tensor info describes the type and shape of tensors More...
#include <nnfw_api_wrapper.h>
Data Fields | |
| const char * | 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 input_tensorinfo and 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 36 of file nnfw_api_wrapper.h.
Field Documentation
◆ dims
| int32_t tensorinfo::dims[NNFW_MAX_RANK] |
The dimension of tensor. Maximum rank is 6 (NNFW_MAX_RANK).
Definition at line 46 of file nnfw_api_wrapper.h.
Referenced by get_dims(), NNFW_SESSION::input_tensorinfo(), NNFW_SESSION::output_tensorinfo(), set_dims(), and NNFW_SESSION::set_input_tensorinfo().
◆ dtype
| const char* tensorinfo::dtype |
The data type
Definition at line 39 of file nnfw_api_wrapper.h.
Referenced by NNFW_SESSION::input_tensorinfo(), NNFW_SESSION::output_tensorinfo(), PYBIND11_MODULE(), and NNFW_SESSION::set_input_tensorinfo().
◆ rank
| int32_t tensorinfo::rank |
The number of dimensions (rank)
Definition at line 41 of file nnfw_api_wrapper.h.
Referenced by get_dims(), NNFW_SESSION::input_tensorinfo(), NNFW_SESSION::output_tensorinfo(), PYBIND11_MODULE(), set_dims(), and NNFW_SESSION::set_input_tensorinfo().
The documentation for this struct was generated from the following file:
- runtime/onert/api/python/include/nnfw_api_wrapper.h
