nnfw.h File Reference

This file describes runtime API. More...

#include <stddef.h>
#include <stdint.h>

Go to the source code of this file.

Data Structures
struct	nnfw_tensorinfo
	tensor info describes the type and shape of tensors More...

Macros
#define	NNFW_MAX_RANK   (6)
	Maximum rank expressible with nnfw.

Typedefs
typedef struct nnfw_session	nnfw_session
	Session to query with runtime.
typedef struct nnfw_tensorinfo	nnfw_tensorinfo
	tensor info describes the type and shape of tensors

Enumerations
enum	NNFW_TYPE {   NNFW_TYPE_TENSOR_FLOAT32 = 0 , NNFW_TYPE_TENSOR_INT32 = 1 , NNFW_TYPE_TENSOR_QUANT8_ASYMM = 2 , NNFW_TYPE_TENSOR_BOOL = 3 ,   NNFW_TYPE_TENSOR_UINT8 = 4 , NNFW_TYPE_TENSOR_INT64 = 5 , NNFW_TYPE_TENSOR_QUANT8_ASYMM_SIGNED = 6 , NNFW_TYPE_TENSOR_QUANT16_SYMM_SIGNED = 7 }
	Tensor types. More...
enum	NNFW_STATUS {   NNFW_STATUS_NO_ERROR = 0 , NNFW_STATUS_ERROR = 1 , NNFW_STATUS_UNEXPECTED_NULL = 2 , NNFW_STATUS_INVALID_STATE = 3 ,   NNFW_STATUS_OUT_OF_MEMORY = 4 , NNFW_STATUS_INSUFFICIENT_OUTPUT_SIZE = 5 , NNFW_STATUS_DEPRECATED_API = 6 }
	Result values returned from a call to an API function. More...
enum	NNFW_LAYOUT { NNFW_LAYOUT_NONE = 0 , NNFW_LAYOUT_CHANNELS_LAST = 1 , NNFW_LAYOUT_CHANNELS_FIRST = 2 }
	Data format of a tensor. More...
enum	NNFW_INFO_ID { NNFW_INFO_ID_VERSION = 0 }
	Information ID for retrieving information on nnfw (e.g. version) More...

Functions
NNFW_STATUS	nnfw_create_session (nnfw_session **session)
	Create a new session instance.
NNFW_STATUS	nnfw_close_session (nnfw_session *session)
	Close a session instance.
NNFW_STATUS	nnfw_load_model_from_file (nnfw_session *session, const char *path)
	Load model from path to model or nnpackage.
NNFW_STATUS	nnfw_apply_tensorinfo (nnfw_session *session, uint32_t index, nnfw_tensorinfo tensor_info)
	Apply i-th input's tensor info to resize input tensor.
NNFW_STATUS	nnfw_set_input_tensorinfo (nnfw_session *session, uint32_t index, const nnfw_tensorinfo *tensor_info)
	Set input model's tensor info for resizing.
NNFW_STATUS	nnfw_prepare (nnfw_session *session)
	Prepare session to be ready for inference.
NNFW_STATUS	nnfw_run (nnfw_session *session)
	Run inference.
NNFW_STATUS	nnfw_run_async (nnfw_session *session)
	Run inference asynchronously.
NNFW_STATUS	nnfw_await (nnfw_session *session)
	Wait for asynchronous run to finish.
NNFW_STATUS	nnfw_set_input (nnfw_session *session, uint32_t index, NNFW_TYPE type, const void *buffer, size_t length)
	Set input buffer.
NNFW_STATUS	nnfw_set_output (nnfw_session *session, uint32_t index, NNFW_TYPE type, void *buffer, size_t length)
	Set output buffer.
NNFW_STATUS	nnfw_input_size (nnfw_session *session, uint32_t *number)
	Get the number of inputs.
NNFW_STATUS	nnfw_output_size (nnfw_session *session, uint32_t *number)
	Get the number of outputs.
NNFW_STATUS	nnfw_set_input_layout (nnfw_session *session, uint32_t index, NNFW_LAYOUT layout)
	Set the layout of an input.
NNFW_STATUS	nnfw_set_output_layout (nnfw_session *session, uint32_t index, NNFW_LAYOUT layout)
	Set the layout of an output.
NNFW_STATUS	nnfw_input_tensorinfo (nnfw_session *session, uint32_t index, nnfw_tensorinfo *tensor_info)
	Get i-th input tensor info.
NNFW_STATUS	nnfw_output_tensorinfo (nnfw_session *session, uint32_t index, nnfw_tensorinfo *tensor_info)
	Get i-th output tensor info.
NNFW_STATUS	nnfw_set_available_backends (nnfw_session *session, const char *backends)
	Set available backends.
NNFW_STATUS	nnfw_set_op_backend (nnfw_session *session, const char *op, const char *backend)
	Set the operation's backend.
NNFW_STATUS	nnfw_query_info_u32 (nnfw_session *session, NNFW_INFO_ID id, uint32_t *val)
	Retrieve uint32 type of nnfw information for given information ID.
NNFW_STATUS	nnfw_set_workspace (nnfw_session *session, const char *dir)
	Set runtime's workspace directory.

