loss_giou: Implements the GIoU loss function.

In tfaddons: Interface to 'TensorFlow SIG Addons'

Description

GIoU loss was first introduced in the [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://giou.stanford.edu/GIoU.pdf). GIoU is an enhancement for models which use IoU in object detection.

Usage

loss_giou(
  mode = "giou",
  reduction = tf$keras$losses$Reduction$AUTO,
  name = "giou_loss"
)

Arguments

mode	one of ['giou', 'iou'], decided to calculate GIoU or IoU loss.
reduction	(Optional) Type of tf$keras$losses$Reduction to apply. Default value is SUM_OVER_BATCH_SIZE.
name	A name for the operation (optional).

Value

GIoU loss float 'Tensor'.

tfaddons documentation built on July 2, 2020, 2:12 a.m.