eIQ MCU Media Processing Pipeline API

MPP VERSION 3.3

1. MPP API

Functions

• int mpp_api_init (mpp_api_params_t ∗params)

• mpp_t mpp_create (mpp_params_t ∗params, int ∗ret)

• int mpp_camera_add (mpp_t mpp, const char ∗name, mpp_camera_params_t ∗params)

• int mpp_static_img_add (mpp_t mpp, mpp_img_params_t ∗params, void ∗addr)

• int mpp_display_add (mpp_t mpp, const char ∗name, mpp_display_params_t ∗params)

• int mpp_nullsink_add (mpp_t mpp)

• int mpp_element_add (mpp_t mpp, mpp_element_id_t id, mpp_element_params_t ∗params, mpp_elem_handle_t ∗elem_h)

• int mpp_split (mpp_t mpp, unsigned int num, mpp_params_t ∗params, mpp_t ∗out_list)

• int mpp_background (mpp_t mpp, mpp_params_t ∗params, mpp_t ∗out_mpp)

• int mpp_element_update (mpp_t mpp, mpp_elem_handle_t elem_h, mpp_element_params_t ∗params)

• int mpp_start (mpp_t mpp, int last)

• int mpp_stop (mpp_t mpp)

• void mpp_stats_enable (mpp_stats_grp_t grp)

• void mpp_stats_disable (mpp_stats_grp_t grp)

• char ∗mpp_get_version (void)

1. Detailed Description

This section provides the detailed documentation for the MCU Media Processing Pipeline API.

2. Function Documentation

3. mpp_api_init()

int mpp_api_init (

mpp_api_params_t ∗ params ) Pipeline initialization.

This function initializes the library and its data structures.

It must be called before any other function of the API is called.

Parameters

in	params	API global parameters
out	ret	return code (0 - success, non-zero - error)

Returns

Return_codes

2. mpp_create()

mpp_t mpp_create (

mpp_params_t ∗ params, int ∗ ret )

Basic pipeline creation.

This function returns a handle to the pipeline. Parameters

in	params	pipeline parameters
out	ret	return code (0 - success, non-zero - error)

Returns

handle to the pipeline if success, NULL if there is an error.

3. mpp_camera_add()

int mpp_camera_add (

mpp_t mpp,

const char ∗ name, mpp_camera_params_t ∗ params )

Camera addition.

This function adds a camera to the pipeline.

Parameters

in	mpp	input pipeline
in	name	camera driver name
in	params	parameters to be configured on the camera

Returns

Return_codes

4. mpp_static_img_add()

int mpp_static_img_add (

mpp_t mpp,

mpp_img_params_t ∗ params, void ∗ addr )

Static image addition. Parameters

in	mpp	input pipeline
in	params	static image parameters
in	addr	image buffer

Returns

Return_codes Precondition

• Image buffer allocation/free is the responsibility of the user.

5. mpp_display_add()

int mpp_display_add (

mpp_t mpp,

const char ∗ name, mpp_display_params_t ∗ params )

Display addition.

This function adds a display to the pipeline. Parameters

in	mpp	input pipeline
in	name	display driver name
in	params	parameters that are configured on the display

Returns

Return_codes

6. **mpp_nullsink_add()**int mpp_nullsink_add (

mpp_t mpp )

Null sink addition.

This function adds a null-type sink to the pipeline.

After this call pipeline is closed and no further elements can be added. Input frames are discarded.

Parameters

in	mpp	input pipeline

Returns

Return_codes

7. mpp_element_add()

int mpp_element_add (

mpp_t mpp,

mpp_element_id_t id, mpp_element_params_t ∗ params, mpp_elem_handle_t ∗ elem_h )

Add processing element (single input, single output) This function adds an element to the pipeline. Available elements are:

• 2D image processing

• ML inference engine

• Labeled rectangle

• Compositor

Parameters

in	mpp	input pipeline
in	id	element id
in	params	element parameters
out	elem← _h	element handle in pipeline

Returns

Return_codes

8. mpp_split()

int mpp_split (

mpp_t mpp,

unsigned int num, mpp_params_t ∗ params, mpp_t ∗ out_list )

Pipeline multiplication. Parameters

in	mpp	input pipeline
in	num	number of output pipeline
in	params	split mpp parameters
out	out_list	list of output pipelines

Returns

Return_codes Precondition

• out_list array must contain at least num elements.

