gstgva.tensor.Tensor Class Reference

This class represents tensor - map-like storage for inference result information, such as output blob description (output layer dims, layout, rank, precision, etc.), inference result in a raw and interpreted forms. More...

Classes
class	LAYOUT
	This enum describes model layer layout. More...
class	PRECISION
	This enum describes model layer precision. More...

Public Member Functions
List[int]	dims (self)
	Get inference result blob dimensions info. More...
PRECISION	precision (self)
	Get inference results blob precision. More...
LAYOUT	layout (self)
	Get inference result blob layout. More...
numpy.ndarray	data (self)
	Get raw inference result blob data. More...
str	name (self)
	Get name as a string. More...
str	model_name (self)
	Get model name which was used for inference. More...
str	layer_name (self)
	Get inference result blob layer name. More...
float	confidence (self)
	Get confidence of inference result. More...
str	label (self)
	Get label. More...
int	object_id (self)
	Get object id. More...
str	format (self)
	Get format. More...
List[str]	fields (self)
	Get list of fields contained in Tensor instance. More...
def	__getitem__ (self, key)
	Get item by the field name. More...
int	__len__ (self)
	Get number of fields contained in Tensor instance. More...
def	__iter__ (self)
	Iterable by all Tensor fields. More...
str	__repr__ (self)
	Return string represenation of the Tensor instance. More...
None	__delitem__ (self, str key)
	Remove item by the field name. More...
int	label_id (self)
	Get label id. More...
str	element_id (self)
	Get inference-id property value of GVA element from which this Tensor came. More...
None	set_name (self, str name)
	Set Tensor instance's name.
str	layout_as_string (self)
	Get inference result blob layout as a string. More...
str	precision_as_string (self)
	Get inference results blob precision as a string. More...
None	set_label (self, str label)
	Set label. More...
bool	has_field (self, str field_name)
	Check if Tensor instance has field. More...
bool	is_detection (self)
	Check if this Tensor is detection Tensor (contains detection results) More...
def	set_labels (self, List[str] labels)
	Set list of labels used as lookup table for label_id. More...
def	__init__ (self, ctypes.c_void_p structure)
	Construct Tensor instance from C-style GstStructure. More...
None	__setitem__ (self, str key, item)
	Set item to Tensor. More...

Detailed Description

This class represents tensor - map-like storage for inference result information, such as output blob description (output layer dims, layout, rank, precision, etc.), inference result in a raw and interpreted forms.

Tensor is based on GstStructure and, in general, can contain arbitrary (user-defined) fields of simplest data types, like integers, floats & strings. Tensor can contain only raw inference result (such Tensor is produced by gvainference in Gstreamer pipeline), detection result (such Tensor is produced by gvadetect in Gstreamer pipeline and it's called detection Tensor), or both raw & interpreted inference results (such Tensor is produced by gvaclassify in Gstreamer pipeline). Tensors can be created and used on their own, or they can be created within RegionOfInterest or VideoFrame instances. Usually, in Gstreamer pipeline with GVA elements (gvadetect, gvainference, gvaclassify) Tensor objects will be available for access and modification from RegionOfInterest and VideoFrame instances

Constructor & Destructor Documentation

__init__()

def gstgva.tensor.Tensor.__init__	(		self,
		ctypes.c_void_p	structure
	)

Construct Tensor instance from C-style GstStructure.

Parameters

structure

C-style pointer to GstStructure to create Tensor instance from. There are much simpler ways for creating and obtaining Tensor instances - see RegionOfInterest and VideoFrame classes

Member Function Documentation

__delitem__()

None gstgva.tensor.Tensor.__delitem__	(		self,
		str	key
	)

Remove item by the field name.

Parameters

key	Field name

__getitem__()

def gstgva.tensor.Tensor.__getitem__	(		self,
			key
	)

Get item by the field name.

Parameters

key	Field name

Returns

Item, None if failed to get

__iter__()

def gstgva.tensor.Tensor.__iter__

(

self

)

Iterable by all Tensor fields.

Returns

Generator for all Tensor fields

__len__()

int gstgva.tensor.Tensor.__len__

(

self

)

Get number of fields contained in Tensor instance.

