Compute Library
18.05
|
Basic function to run NEConvertFullyConnectedWeightsKernel. More...
#include <NEConvertFullyConnectedWeights.h>
Public Member Functions | |
NEConvertFullyConnectedWeights () | |
Default constructor. More... | |
void | configure (const ITensor *input, ITensor *output, const TensorShape &original_input_shape, DataLayout data_layout) |
Initialize the function. More... | |
void | run () override |
Run the kernels contained in the function. More... | |
Public Member Functions inherited from IFunction | |
virtual | ~IFunction ()=default |
Destructor. More... | |
virtual void | prepare () |
Prepare the function for executing. More... | |
Static Public Member Functions | |
static Status | validate (const ITensorInfo *input, const ITensorInfo *output, const TensorShape &original_input_shape, DataLayout data_layout) |
Static function to check if given info will lead to a valid configuration of NEConvertFullyConnectedWeights. More... | |
Basic function to run NEConvertFullyConnectedWeightsKernel.
Definition at line 36 of file NEConvertFullyConnectedWeights.h.
Default constructor.
void configure | ( | const ITensor * | input, |
ITensor * | output, | ||
const TensorShape & | original_input_shape, | ||
DataLayout | data_layout | ||
) |
Initialize the function.
[in] | input | Source weights tensor to convert. Must be 2 dimensional. Data types supported: U8/S8/QS8/QASYMM8/U16/S16/QS16/U32/S32/QS32/F16/F32. |
[out] | output | The converted weights tensor. Shape and Data Type: Same as input . |
[in] | original_input_shape | Shape of the original input tensor (the one entering fully connected layer). Must be in NCHW format. |
[in] | data_layout | The data layout the weights have been trained in. |
|
overridevirtual |
Run the kernels contained in the function.
For NEON kernels:
For OpenCL kernels:
Implements IFunction.
|
static |
Static function to check if given info will lead to a valid configuration of NEConvertFullyConnectedWeights.
[in] | input | Source weights tensor info to convert. Must be 2 dimensional. Data types supported: U8/S8/QS8/QASYMM8/U16/S16/QS16/U32/S32/QS32/F16/F32. |
[in] | output | The converted weights tensor info. Shape and Data Type: Same as input . |
[in] | original_input_shape | Shape of the original input tensor (the one entering fully connected layer). Must be in NCHW format. |
[in] | data_layout | The data layout the weights have been trained in. |