9. mpp_background()

int mpp_background (

mpp_t mpp,

mpp_params_t ∗ params, mpp_t ∗ out_mpp )

Put next elements processing in background. Parameters

in	mpp	input pipeline
in	params	new mpp parameters (exec_flag must be MPP_EXEC_PREEMPT)
out	out_mpp	output pipeline

Returns

Return_codes

10. mpp_element_update()

int mpp_element_update (

mpp_t mpp,

mpp_elem_handle_t elem_h, mpp_element_params_t ∗ params )

Update element parameters.

MCU Media Processing Pipeline 2. MPP Types 29**

Parameters

in	mpp	input pipeline
in	elem_h	element handle in the pipeline.
in	params	new element parameters

Returns

Return_codes

11. **mpp_start()**int mpp_start (

mpp_t mpp, int last )

Start pipeline.

When called with last=0, this function prepares the branch of the pipeline specified with mpp. When called with last!=0, this function starts the data flow of the pipeline.

Data flow should start after all the branches of the pipeline have been prepared.

Parameters

in	mpp	pipeline branch handle to start/prepare
in	last	if non-zero start pipeline processing. No further start call is possible thereafter.

Returns

Return_codes

12. **mpp_stop()**int mpp_stop (

mpp_t mpp )

Stop a branch of the pipeline.

This function stops the data processing and peripherals of a pipeline branch. Parameters

in	mpp	pipeline branch to stop

Returns

Return_codes

13. **mpp_stats_enable()**void mpp_stats_enable (

    mpp_stats_grp_t grp ) Enable statistics collection.

    This function enables statistics collection for a given group. Statistics collection is disabled by default after API initialization. Calling this function when stats are enabled has no effect.

    Parameters

in	grp	statistics group

Returns

14. **mpp_stats_disable()**void mpp_stats_disable (

    mpp_stats_grp_t grp ) Disable statistics collection.

    This function disables statistics collection for a given group. Calling this function when stats are disabled has no effect. This function is used to ensure stats are not updated while application tasks use the stats structures.

    Parameters

[in}	grp statistics group

15. **mpp_get_version()**char ∗ mpp_get_version (

void )

Get MPP version. Returns

pointer to the MPP version string

2. MPP Types

Data Structures

• union mpp_stats_t

• struct mpp_api_params_t

• struct mpp_params_t

• struct mpp_camera_params_t

• struct mpp_img_params_t

• struct mpp_display_params_t

• struct mpp_tensor_dims_t

• struct mpp_inference_tensor_params_t

• struct mpp_inference_cb_param_t

• union mpp_color_t

• struct mpp_labeled_rect_t

• struct mpp_area_t

• struct mpp_dims_t

• struct mpp_position_t

• struct mpp_inference_params_t

• struct mpp_element_params_t

• struct mpp_stats_t.api

• struct mpp_stats_t.mpp

• struct mpp_stats_t.elem

• struct mpp_color_t.rgb

• union mpp_element_params_t.unnamed5

• struct mpp_element_params_t.unnamed5.compose

• struct mpp_element_params_t.unnamed5.labels

• struct mpp_element_params_t.unnamed5.convert

• struct mpp_element_params_t.unnamed5.resize

• struct mpp_element_params_t.unnamed5.color_conv

• struct mpp_element_params_t.unnamed5.rotate

• struct mpp_element_params_t.unnamed5.test

• struct mpp_element_params_t.unnamed5.ml_inference

Macros

• #define MPP_INFERENCE_MAX_OUTPUTS

• #define MPP_INFERENCE_MAX_INPUTS

• #define MPP_INVALID

• #define MPP_EVENT_ALL

• #define MAX_TENSOR_DIMS

Typedefs

• typedef void ∗mpp_t

• typedef uintptr_t mpp_elem_handle_t

• typedef unsigned int mpp_evt_mask_t

• typedef int(∗inference_entry_point_t) (uint8_t ∗, uint8_t ∗, uint8_t ∗)

