Add scale factor for smoothL1 and smoothL1Bp

[pkuyym]

Whether to add costs or gradients to destination Matrix should be decided by user. Current implement is:

void CpuMatrix::smoothL1(Matrix& output, Matrix& label) {
  CHECK(output.useGpu_ == false && label.useGpu_ == false)
      << "Matrix type are not equal";

  size_t numSamples = getHeight();
  size_t dim = output.getWidth();
  CHECK_EQ(label.getHeight(), numSamples);
  CHECK_EQ(output.getHeight(), numSamples);
  CHECK_EQ(label.getWidth(), dim);
  CHECK_EQ(getWidth(), (size_t)1);

  real* cost = getData();
  real* out = output.getData();
  real* lbl = label.getData();

  for (size_t i = 0; i < numSamples; ++i, out += dim, lbl += dim) {
    for (size_t j = 0; j < dim; ++j) {
      real absVal = std::fabs(out[j] - lbl[j]);
      if (absVal < 1.0)
        cost[i] += 0.5 * absVal * absVal;
      else
        cost[i] += absVal - 0.5;
    }
  }
}

void CpuMatrix::smoothL1Bp(Matrix& output, Matrix& label) {
  CHECK(output.useGpu_ == false && label.useGpu_ == false)
      << "Matrix type are not equal";

  size_t numSamples = getHeight();
  size_t dim = output.getWidth();
  CHECK_EQ(label.getHeight(), numSamples);
  CHECK_EQ(output.getHeight(), numSamples);
  CHECK_EQ(label.getWidth(), dim);
  CHECK_EQ(getWidth(), dim);

  real* out = output.getData();
  real* lbl = label.getData();
  real* grad = getData();

  for (size_t i = 0; i < numSamples; ++i, out += dim, grad += dim, lbl += dim) {
    for (size_t j = 0; j < dim; ++j) {
      real val = out[j] - lbl[j];
      if (std::fabs(val) < 1) {
        grad[j] += val;
      } else {
        grad[j] += (real(0) < val) - (val < real(0));
      }
    }
  }
}

As we can see, current implement adds cost and gradient to caller object leaving no other choice. A solution is adding a scale factor to caller object.