Returns

Number of fields contained in Tensor instance

__repr__()

str gstgva.tensor.Tensor.__repr__

(

self

)

Return string represenation of the Tensor instance.

Returns

String of field names and values

__setitem__()

None gstgva.tensor.Tensor.__setitem__	(		self,
		str	key,
			item
	)

Set item to Tensor.

It can be one of the following types: string, int, float.

Parameters

key	Name of new field
item	Item

confidence()

float gstgva.tensor.Tensor.confidence

(

self

)

Get confidence of inference result.

Returns

confidence of inference result as a float, None if failed to get

data()

numpy.ndarray gstgva.tensor.Tensor.data

(

self

)

Get raw inference result blob data.

Returns

numpy.ndarray of values representing raw inference data, None if data can't be read

dims()

List[int] gstgva.tensor.Tensor.dims

(

self

)

Get inference result blob dimensions info.

Returns

list of dimensions

element_id()

str gstgva.tensor.Tensor.element_id

(

self

)

Get inference-id property value of GVA element from which this Tensor came.

Returns

inference-id property value of GVA element from which this Tensor came, None if failed to get

fields()

List[str] gstgva.tensor.Tensor.fields

(

self

)

Get list of fields contained in Tensor instance.

Returns

List of fields contained in Tensor instance

format()

str gstgva.tensor.Tensor.format

(

self

)

Get format.

Returns

format as a string, None if failed to get

has_field()

bool gstgva.tensor.Tensor.has_field	(		self,
		str	field_name
	)

Check if Tensor instance has field.

Parameters

field_name

field name

Returns

True if field with this name is found, False otherwise

is_detection()

bool gstgva.tensor.Tensor.is_detection

(

self

)

Check if this Tensor is detection Tensor (contains detection results)

Returns

True if tensor contains detection results, False otherwise

label()

str gstgva.tensor.Tensor.label

(

self

)

Get label.

This label is set for Tensor instances produced by gvaclassify element. It will raise exception if called for detection Tensor. To get detection class label, use RegionOfInterest.label

Returns

label as a string, None if failed to get

label_id()

int gstgva.tensor.Tensor.label_id

(

self

)

Get label id.

Returns

label id as an int, None if failed to get

layer_name()

str gstgva.tensor.Tensor.layer_name

(

self

)

Get inference result blob layer name.

Returns

layer name as a string, None if failed to get

layout()

LAYOUT gstgva.tensor.Tensor.layout

(

self

)

Get inference result blob layout.

Returns

LAYOUT, LAYOUT.ANY if can't be read

layout_as_string()

str gstgva.tensor.Tensor.layout_as_string

(

self

)

Get inference result blob layout as a string.

Returns

layout as a string, "ANY" if can't be read

model_name()

str gstgva.tensor.Tensor.model_name

(

self

)

Get model name which was used for inference.

Returns

model name as a string, None if failed to get

name()

str gstgva.tensor.Tensor.name

(

self

)

Get name as a string.

Returns

Tensor instance's name

object_id()

int gstgva.tensor.Tensor.object_id

(

self

)

Get object id.

Returns

object id as an int, None if failed to get

precision()

PRECISION gstgva.tensor.Tensor.precision

(

self

)

Get inference results blob precision.

Returns

PRECISION, PRECISION.ANY if can't be read

precision_as_string()

str gstgva.tensor.Tensor.precision_as_string

(

self

)

Get inference results blob precision as a string.

Returns

precision as a string, "UNSPECIFIED" if can't be read

set_label()

None gstgva.tensor.Tensor.set_label	(		self,
		str	label
	)

Set label.

It will raise exception if called for detection Tensor

Parameters

label

label name as a string

set_labels()

def gstgva.tensor.Tensor.set_labels	(		self,
		List[str]	labels
	)

Set list of labels used as lookup table for label_id.

Deprecated:

This function and result of calling it should never be used. User application must not expect Tensor to contain labels

Returns

Object itself

---

The documentation for this class was generated from the following file:

• /home/python/gstgva/tensor.py