Enumerations

• enum mpp_evt_t {

  MPP_EVENT_INVALID , MPP_EVENT_INFERENCE_OUTPUT_READY , MPP_EVENT_INTERNAL_TEST_RESERVED , MPP_EVENT_NUM }

• enum mpp_exec_flag_t {

  MPP_EXEC_INHERIT ,

  MPP_EXEC_RC ,

  MPP_EXEC_PREEMPT }

• enum mpp_stats_grp_t {

  MPP_STATS_GRP_API , MPP_STATS_GRP_MPP , MPP_STATS_GRP_ELEMENT , MPP_STATS_GRP_NUM }

• enum mpp_rotate_degree_t {

  ROTATE_0 ,

  ROTATE_90 ,

  ROTATE_180 ,

  ROTATE_270 }

• enum mpp_flip_mode_t {

  FLIP_NONE ,

  FLIP_HORIZONTAL ,

  FLIP_VERTICAL ,

  FLIP_BOTH }

• enum mpp_convert_ops_t { MPP_CONVERT_NONE , MPP_CONVERT_ROTATE , MPP_CONVERT_SCALE , MPP_CONVERT_COLOR , MPP_CONVERT_CROP , MPP_CONVERT_OUT_WINDOW }

• enum mpp_pixel_format_t { MPP_PIXEL_ARGB ,

  MPP_PIXEL_BGRA ,

  MPP_PIXEL_RGBA ,

  MPP_PIXEL_RGB ,

  MPP_PIXEL_RGB565 ,

  MPP_PIXEL_BGR ,

  MPP_PIXEL_GRAY888 , MPP_PIXEL_GRAY888X , MPP_PIXEL_GRAY ,

  MPP_PIXEL_GRAY16 , MPP_PIXEL_YUV1P444 , MPP_PIXEL_VYUY1P422 , MPP_PIXEL_UYVY1P422 , MPP_PIXEL_YUYV , MPP_PIXEL_DEPTH16 , MPP_PIXEL_DEPTH8 , MPP_PIXEL_YUV420P , MPP_PIXEL_INVALID }

• enum mpp_element_id_t { MPP_ELEMENT_INVALID , MPP_ELEMENT_COMPOSE , MPP_ELEMENT_LABELED_RECTANGLE , MPP_ELEMENT_TEST , MPP_ELEMENT_INFERENCE ,

  MPP_ELEMENT_CONVERT , MPP_ELEMENT_NUM }

• enum mpp_tensor_type_t { MPP_TENSOR_TYPE_FLOAT32 , MPP_TENSOR_TYPE_UINT8 , MPP_TENSOR_TYPE_INT8 }

• enum mpp_tensor_order_t { MPP_TENSOR_ORDER_UNKNOWN , MPP_TENSOR_ORDER_NHWC , MPP_TENSOR_ORDER_NCHW }

• enum mpp_inference_type_t { MPP_INFERENCE_TYPE_TFLITE }

1. Detailed Description

This section provides the detailed documentation for the MCU Media Processing Pipeline types.

2. Data Structure Documentation

3. union mpp_stats_t Data Fields

struct mpp_stats_t.api	api	Global execution performance counters.
struct mpp_stats_t.mpp	mpp	Pipeline execution performance counters.
struct mpp_stats_t.elem	elem	Element execution performance counters.

2. struct mpp_api_params_t Data Fields

mpp_stats_t ∗	stats	API stats.
unsigned int	rc_cycle_min	minimum cycle duration for RC tasks (ms), 0: sets default value
unsigned int	rc_cycle_inc	time increment for RC tasks (ms), 0: sets default value
int	pipeline_task_max_prio	pipeline tasks maximum priority.

3. struct mpp_params_t Pipeline creation parameters.

