SoftmaxWithLoss

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

Compute the softmax cross entropy with sparse labels.

The CrossEntropy function is defined as:

\[\text{CrossEntropy}(p_{t}) = -\log(p_{t}) \]

Examples:

layer {
    type: "SoftmaxWithLoss"
    bottom: "cls_score"
    bottom: "labels"
    top: "cls_loss"
    softmax_param { axis: 1 }
    loss_param {
        ignore_label: -1
        normalization: VALID
    }
}