Detailed Description

This file describes runtime API.

Definition in file nnfw.h.

Macro Definition Documentation

NNFW_MAX_RANK

#define NNFW_MAX_RANK   (6)

Maximum rank expressible with nnfw.

Definition at line 163 of file nnfw.h.

Typedef Documentation

nnfw_session

typedef struct nnfw_session nnfw_session

Session to query with runtime.

nnfw_session is started and passed by calling nnfw_create_session. Each session has its own inference environment, such as model to inference, backend usage, etc.

Load model by calling nnfw_load_model_from_file

After loading, prepare inference by calling nnfw_prepare. Application can set runtime environment before prepare by calling nnfw_set_available_backends, and it is optional.

Application can inference by calling nnfw_run. Before inference, application has responsibility to set input tensor to set input data by calling nnfw_set_output, and output tensor to get output by calling nnfw_set_input

To support input and output setting, application can get input and output tensor information by calling

• nnfw_input_size
• nnfw_output_size
• nnfw_input_tensorinfo
• nnfw_output_tensorinfo

Application can inference many times using one session, but next inference can do after prior inference end

Application cannot use muitiple model using one session

Definition at line 60 of file nnfw.h.

nnfw_tensorinfo

typedef struct nnfw_tensorinfo nnfw_tensorinfo

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]

Enumeration Type Documentation

NNFW_INFO_ID

enum NNFW_INFO_ID

Information ID for retrieving information on nnfw (e.g. version)

Enumerator
NNFW_INFO_ID_VERSION	nnfw runtime version Its value is uint32 in 0xMMmmmmPP, where MM = major, mmmm = minor, PP = patch.

Definition at line 152 of file nnfw.h.

{
  NNFW_INFO_ID_VERSION = 0,
} NNFW_INFO_ID;

NNFW_LAYOUT

enum NNFW_LAYOUT

Data format of a tensor.

Enumerator
NNFW_LAYOUT_NONE	Don't care layout
NNFW_LAYOUT_CHANNELS_LAST	Channel last layout If rank is 4, layout is NHWC
NNFW_LAYOUT_CHANNELS_FIRST	Channel first layout If rank is 4, layout is NCHW

Definition at line 133 of file nnfw.h.

{
  NNFW_LAYOUT_NONE = 0,
  NNFW_LAYOUT_CHANNELS_LAST = 1,
  NNFW_LAYOUT_CHANNELS_FIRST = 2,
} NNFW_LAYOUT;

NNFW_STATUS

enum NNFW_STATUS

Result values returned from a call to an API function.

Enumerator
NNFW_STATUS_NO_ERROR	Successful
NNFW_STATUS_ERROR	An error code for general use. Mostly used when there is no specific value for that certain situation.
NNFW_STATUS_UNEXPECTED_NULL	Unexpected null argument is given.
NNFW_STATUS_INVALID_STATE	When a function was called but it is not valid for the current session state.
NNFW_STATUS_OUT_OF_MEMORY	When it is out of memory
NNFW_STATUS_INSUFFICIENT_OUTPUT_SIZE	When it was given an insufficient output buffer
NNFW_STATUS_DEPRECATED_API	When API is deprecated

Definition at line 109 of file nnfw.h.

