nn_tensor4d_f32()

Tensor4D_F32 * nn_tensor4d_f32	(	size_t	shape[4],
		const float *	data
	)

Creates a 4D floating-point data tensor, with the shape defined by the 4-element array shape.

This method always allocates memory for the tensor. If data is specified, it copies the data from data to the tensor.

Parameters

shape	The shape of the tensor.
data	If specified, the data to copy from and store in the tensor.