Main Content

Compute focal cross-entropy loss

computes the focal cross-entropy between network predictions and target values for
single-label and multi-label classification tasks. The classes are mutually-exclusive
classes. The focal cross-entropy loss weights towards poorly classified training samples and
ignores well-classified samples. The focal cross-entropy loss is computed as the average
logarithmic loss divided by number of non-zero targets.`dlY`

= focalCrossEntropy(`dlX`

,`targets`

)

specifies options using one or more name-value pair arguments in addition to the input
arguments in previous syntaxes. For example,
`dlY`

= focalCrossEntropy(___,`Name,Value`

)`'TargetCategories','independent'`

computes the cross-entropy loss for a
multi-label classification task.

`focalLossLayer`

| `crossentropy`

(Deep Learning Toolbox) | `mse`

(Deep Learning Toolbox) | `sigmoid`

(Deep Learning Toolbox) | `softmax`

(Deep Learning Toolbox)

- Lidar 3-D Object Detection Using PointPillars Deep Learning (Lidar Toolbox)