{
  NNFW_STATUS_NO_ERROR = 0,
  NNFW_STATUS_ERROR = 1,
  NNFW_STATUS_UNEXPECTED_NULL = 2,
  NNFW_STATUS_INVALID_STATE = 3,
  NNFW_STATUS_OUT_OF_MEMORY = 4,
  NNFW_STATUS_INSUFFICIENT_OUTPUT_SIZE = 5,
  NNFW_STATUS_DEPRECATED_API = 6,
} NNFW_STATUS;

NNFW_TYPE

enum NNFW_TYPE

Tensor types.

The type of tensor represented in nnfw_tensorinfo

Enumerator
NNFW_TYPE_TENSOR_FLOAT32	A tensor of 32 bit floating point
NNFW_TYPE_TENSOR_INT32	A tensor of 32 bit signed integer
NNFW_TYPE_TENSOR_QUANT8_ASYMM	A tensor of 8 bit unsigned integers that represent real numbers. real_value = (integer_value - zeroPoint) * scale.
NNFW_TYPE_TENSOR_BOOL	A tensor of boolean
NNFW_TYPE_TENSOR_UINT8	A tensor of 8 bit unsigned integer
NNFW_TYPE_TENSOR_INT64	A tensor of 64 bit signed integer
NNFW_TYPE_TENSOR_QUANT8_ASYMM_SIGNED	A tensor of 8 bit signed integers that represent real numbers. real_value = (integer_value - zeroPoint) * scale.
NNFW_TYPE_TENSOR_QUANT16_SYMM_SIGNED	A tensor of 16 bit signed integers that represent real numbers. real_value = (integer_value - zeroPoint) * scale. Forced to have zeroPoint equal to 0.

Definition at line 67 of file nnfw.h.

{
  NNFW_TYPE_TENSOR_FLOAT32 = 0,
  NNFW_TYPE_TENSOR_INT32 = 1,
  NNFW_TYPE_TENSOR_QUANT8_ASYMM = 2,
  NNFW_TYPE_TENSOR_BOOL = 3,
 
  NNFW_TYPE_TENSOR_UINT8 = 4,
 
  NNFW_TYPE_TENSOR_INT64 = 5,
 
  NNFW_TYPE_TENSOR_QUANT8_ASYMM_SIGNED = 6,
 
  NNFW_TYPE_TENSOR_QUANT16_SYMM_SIGNED = 7,
 
} NNFW_TYPE;

Function Documentation

nnfw_apply_tensorinfo()

NNFW_STATUS nnfw_apply_tensorinfo	(	nnfw_session *	session,
		uint32_t	index,
		nnfw_tensorinfo	tensor_info
	)

Apply i-th input's tensor info to resize input tensor.

This function should be called before nnfw_prepare is invoked, and should be called after nnfw_load_model_from_file is invoked See nnfw_prepare for information applying updated tensor info If this function is called many times for same index, tensor info is overwritten

Parameters

[in]	session	Session to the input tensor info is to be set
[in]	index	Index of input to be applied (0-indexed)
[in]	tensor_info	Tensor info to be applied

Returns

NNFW_STATUS_NO_ERROR if successful, otherwise return NNFW_STATUS_ERROR

Definition at line 155 of file nnfw_api.cc.

{
  return nnfw_session::deprecated("nnfw_apply_tensorinfo: Deprecated");
}

References nnfw_session::deprecated().

nnfw_await()

NNFW_STATUS nnfw_await

(

nnfw_session *

session

)

Wait for asynchronous run to finish.

This function must be called after calling nnfw_run_async, and can be called only once for a nnfw_run_async call.

When this function returns, it means that this session has finished the asynchronous run. Then the user can safely use the output data.

This function returns after the asynchronous inference is finished.

Parameters

[in]

session

The session to run inference

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 90 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->await();
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by NNFW_SESSION::wait().

nnfw_close_session()

NNFW_STATUS nnfw_close_session

(

nnfw_session *

session

)

Close a session instance.

After called, access to closed session by application will be invalid

Parameters

[in]

session

The session to be closed

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 60 of file nnfw_api.cc.

{
  delete session;
  return NNFW_STATUS_NO_ERROR;
}

nnfw_create_session()

NNFW_STATUS nnfw_create_session

(

nnfw_session **

session

)

Create a new session instance.

