SmoothL1Loss

class dragon.vm.caffe.layers.SmoothL1Loss(layer_param)[source]

Compute the element-wise error transited from L1 and L2. [Girshick, 2015].

Examples:

layer {
    type: "SmoothL1Loss"
    bottom: "bbox_pred"
    bottom: "bbox_targets"
    bottom: "bbox_inside_weights"
    bottom: "bbox_outside_weights"
    top: "bbox_loss"
    loss_param {
        normalization: BATCH_SIZE
    }
}