   Data Fields

• int(∗evt_callback_f )(mpp_t mpp, mpp_evt_t evt, void ∗evt_data, void ∗user_data)

• mpp_evt_mask_t mask

• mpp_exec_flag_t exec_flag

• void ∗cb_userdata

• mpp_stats_t ∗stats

4. struct mpp_camera_params_t

Camera parameters. Data Fields

int	height	buffer height
int	width	buffer width
mpp_pixel_format_t	format	pixel format
int	fps	frames per second
bool	stripe	stripe mode

5. struct mpp_img_params_t

Static image parameters. Data Fields

int	height	buffer height
int	width	buffer width
mpp_pixel_format_t	format	pixel format
bool	stripe	stripe mode

6. struct mpp_display_params_t

Display parameters. Data Fields

int	height	buffer resolution: setting to 0 will default to panel physical resolution
int	width	buffer resolution: setting to 0 will default to panel physical resolution
int	pitch	buffer resolution: setting to 0 will default to panel physical resolution
int	left	active rect: setting to 0 will default to fullscreen
int	top	active rect: setting to 0 will default to fullscreen
int	right	active rect: setting to 0 will default to fullscreen
int	bottom	active rect: setting to 0 will default to fullscreen
mpp_rotate_degree_t	rotate	rotate degree
mpp_pixel_format_t	format	pixel format
bool	stripe	stripe mode

7. struct mpp_tensor_dims_t Inference tensor dimensions.

   Data Fields

uint32_t	size
uint32_t	data[MAX_TENSOR_DIMS]

8. struct mpp_inference_tensor_params_t

tensor parameters Data Fields

const uint8_t ∗	data	data address
mpp_tensor_dims_t	dims	tensor data dimensions
mpp_tensor_type_t	type	tensor data type

9. struct mpp_inference_cb_param_t

Inference callback parameters. Data Fields

void ∗	user_data	callback will pass this pointer
mpp_inference_tensor_params_t ∗	out_tensors[MPP_INFERENCE_MAX	_OUTPUTSoutput tensors] parameters
int	inference_time_ms	inference run time measurement - output to user
mpp_inference_type_t	inference_type	type of the inference

10. union mpp_color_t

mpp color encoding Data Fields

uint32_t	raw	Raw color.
struct mpp_color_t.rgb	rgb	rgb color values RGB color

11. struct mpp_labeled_rect_t

mpp labeled rectangle element structure Data Fields

uint8_t	label[64]	label to print

Data Fields

uint16_t	clear	clear rectangle
uint16_t	line_width	rectangle line thickness
mpp_color_t	line_color	rectangle line color
uint16_t	top	rectangle top position
uint16_t	left	rectangle left position
uint16_t	bottom	rectangle bottom position
uint16_t	right	rectangle right position
uint16_t	tag	labeled rectangle tag
uint16_t	reserved	pad for 32 bits alignment
bool	stripe	stripe mode

12. struct mpp_area_t

Image area coordinates. Data Fields

int	top
int	left
int	bottom
int	right

13. struct mpp_dims_t

Image dimensions. Data Fields

unsigned int	width
unsigned int	height

14. struct mpp_position_t

Image position. Data Fields

int	top
int	left

15. struct mpp_inference_params_t

Model parameters. Data Fields

uint64_t	constant_weight_MemSize	model constant weights memory size
uint64_t	mutable_weight_MemSize	Defines the amount of memory required both input & output data buffers.
uint64_t	activations_MemSize	Size of scratch memory used for intermediate computations needed by the model.
int	num_inputs	model’s number of inputs
int	num_outputs	model’s number of outputs
uint64_t	inputs_offsets[MPP_INFERENCE_MAX_IN	PUTSoffset]of each input
uint64_t	outputs_offsets[MPP_INFERENCE_MAX_O	UTPUTSoffset ofeach] output
inference_entry_point_t	model_entry_point	function called to perform the inference
mpp_tensor_type_t	model_input_tensors_type	type of input buffer

