vision_ops

package
v1.11.0-0.1.5 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Apr 2, 2023 License: MIT Imports: 2 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

func BoxArea

func BoxArea(boxes *torch.Tensor) *torch.Tensor

Compute the area of a set of bounding boxes. boxes are expected to be in (N, 4, ...) (xmin, ymin, xmax, ymax) format with 0 <= xmin < xmax and 0 <= ymin < ymax.

func ClipBoxesToImage

func ClipBoxesToImage(boxes *torch.Tensor, height, width int64) *torch.Tensor

Clip boxes so that they lie inside an image of size size. Boxes are expected to have shape (N, 4, ...) and be in (xmin, ymin, xmax, ymax) format.

func ClipBoxesToImage_

func ClipBoxesToImage_(boxes *torch.Tensor, height, width int64) *torch.Tensor

In-place version of ClipBoxesToImage.

func FindBoxesInSizeRange

func FindBoxesInSizeRange(
	boxes *torch.Tensor,
	widthMin, heightMin, widthMax, heightMax int64,
) *torch.Tensor

Find boxes within a particular inclusive minimum and maximum bound. Boxes are expected to be shaped as (N, 4, ...) in (xmin, ymin, xmax, ymax) format.

func FindLargeBoxes

func FindLargeBoxes(boxes *torch.Tensor, widthMin, heightMin int64) *torch.Tensor

Find boxes that are larger than or equal to a given size. Boxes are expected to be shaped as (N, 4, ...) in (xmin, ymin, xmax, ymax) format.

func FindSmallBoxes

func FindSmallBoxes(boxes *torch.Tensor, widthMax, heightMax int64) *torch.Tensor

Find boxes that are smaller than or equal to a given size. Boxes are expected to be shaped as (N, 4, ...) in (xmin, ymin, xmax, ymax) format.

Types

This section is empty.

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL