TensorParameters Class Reference

Class containing the parameters of a Tensor. More...

Functions
Resolution	target_size (self)
	Target size for the input image (Width, Height). More...
TENSOR_PIXEL_TYPE	pixel_type (self)
	Pixel data type for the Tensor elements. More...
list[float]	mean (self)
	Normalization parameter: Mean. More...
list[float]	std (self)
	Normalization parameter: Standard Deviation. More...
bool	stretch (self)
	If true, stretches the image to target_size. More...
list[float]	scale (self)
	Scale factor applied to the pixel values before normalization.
TENSOR_COLOR_FORMAT	color_format (self)
	Desired color format for the output Tensor.
TENSOR_LAYOUT	layout (self)
	Desired memory layout for the output Tensor. More...
int	batch_size (self)
	Number of images in the batch.
MEM	memory_type (self)
	Where the Tensor should be stored (CPU or GPU).
int	get_pixel_size (self)
	Returns the size in bytes of a single pixel element based on pixel_type. More...
int	get_requested_channels (self)
	Returns the number of channels associated with the color_format. More...

Detailed Description

Class containing the parameters of a Tensor.

Functions

target_size()

Resolution target_size

(

self

)

Target size for the input image (Width, Height).

Default: (640,640).

pixel_type()

TENSOR_PIXEL_TYPE pixel_type

(

self

)

Pixel data type for the Tensor elements.

Note

Specifies the underlying data type: UCHAR (8-bit), FLOAT (32-bit), or HALF (16-bit). Default: TENSOR_PIXEL_TYPE.FLOAT.

mean()

list[float] mean

(

self

)

Normalization parameter: Mean.

Note

Pixel = (Pixel * Scale - Mean) / Std. Default: ImageNet Standard [0.485, 0.456, 0.406].

std()

list[float] std

(

self

)

Normalization parameter: Standard Deviation.

Note

Pixel = (Pixel * Scale - Mean) / Std. Default: ImageNet Standard [0.229, 0.224, 0.225].

stretch()

bool stretch

(

self

)

If true, stretches the image to target_size.

If false, keeps aspect ratio and applies letterboxing (padding).

layout()

TENSOR_LAYOUT layout

(

self

)

Desired memory layout for the output Tensor.

Note

NCHW (planar) is common for PyTorch models.

NHWC (interleaved) is common for TensorFlow models.

get_pixel_size()

int get_pixel_size

(

self

)

Returns the size in bytes of a single pixel element based on pixel_type.

Returns

The size in bytes (1 for UCHAR, 2 for HALF, 4 for FLOAT).

get_requested_channels()

int get_requested_channels

(

self

)

Returns the number of channels associated with the color_format.

Returns

The number of channels.