16. struct mpp_element_params_t

Processing element parameters. Data Fields

union mpp_element_params_t.unnamed5	__unnamed__
mpp_stats_t ∗	stats

17. struct mpp_stats_t.api Data Fields

unsigned int	rc_cycle	run-to-completion (RC) cycle duration (ms)
unsigned int	rc_cycle_max	run-to-completion work deadline (ms)
unsigned int	pr_slot	available slot for preemptable (PR) work (ms)
unsigned int	pr_rounds	number of RC cycles required to complete one PR cycle (ms)
unsigned int	app_slot	remaining time for application (ms)

18. struct mpp_stats_t.mpp Data Fields

mpp_t	mpp
unsigned int	mpp_exec_time	pipeline execution time (ms)

19. struct mpp_stats_t.elem Data Fields

mpp_elem_handle_t	hnd
unsigned int	elem_exec_time	element execution time (ms)

20. struct mpp_color_t.rgb

rgb color values Data Fields

uint8_t	R	Red byte.
uint8_t	G	Green byte.
uint8_t	B	Blue byte.
uint8_t	pad	padding byte

21. union mpp_element_params_t.__unnamed5__ Data Fields

struct mpp_element_params_t.unnamed5.compose	compose	Compose element’s parameters - NOT IMPLEMENTED YET.
struct mpp_element_params_t.unnamed5.labels	labels	Labeled Rectangle element’s parameters.
struct mpp_element_params_t.unnamed5.convert	convert	Convert element’s parameters.
struct mpp_element_params_t.unnamed5.resize	resize	Resize element’s parameters.
struct mpp_element_params_t.unnamed5.color_conv	color_conv	Color convert element’s parameters.
struct mpp_element_params_t.unnamed5.rotate	rotate	Rotate element’s parameters.
struct mpp_element_params_t.unnamed5.test	test	Test element’s parameters.
struct mpp_element_params_t.unnamed5.ml_inferen	ml_inference ce	ML inference element’s parameters.

22. struct mpp_element_params_t.__unnamed5__.compose

Compose element’s parameters - NOT IMPLEMENTED YET. Data Fields

float	a
float	b

23. struct mpp_element_params_t.__unnamed5__.labels

Labeled Rectangle element’s parameters. Data Fields

uint32_t	max_count	maximum number of rectangles
uint32_t	detected_count	detected rectangles
mpp_labeled_rect_t ∗	rectangles	array of rectangle data

24. struct mpp_element_params_t.__unnamed5__.convert

Convert element’s parameters. Data Fields

mpp_dims_t	out_buf	output buffer dimensions
mpp_pixel_format_t	pixel_format	new pixel format
mpp_rotate_degree_t	angle	rotation angle
mpp_flip_mode_t	flip	flip mode
mpp_area_t	crop	input crop area
mpp_position_t	out_window	output window position
mpp_dims_t	scale	scaling dimensions
mpp_convert_ops_t	ops	operation selector mask
const char ∗	dev_name	device name used for graphics
bool	stripe_in	input stripe mode
bool	stripe_out	output stripe mode

25. struct mpp_element_params_t.__unnamed5__.resize

Resize element’s parameters. Data Fields

unsigned int	width
unsigned int	height

26. struct mpp_element_params_t.__unnamed5__.color_conv

Color convert element’s parameters. Data Fields

mpp_pixel_format_t	pixel_format

27. struct mpp_element_params_t.__unnamed5__.rotate

Rotate element’s parameters. Data Fields

mpp_rotate_degree_t	angle

28. struct mpp_element_params_t.__unnamed5__.test

Test element’s parameters. Data Fields

_Bool	inp
unsigned int	width
unsigned int	height
mpp_pixel_format_t	format

29. struct mpp_element_params_t.__unnamed5__.ml_inference

ML inference element’s parameters. Data Fields

const void ∗	model_data	pointer to model binary
mpp_inference_type_t	type	inference type
int	model_size	model binary size
float	model_input_mean	model ‘mean’ of input values, used for normalization
float	model_input_std	model ‘standard deviation’ of input values, used for normalization
mpp_tensor_order_t	tensor_order	model input tensor component order
mpp_inference_params_t	inference_params	model specific parameters used by the inference

3. Macro Definition Documentation

4. MPP_INFERENCE_MAX_OUTPUTS

#define MPP_INFERENCE_MAX_OUTPUTS

Maximum number of inference inputs and outputs. Maximum number of outputs supported by the pipeline

2. MPP_INFERENCE_MAX_INPUTS

#define MPP_INFERENCE_MAX_INPUTS

Maximum number of inputs supported by the pipeline.

