Method Evaluate

include/singa/model/loss.h:52–55

Average loss values for all samples in the mini-batch It calls Forward() internally. The calling pattern should be [Evaluate|Forward] Backward.

  /// It calls Forward() internally. The calling pattern should be
  /// [Evaluate|Forward] Backward.
  float Evaluate(int flag, const Tensor &prediction, const Tensor &target) {
    Tensor loss = Forward(flag, prediction, target);
    return Sum<float>(loss) / (1.0f * loss.Size());
  }

  /// Compute the gradients of the loss values w.r.t. the prediction.
  virtual Tensor Backward() = 0;