides kernel weights. Kernel weights tensor (computed at build-time) must be an output of dequantize scale layer (i.e. a scale layer with int8 input and float output) in explicit precision network. Conversely, this input tensor can be overridden via appropriate set call. The indices are as follows:

  • 0: The input activation tensor.
  • 1: The kernel weights tensor (a constant tensor).

If this function is called with a value greater than 0, then the function getNbInputs() changes

Implements nvinfer1::ILayer.

◆ getType()

virtual LayerType nvinfer1::ILayer::getType ( ) const
pure virtualinherited

Return the type of a layer.

See also
LayerType

◆ setName()

virtual void nvinfer1::ILayer::setName ( const char *  name)
pure virtualinherited

Set the name of a layer.

This method copies the name string.

See also
getName()
Here is the caller graph for this function:

◆ getName()

virtual const char* nvinfer1::ILayer::getName ( ) const
pure virtualinherited

Return the name of a layer.

See also
setName()
Here is the caller graph for this function:

◆ getNbInputs()

virtual int32_t nvinfer1::ILayer::getNbInputs ( ) const
pure virtualinherited

Get the number of inputs of a layer.

◆ getInput()

virtual ITensor* nvinfer1::ILayer::getInput ( int32_t  index) const
pure virtualinherited

Get the layer input corresponding to the given index.

Parameters
indexThe index of the input tensor.
Returns
The input tensor, or nullptr if the index is out of range or the tensor is optional (ISliceLayer, IRNNLayer and IRNNv2Layer).

◆ getNbOutputs()

virtual int32_t nvinfer1::ILayer::getNbOutputs ( ) const
pure virtualinherited

Get the number of outputs of a layer.

Here is the caller graph for this function:

◆ getOutput()

virtual ITensor* nvinfer1::ILayer::getOutput ( int32_t  index) const
pure virtualinherited

Get the layer output corresponding to the given index.

Returns
The indexed output tensor, or nullptr if the index is out of range or the tensor is optional (IRNNLayer and IRNNv2Layer).
Here is the caller graph for this function:

◆ setPrecision()

virtual void nvinfer1::ILayer::setPrecision ( DataType  dataType)
pure virtualinherited

Set the computational precision of this layer.

Setting the precision allows TensorRT to choose implementation which run at this computational precision. Layer input type would also get inferred from layer computational precision. TensorRT could still choose a non-conforming fastest implementation ignoring set layer precision. Use BuilderFlag::kSTRICT_TYPES to force choose implementations with requested precision. In case no implementation is found with requested precision, TensorRT would choose available fastest implementation. If precision is not set, TensorRT will select the layer computational precision and layer input type based on performance considerations and the flags specified to the builder.

Parameters
precisionthe computational precision.
See also
getPrecision() precisionIsSet() resetPrecision()

◆ getPrecision()

virtual DataType nvinfer1::ILayer::getPrecision ( ) const
pure virtualinherited

get the computational precision of this layer

Returns
the computational precision
See also
setPrecision() precisionIsSet() resetPrecision()

◆ precisionIsSet()

virtual bool nvinfer1::ILayer::precisionIsSet ( ) const
pure virtualinherited

whether the computational precision has been set for this layer

Returns
whether the computational precision has been explicitly set
See also
setPrecision() getPrecision() resetPrecision()

◆ resetPrecision()

virtual void nvinfer1::ILayer::resetPrecision ( )
pure virtualinherited

reset the computational precision for this layer

See also
setPrecision() getPrecision() precisionIsSet()

◆ setOutputType()

virtual void nvinfer1::ILayer::setOutputType ( int32_t  index,
DataType  dataType 
)
pure virtualinherited

Set the output type of this layer.

Setting the output type constrains TensorRT to choose implementations which generate output data with the given type. If it is not set, TensorRT will select output type based on layer computational precision. TensorRT could still choose non-conforming output type based on fastest implementation. Use BuilderFlag::kSTRICT_TYPES to force choose requested output type. In case layer precision is not specified, output type would depend on chosen implementation based on performance considerations and the flags specified to the builder.

This method cannot be used to set the data type of the second output tensor of the TopK layer. The data type of the second output tensor of the topK layer is always Int32. Also the output type of all layers that are shape operations must be DataType::kINT32, and all attempts to set the output type to some other data type will be ignored except for issuing an error message.

Note that the layer output type is generally not identical to the data type of the output tensor, as TensorRT may insert implicit reformatting operations to convert the former to the latter. Calling layer->setOutputType(i, type) has no effect on the data type of the i-th output tensor of layer, and users need to call layer->getOutput(i)->setType(type) to change the tensor data type. This is particularly relevant if the tensor is marked as a network output, since only setType() [but not setOutputType()] will affect the data representation in the corresponding output binding.

Parameters
indexthe index of the output to set
dataTypethe type of the output
See also
getOutputType() outputTypeIsSet() resetOutputType()

◆ getOutputType()

virtual DataType nvinfer1::ILayer::getOutputType ( int32_t  index) const
pure virtualinherited

get the output type of this layer

Parameters
indexthe index of the output
Returns
the output precision. If no precision has been set, DataType::kFLOAT will be returned, unless the output type is inherently DataType::kINT32.
See also
getOutputType() outputTypeIsSet() resetOutputType()

◆ outputTypeIsSet()

virtual bool nvinfer1::ILayer::outputTypeIsSet ( int32_t  index) const
pure virtualinherited

whether the output type has been set for this layer

Parameters
indexthe index of the output
Returns
whether the output type has been explicitly set
See also
setOutputType() getOutputType() resetOutputType()

◆ resetOutputType()

virtual void nvinfer1::ILayer::resetOutputType ( int32_t  index)
pure virtualinherited

reset the output type for this layer

Parameters
indexthe index of the output
See also
setOutputType() getOutputType() outputTypeIsSet()

The documentation for this class was generated from the following file:
example.Y
Y
Definition: onnx-graphsurgeon/examples/01_creating_a_model/example.py:23