Enums

Details

class GstAnalytics.ModelInfoTensorDirection(value)

Bases: GLib.Enum

New in version 1.28.

UNKNOWN = 0

Tensor location is unknown

INPUT = 1

Input tensor

OUTPUT = 2

Output tensor

class GstAnalytics.SegmentationType(value)

Bases: GLib.Enum

Enum value describing supported segmentation type

New in version 1.26.

SEMANTIC = 0

Segmentation where the belonging of each pixel to a class of objects is identified.

INSTANCE = 1

Segmentation where the belonging of each pixel to instance of an object is identified.

class GstAnalytics.TensorDataType(value)

Bases: GLib.Enum

Describe the type of data contain in the tensor.

New in version 1.26.

INT4 = 0

signed 4 bit integer tensor data

INT8 = 1

signed 8 bit integer tensor data

FLOAT16 = 10

16 bit floating point tensor data

FLOAT32 = 11

32 bit floating point tensor data

FLOAT64 = 12

64 bit floating point tensor data

BFLOAT16 = 13

“brain” 16 bit floating point tensor data

STRING = 14

UTF-8 string

New in version 1.28.

BOOL = 15

A boolean value stored in 1 byte.

New in version 1.28.

COMPLEX64 = 16

A 64-bit complex number stored in 2 32-bit values.

New in version 1.28.

COMPLEX128 = 17

A 128-bit complex number stored in 2 64-bit values.

New in version 1.28.

FLOAT8E4M3FN = 18

A non-IEEE 8-bit floating point format with 4 exponent bits and 3 mantissa bits, with NaN and no infinite values (FN). See this paper for more details

New in version 1.28.

FLOAT8E4M3FNUZ = 19

A non-IEEE 8-bit floating point format with 4 exponent bits and 3 mantissa bits, with NaN, no infinite values (FN) and no negative zero (UZ). See this paper for more details

New in version 1.28.

INT16 = 2

signed 16 bit integer tensor data

FLOAT8E5M2 = 20

A non-IEEE 8-bit floating point format with 5 exponent bits and 2 mantissa bits. See this paper for more details

New in version 1.28.

FLOAT8E5M2FNUZ = 21

A non-IEEE 8-bit floating point format with 5 exponent bits and 2 mantissa bits, with NaN, no infinite values (FN) and no negative zero (UZ). See this paper for more details

New in version 1.28.

INT32 = 3

signed 32 bit integer tensor data

INT64 = 4

signed 64 bit integer tensor data

UINT4 = 5

unsigned 4 bit integer tensor data

UINT8 = 6

unsigned 8 bit integer tensor data

UINT16 = 7

unsigned 16 bit integer tensor data

UINT32 = 8

unsigned 32 bit integer tensor data

UINT64 = 9

unsigned 64 bit integer tensor data

class GstAnalytics.TensorDimOrder(value)

Bases: GLib.Enum

Indicate to read tensor from memory in row-major or column-major order.

New in version 1.26.

ROW_MAJOR = 0

elements along a row are consecutive in memory

COL_MAJOR = 1

elements along a column are consecutive in memory

class GstAnalytics.TensorLayout(value)

Bases: GLib.Enum

Indicate tensor storage in memory.

New in version 1.26.

TENSOR_LAYOUT_CONTIGUOUS = 0

indicate the tensor is stored in a dense format in memory