Class CosineProximity
Cosine Proximity loss function computes the cosine proximity between predicted value and actual value. It is same as Cosine Similarity, which is a measure of similarity between two non-zero vectors of an inner product space that measures the cosine of the angle between them. In this case, note that unit vectors are maximally “similar” if they’re parallel and maximally “dissimilar” if they’re orthogonal (perpendicular). This is analogous to the cosine, which is unity (maximum value) when the segments subtend a zero angle and zero (uncorrelated) when the segments are perpendicular.
Inherited Members
Namespace: SiaNet.Losses
Assembly: SiaNet.dll
Syntax
public class CosineProximity : BaseLoss
Constructors
| Improve this Doc View SourceCosineProximity()
Initializes a new instance of the CosineProximity class.
Declaration
public CosineProximity()
Methods
| Improve this Doc View SourceBackward(Tensor, Tensor)
Backpropagation method to calculate gradient of the loss function
Declaration
public override Tensor Backward(Tensor preds, Tensor labels)
Parameters
Type | Name | Description |
---|---|---|
Tensor | preds | The predicted result. |
Tensor | labels | The true result. |
Returns
Type | Description |
---|---|
Tensor |
Overrides
| Improve this Doc View SourceForward(Tensor, Tensor)
Forwards the inputs and calculate the loss.
Declaration
public override Tensor Forward(Tensor preds, Tensor labels)
Parameters
Type | Name | Description |
---|---|---|
Tensor | preds | The predicted result. |
Tensor | labels | The true result. |
Returns
Type | Description |
---|---|
Tensor |