Get the scale of the feature map */

The size in bytes of the data type * * @param[in] data_type Input data type * * @return The size in bytes of the data type */

First 2D slice of the window * * @return The first slice of the window. */

Returns an explanatory exception message * * @return Status message */

Get end of const iterator. * * @return end of const iterator. */

Access uderlying object * * @return Underlying object */

Get min sizes. */

Returns producer node id * * @return Producer node id */

Iterator pointing at the begin of the dataset. * * @return Iterator for the dataset. */

Collapse dimensions starting from a given point * * @param[in] start Starting point of collapsing dimensions */

First 4D slice of the window * * @return The first slice of the window. */

Method to return the GEMM configuration function based on data type * * @param[in] data_type Input data type * * @return the valid

Compute the mininum and maximum values a data type can take * * @param[in] dt Data type to get the min/max bounds of * * @return A tuple (min,max)

Get the pointer position of a Image * * @param[in] img Pointer to the starting position of the buffer * @param[in] x Relative X position * @para

Open a NPY file and reads its metadata * * @param[in] npy_filename File to open * @param[in] file_layout (Optional) Layout in which th

Compute size of dimensions lower than the given one. * * @param[in] dimension Upper boundary. * * @return The linear size of the c

Generates appropriate output accessor according to the specified graph parameters * * @note If the output accessor is requested to validate the grap

Quantize a value given a 16-bit symmetric quantization scheme * * @param[in] value Value to quantize * @param[in] qinfo Quantiz

Accessor to remove the dimension n from the tensor shape. * * @note The upper dimensions of the tensor shape will be shifted down by 1

Return true if a NPY file is currently open */

Slide the passed 2D window slice. * * If slice contains the last slice then it will remain unchanged and false will be returned. *

Get min variances. */

Calculate the reduced shape of a tensor given an axis * * @param[in] input Input tensor info * @param[in] axis Axis on which to perform re

Return the pixel at (x,y) using area interpolation by clamping when out of borders. The image must be single channel U8 * * @note The interpolation

Returns producer node * * @return Producer node */

Check that the provided Requantize32 is compatible with the "asymmetric" hybrid kernels. These don't support per channel quantization. Technically b

Convert string values to integer. * * @note This function implements the same behaviour as std::stoi. The latter * is missing in some Android

Calculate the transposed shape of a tensor * * @param[in] input Input tensor info * * @return the calculated shape */

Absolute value. \param arg operand \return absolute value of \a arg template<typename T> typename enable<T,T>::type fabs(T arg) { return unary_special

Cast char values to int so that their numeric value are printed.

Quantize a neon vector holding 8 floating point values. * * @param[in] qv Input values to be quantized. * @param[in] qi Quantization information to