Tensor Properties

How memory is mapped kTfLiteMmapRo: Memory mapped read only. i.e. weights kTfLiteArenaRw: Arena allocated read write memory (i.e. temporaries, outputs).

The number of bytes required to store the data of this Tensor. I.e. (bytes of each element) * dims[0] * ... * dims[n-1]. For example, if type is kTfLiteFloat32 and dims = {3, 2} then bytes = sizeof(float) * 3 * 2 = 4 * 3 * 2 = 24.

Get a copy of the tensor data as a managed array

A raw data pointers.

Get the size of the dimensions of the tensor

Returns true if the object has been disposed.

Get the tensor data as a jagged array

Name of this tensor.

Pointer to the unmanaged object

Quantization information.

The data type specification for data stored in `data`. This affects what member of `data` union should be used.