This only creates a session. Model is loaded after nnfw_load_model_from_file is invoked. And inference is performed after nnfw_run is invoked.

nnfw_close_session should be called once if session is no longer needed

Parameters

[out]

session

The session to be created

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 390 of file onert-micro.cpp.

{ return nnfw_session::create(session); }

References nnfw_session::create().

nnfw_input_size()

NNFW_STATUS nnfw_input_size	(	nnfw_session *	session,
		uint32_t *	number
	)

Get the number of inputs.

Application can call this function to get number of inputs defined in loaded model. This function should be called after nnfw_load_model_from_file is invoked to load model

Parameters

[in]	session	Session from input information is to be extracted
[out]	number	Variable which the number of inputs is put into

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 110 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->input_size(number);
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by NNFW_SESSION::input_size().

nnfw_input_tensorinfo()

NNFW_STATUS nnfw_input_tensorinfo	(	nnfw_session *	session,
		uint32_t	index,
		nnfw_tensorinfo *	tensor_info
	)

Get i-th input tensor info.

Before nnfw_prepare is invoked, this function return tensor info in model, so updated tensor info by nnfw_apply_tensorinfo is not returned.

After nnfw_prepare is invoked, this function return updated tensor info if tensor info is updated by nnfw_apply_tensorinfo.

Parameters

[in]	session	Session from input information is to be extracted
[in]	index	Index of input
[out]	tensor_info	Tensor info (shape, type, etc)

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 134 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->input_tensorinfo(index, tensor_info);
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by NNFW_SESSION::input_tensorinfo(), main(), and NNFW_SESSION::set_input().

nnfw_load_model_from_file()

NNFW_STATUS nnfw_load_model_from_file	(	nnfw_session *	session,
		const char *	path
	)

Load model from path to model or nnpackage.

The length of path must not exceed 1024 bytes including zero at the end.

Parameters

[in]	session	nnfw_session loading the given file/dir
[in]	path	Path to the model file or nnpackage directory to be loaded

Returns

NNFW_STATUS_NO_ERROR if successful

Load model from path to model or nnpackage.

The length of package_file_path must not exceed 1024 bytes including zero at the end.

Parameters

[in]	session	nnfw_session loading the given nnpackage file/dir
[in]	package_file_path	Path to the nnpackage file or unzipped directory to be loaded

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 392 of file onert-micro.cpp.

{
  return session->load_model_from_file(package_file_path);
}

References NNFW_RETURN_ERROR_IF_NULL.

nnfw_output_size()

NNFW_STATUS nnfw_output_size	(	nnfw_session *	session,
		uint32_t *	number
	)

Get the number of outputs.

Application can call this function to get number of outputs defined in loaded model. This function should be called after nnfw_load_model_from_file is invoked to load model

Parameters

[in]	session	Session from output information is to be extracted
[out]	number	Variable which the number of outputs is put into

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 116 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->output_size(number);
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by NNFW_SESSION::output_size().

nnfw_output_tensorinfo()

NNFW_STATUS nnfw_output_tensorinfo	(	nnfw_session *	session,
		uint32_t	index,
		nnfw_tensorinfo *	tensor_info
	)

Get i-th output tensor info.

After nnfw_load_model_from_file and before nnfw_prepare is invoked, it returns tensor info in the model.

After nnfw_prepare and before nnfw_run is invoked, this function returns updated tensor info if tensor info is updated by nnfw_set_input_tensorinfo.

After nnfw_run is invoked(at least once), it returns the updated tensor info during the latest execution.

Parameters

[in]	session	Session from output information is to be extracted
[in]	index	Index of output
[out]	tensor_info	Tensor info (shape, type, etc)

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 141 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->output_tensorinfo(index, tensor_info);
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by main(), NNFW_SESSION::output_tensorinfo(), and NNFW_SESSION::set_output().

nnfw_prepare()

NNFW_STATUS nnfw_prepare

(

nnfw_session *

session

)

Prepare session to be ready for inference.

This phase may finalize model compilation, scheduling, and additional settings. If nnfw_apply_tensorinfo is called to apply input tensor info different with model before this function, tries to resize all tensors.

Parameters

[in]

session

the session to be prepared

Returns

NNFW_STATUS_NO_ERROR if successful, otherwise return NNFW_STATUS_ERROR

Definition at line 72 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->prepare();
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by main(), and NNFW_SESSION::NNFW_SESSION().

nnfw_query_info_u32()

NNFW_STATUS nnfw_query_info_u32	(	nnfw_session *	session,
		NNFW_INFO_ID	id,
		uint32_t *	val
	)

Retrieve uint32 type of nnfw information for given information ID.