3. MPP_INVALID

#define MPP_INVALID Invalid pipeline handle.

4. MPP_EVENT_ALL

#define MPP_EVENT_ALL

Bit mask to receive all Events.

5. MAX_TENSOR_DIMS

#define MAX_TENSOR_DIMS

Maximum number of dimensions for tensors.

4. Typedef Documentation

5. mpp_t

typedef void∗ mpp_t Pipeline handle type.

2. mpp_elem_handle_t

typedef uintptr_t mpp_elem_handle_t Element handle type.

3. mpp_evt_mask_t

typedef unsigned int mpp_evt_mask_t Event mask for pipeline creation.

4. inference_entry_point_t

typedef int(∗ inference_entry_point_t) (uint8_t ∗, uint8_t ∗, uint8_t ∗) Bundle inference function type.

5. Enumeration Type Documentation

6. mpp_evt_t

enum mpp_evt_t

Pipeline generated events.

Enumerator

MPP_EVENT_INVALID	invalid event
MPP_EVENT_INFERENCE_OUTPUT_READY	inference out is ready
MPP_EVENT_INTERNAL_TEST_RESERVED	INTERNAL: DO NOT USE.
MPP_EVENT_NUM	DO NOT USE.

2. mpp_exec_flag_t

enum mpp_exec_flag_t Execution parameters.

These parameters control the execution of the elements of an mpp.

The “mpps” created using the flag MPP_EXEC_RC are guaranteed to run up to the completion of all processing elements, while not being preempted by other “mpps”.

The “mpps” created using the flag MPP_EXEC_PREEMPT are preempted after a given time interval by “mpps” that will run-to-completion again.

The “mpps” created with the MPP_EXEC_INHERIT flag inherit the same execution flag as the parent(s) in case of split operation.

Note: It is not possible to request run-to-completion execution when spliting preemptable-execution “mpps”.

Enumerator

MPP_EXEC_INHERIT	inherit from parent(s)
MPP_EXEC_RC	run-to-completion
MPP_EXEC_PREEMPT	preemptable

3. mpp_stats_grp_t

enum mpp_stats_grp_t Enumerator

MPP_STATS_GRP_API	API (global) stats.
MPP_STATS_GRP_MPP	mpp_t stats
MPP_STATS_GRP_ELEMENT	element stats
MPP_STATS_GRP_NUM	number of groups

4. mpp_rotate_degree_t

enum mpp_rotate_degree_t Rotation value.

Enumerator

ROTATE_0	0 degree
ROTATE_90	90 degrees
ROTATE_180	180 degrees
ROTATE_270	270 degrees

5. mpp_flip_mode_t

enum mpp_flip_mode_t Flip type. Enumerator

FLIP_NONE	no flip
FLIP_HORIZONTAL	horizontal flip
FLIP_VERTICAL	vertical flip
FLIP_BOTH	vertical and horizontal flip

6. mpp_convert_ops_t

enum mpp_convert_ops_t

The convert operations selector flags. Enumerator

MPP_CONVERT_NONE	no frame conversion
MPP_CONVERT_ROTATE	frame rotation and flip
MPP_CONVERT_SCALE	scaling from input_frame toward output window
MPP_CONVERT_COLOR	frame color conversion
MPP_CONVERT_CROP	input frame crop
MPP_CONVERT_OUT_WINDOW	output window

7. mpp_pixel_format_t

enum mpp_pixel_format_t Pixel format. Enumerator

MPP_PIXEL_ARGB	ARGB 32 bits.
MPP_PIXEL_BGRA	BGRA 32 bits.
MPP_PIXEL_RGBA	RGBA 32 bits.

