tensor info describes the type and shape of tensors More...

#include <onert-micro.h>

Collaboration diagram for nnfw_tensorinfo:

Data Fields
NNFW_TYPE	dtype

int32_t	rank

int32_t	dims [NNFW_MAX_RANK]

Detailed Description

tensor info describes the type and shape of tensors

This structure is used to describe input and output tensors. Application can get input and output tensor type and shape described in model by using nnfw_input_tensorinfo and nnfw_output_tensorinfo

Maximum rank is 6 (NNFW_MAX_RANK). And tensor's dimension value is filled in 'dims' field from index 0. For example, if tensor's rank is 4, application can get dimension value from dims[0], dims[1], dims[2], and dims[3]

Definition at line 123 of file onert-micro.h.

Field Documentation

◆ dims

int32_t nnfw_tensorinfo::dims

The dimension of tensor. Maximum rank is 6 (NNFW_MAX_RANK).

Definition at line 133 of file onert-micro.h.

Referenced by onert::api::APIConverter::convertType(), NNFW_SESSION::input_tensorinfo(), num_elems(), num_elems(), NNFW_SESSION::output_tensorinfo(), nnfw_session::set_input_tensorinfo(), and NNFW_SESSION::set_input_tensorinfo().

◆ dtype

NNFW_TYPE nnfw_tensorinfo::dtype

The data type

Definition at line 126 of file onert-micro.h.

Referenced by onert::api::APIConverter::convertType(), NNFW_SESSION::input_tensorinfo(), main(), NNFW_SESSION::output_tensorinfo(), nnfw_session::run_with_auto_compilation(), NNFW_SESSION::set_input(), NNFW_SESSION::set_input_tensorinfo(), and NNFW_SESSION::set_output().

◆ rank

int32_t nnfw_tensorinfo::rank

The number of dimensions (rank)

Definition at line 128 of file onert-micro.h.