ELocator::GenerateAnchors

Generates anchors based on the objects in the dataset or a formal specification.
For the version that takes a dataset, the properties ELocator and ELocator must be set.

Namespace: Euresys::Open_eVision::EasyDeepLearning

[C++]

std::vector<Euresys::Open_eVision::ESize> GenerateAnchors(
   const EClassificationDataset& dataset
)

std::vector<Euresys::Open_eVision::ESize> GenerateAnchors(
   float minDimension,
   float maxDimension,
   int numSubScales,
   std::vector<float> aspectRatios
)

Parameters

dataset

Dataset

minDimension

Minimum dimension of objects (minimum value: 16)

maxDimension

Maximum dimension of objects.

numSubScales

Number of sub-scales to produce for each scale covered by the given dimensions.

aspectRatios

Aspect ratios to generate at each scale. The aspect ratios are the ratios between the width and height of the anchor. Recommended value: {1.0f, 0.5f, 2.0f}.

Remarks

The dimension of an object corresponds to the square root of its area.

ELocator.GenerateAnchors

Generates anchors based on the objects in the dataset or a formal specification.
For the version that takes a dataset, the properties ELocator and ELocator must be set.

Namespace: Euresys.Open_eVision.EasyDeepLearning

[C#]

Euresys.Open_eVision.ESize[] GenerateAnchors(
   Euresys.Open_eVision.EasyDeepLearning.EClassificationDataset dataset
)

Euresys.Open_eVision.ESize[] GenerateAnchors(
   float minDimension,
   float maxDimension,
   int numSubScales,
   float[] aspectRatios
)

Parameters

dataset

Dataset

minDimension

Minimum dimension of objects (minimum value: 16)

maxDimension

Maximum dimension of objects.

numSubScales

Number of sub-scales to produce for each scale covered by the given dimensions.

aspectRatios

Aspect ratios to generate at each scale. The aspect ratios are the ratios between the width and height of the anchor. Recommended value: {1.0f, 0.5f, 2.0f}.

Remarks

The dimension of an object corresponds to the square root of its area.