Enumerator

MPP_PIXEL_RGB	RGB 24 bits.
MPP_PIXEL_RGB565	RGB 16 bits.
MPP_PIXEL_BGR	BGR 24 bits.
MPP_PIXEL_GRAY888	gray 3x8 bits
MPP_PIXEL_GRAY888X	gray 3x8 bits +8 unused bits
MPP_PIXEL_GRAY	gray 8 bits
MPP_PIXEL_GRAY16	gray 16 bits
MPP_PIXEL_YUV1P444	YUVX interleaved 4:4:4.
MPP_PIXEL_VYUY1P422	VYUY interleaved 4:2:2.
MPP_PIXEL_UYVY1P422	UYVY interleaved 4:2:2.
MPP_PIXEL_YUYV	YUYV interleaved 4:2:2.
MPP_PIXEL_DEPTH16	depth 16 bits
MPP_PIXEL_DEPTH8	depth 8 bits
MPP_PIXEL_YUV420P	YUV planar 4:2:0.
MPP_PIXEL_INVALID	invalid pixel format

8. mpp_element_id_t

enum mpp_element_id_t Processing element ids. Enumerator

MPP_ELEMENT_INVALID	Invalid element.
MPP_ELEMENT_COMPOSE	Image composition - NOT IMPLEMENTED YET.
MPP_ELEMENT_LABELED_RECTANGLE	Labeled rectangle - bounding box.
MPP_ELEMENT_TEST	Test inplace element - NOT FOR USE.
MPP_ELEMENT_INFERENCE	Inference engine.
MPP_ELEMENT_CONVERT	Image conversion: resolution, orientation, color format.
MPP_ELEMENT_NUM	DO NOT USE.

9. mpp_tensor_type_t

enum mpp_tensor_type_t Inference tensor type. Enumerator

MPP_TENSOR_TYPE_FLOAT32	floating point 32 bits
MPP_TENSOR_TYPE_UINT8	unsigned integer 8 bits
MPP_TENSOR_TYPE_INT8	signed integer 8 bits

MCU Media Processing Pipeline

10. mpp_tensor_order_t

enum mpp_tensor_order_t Inference input tensor order. Enumerator

MPP_TENSOR_ORDER_UNKNOWN	order not set
MPP_TENSOR_ORDER_NHWC	order: Batch, Height, Width, Channels
MPP_TENSOR_ORDER_NCHW	order: Batch, Channels, Height, Width

11. mpp_inference_type_t

enum mpp_inference_type_t Inference type. Enumerator

MPP_INFERENCE_TYPE_TFLITE	TensorFlow-Lite.

3. Return_codes

Macros

• #define MPP_SUCCESS

• #define MPP_ERROR

• #define MPP_INVALID_ELEM

• #define MPP_INVALID_PARAM

• #define MPP_ERR_ALLOC_MUTEX

• #define MPP_INVALID_MUTEX

• #define MPP_MUTEX_TIMEOUT

• #define MPP_MUTEX_ERROR

• #define MPP_MALLOC_ERROR

1. Detailed Description

MPP APIs return status definitions.

2. Macro Definition Documentation

3. MPP_SUCCESS

#define MPP_SUCCESS Success return code.

3.3 Return_codes 27

2. MPP_ERROR

#define MPP_ERROR

A generic error occured.

3. MPP_INVALID_ELEM

#define MPP_INVALID_ELEM Invalid element provided.

4. MPP_INVALID_PARAM

#define MPP_INVALID_PARAM Invalid parameter provided.

5. MPP_ERR_ALLOC_MUTEX

#define MPP_ERR_ALLOC_MUTEX Error occured while allocating mutex.

6. MPP_INVALID_MUTEX

#define MPP_INVALID_MUTEX Invalid mutex provided.

7. MPP_MUTEX_TIMEOUT

#define MPP_MUTEX_TIMEOUT Mutex timeout occured.

8. MPP_MUTEX_ERROR

#define MPP_MUTEX_ERROR Mutex error occured.

9. MPP_MALLOC_ERROR

#define MPP_MALLOC_ERROR Memory allocation error occured.