Retrieves the information of property given by information id

Note

: The input session could be null for global information (e.g. runtime version).*

Parameters

[in]	session	session to be queried on.
[in]	id	ID to be queried
[out]	val	uint32 value to be returned.

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 178 of file nnfw_api.cc.

{
  (void)session;
  switch (id)
  {
    case NNFW_INFO_ID_VERSION:
      if (val)
      {
        *val = NNFW_VERSION;
        return NNFW_STATUS_NO_ERROR;
      }
      break;
    default:
      return NNFW_STATUS_ERROR;
  }
  // It should not be reached.
  return NNFW_STATUS_ERROR;
}

References NNFW_INFO_ID_VERSION, NNFW_STATUS_ERROR, NNFW_STATUS_NO_ERROR, and NNFW_VERSION.

nnfw_run()

NNFW_STATUS nnfw_run

(

nnfw_session *

session

)

Run inference.

This function should be called after model is loaded by nnfw_load_model_from_file, session is prepared for inference by nnfw_prepare, set input and output buffers by nnfw_set_input and nnfw_set_output.

This function return after inference is finished.

Parameters

[in]

session

The session to run inference

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 78 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->run();
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by main(), and NNFW_SESSION::run().

nnfw_run_async()

NNFW_STATUS nnfw_run_async

(

nnfw_session *

session

)

Run inference asynchronously.

This function must be called after model is loaded by nnfw_load_model_from_file, session is prepared for inference by nnfw_prepare, set input and output buffers by nnfw_set_input and nnfw_set_output.

This function returns immediately after starting a thread to run the inference. To get the result of it or to do the next inference with nnfw_run or nnfw_run_async, nnfw_await must be called to ensure the current asynchronous inference has finished. Only one asynchronous inference is allowed at a time for a session. If this function is called while the previous one is still running, it returns an error.

Parameters

[in]

session

The session to run inference

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 84 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->run_async();
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by NNFW_SESSION::run_async().

nnfw_set_available_backends()

NNFW_STATUS nnfw_set_available_backends	(	nnfw_session *	session,
		const char *	backends
	)

Set available backends.

This function should be called before nnfw_prepare is invoked.

Supported backends differs on each platforms. For example, x86_64 supports "cpu" only. Multiple backends can be set and they must be separated by a semicolon (ex: "acl_cl;cpu"). For each backend string, libbackend_{backend}.so will be dynamically loaded during nnfw_prepare. Among the multiple backends, the 1st element is used as the default backend.

Parameters

[in]	session	session to which avilable backends are set
[in]	backends	available backends on which nnfw uses

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 167 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->set_available_backends(backends);
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by NNFW_SESSION::NNFW_SESSION().

nnfw_set_input()

NNFW_STATUS nnfw_set_input	(	nnfw_session *	session,
		uint32_t	index,
		NNFW_TYPE	type,
		const void *	buffer,
		size_t	length
	)

Set input buffer.

This function must be called after nnfw_prepare, buffer given to this function can be reused for many inferences. length must be greater or equal than the operand requires. To specify an optional input, you can either not call this for that input or call this with buffer of NULL and length of 0. If you set NNFW_TYPE_TENSOR_FLOAT32 type and model has quantized input type on given index, runtime will set quantized data type model input by converting from float buffer data internally.

Parameters

[in]	session	Session to the input is to be set
[in]	index	Index of input to be set (0-indexed)
[in]	type	Type of the input
[in]	buffer	Raw buffer for input
[in]	length	Size of bytes of input buffer

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 96 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->set_input(index, type, buffer, length);
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by main(), and NNFW_SESSION::set_input().

nnfw_set_input_layout()

NNFW_STATUS nnfw_set_input_layout	(	nnfw_session *	session,
		uint32_t	index,
		NNFW_LAYOUT	layout
	)

Set the layout of an input.

