Softmax

class dragon.vm.caffe.core.layers.Softmax(layer_param)[source]

Apply the softmax function.

The Softmax function is defined as:

\[\text{Softmax}(x_{i}) = \frac{\exp(x_{i})}{\sum_{j} \exp(x_{j})} \]

Examples:

layer {
  type: "Softmax"
  bottom: "cls_score"
  top: "cls_prob"
  softmax_param {
    axis: 1
  }
}