The input that does not call this has NNFW_LAYOUT_NHWC layout

Parameters

[in]	session	session from inference input is to be extracted
[in]	index	index of input to be set (0-indexed)
[in]	layout	layout to set to target input

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 122 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->set_input_layout(index, layout);
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by NNFW_SESSION::set_input_layout().

nnfw_set_input_tensorinfo()

NNFW_STATUS nnfw_set_input_tensorinfo	(	nnfw_session *	session,
		uint32_t	index,
		const nnfw_tensorinfo *	tensor_info
	)

Set input model's tensor info for resizing.

This function can be called at any time after calling nnfw_load_model_from_file. Changing input tensor's shape will cause shape inference for the model. There are two different types of shape inference - static and dynamic. Which one to use is depend on the current state of the session. When it is called after calling nnfw_load_model_from_file and before calling nnfw_prepare, this info will be used when nnfw_prepare. And it will perform static shape inference for all tensors. When it is called after calling nnfw_prepare or even after nnfw_run, this info will be used when nnfw_run. And the shapes of the tensors are determined on the fly. If this function is called many times for the same index, it is overwritten. tensor_info's dtype field is ignored.

Parameters

[in]	session	Session to the input tensor info is to be set
[in]	index	Index of input to be set (0-indexed)
[in]	tensor_info	Tensor info to be set

Returns

NNFW_STATUS_NO_ERROR if successful, otherwise return NNFW_STATUS_ERROR

Definition at line 160 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->set_input_tensorinfo(index, tensor_info);
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by NNFW_SESSION::set_input_tensorinfo().

nnfw_set_op_backend()

NNFW_STATUS nnfw_set_op_backend	(	nnfw_session *	session,
		const char *	op,
		const char *	backend
	)

Set the operation's backend.

This function should be called before nnfw_prepare is invoked.

The backend for op has higher priority than available backends specified by nnfw_set_available_backends.

Parameters

[in]	session	session to be modified
[in]	op	operation to be set
[in]	backend	bakcend on which operation run

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 173 of file nnfw_api.cc.

{
  return nnfw_session::deprecated("nnfw_set_op_backend: Deprecated");
}

References nnfw_session::deprecated().

Referenced by main().

nnfw_set_output()

NNFW_STATUS nnfw_set_output	(	nnfw_session *	session,
		uint32_t	index,
		NNFW_TYPE	type,
		void *	buffer,
		size_t	length
	)

Set output buffer.

This function must be called after nnfw_prepare, buffer given to this function can be reused for many inferences. length must be greater or equal than the operand requires. An output operand can have unspecified shape and deduced dynamically during the execution. You must provide buffer large enough. If you set NNFW_TYPE_TENSOR_FLOAT32 type and model has quantized output type on given index, runtime will set dequantized float buffer data from quantize data type model output internally.

Parameters

[in]	session	Session from inference output is to be extracted
[in]	index	Index of output to be set (0-indexed)
[in]	type	Type of the output
[out]	buffer	Raw buffer for output
[in]	length	Size of bytes of output buffer

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 103 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->set_output(index, type, buffer, length);
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by main(), and NNFW_SESSION::set_output().

nnfw_set_output_layout()

NNFW_STATUS nnfw_set_output_layout	(	nnfw_session *	session,
		uint32_t	index,
		NNFW_LAYOUT	layout
	)

Set the layout of an output.

The output that does not call this has NNFW_LAYOUT_NHWC layout

Parameters

[in]	session	session from inference output is to be extracted
[in]	index	index of output to be set (0-indexed)
[in]	layout	layout to set to target output

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 128 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->set_output_layout(index, layout);
}

References NNFW_RETURN_ERROR_IF_NULL.

Referenced by NNFW_SESSION::set_output_layout().

nnfw_set_workspace()

NNFW_STATUS nnfw_set_workspace	(	nnfw_session *	session,
		const char *	dir
	)

Set runtime's workspace directory.

This function sets the directory to be used as a workspace. System should allow read and write access to the directory for the runtime. Default workspace is running directory of the application. This function should be called before nnfw_load_model_from_file is invoked.

Parameters

[in]	session	session to be queried on.
[in]	dir	workspace directory path

Returns

NNFW_STATUS_NO_ERROR if successful

Definition at line 230 of file nnfw_api.cc.

{
  NNFW_RETURN_ERROR_IF_NULL(session);
  return session->set_workspace(dir);
}

References NNFW_RETURN_ERROR_IF_NULL.