QKeras/Python中的round through函数是什么？

Question

我正在研究 'quantized_bits' class 的 QKeras 实现。在 call 函数中，我遇到了一个“_round_through”函数。

调用函数的方式如下：

if unsigned_bits > 0:
      p = x * m / m_i
      xq = m_i * tf.keras.backend.clip(
          _round_through(p, self.use_stochastic_rounding, precision=1.0),
          self.keep_negative  * (-m + self.symmetric), m - 1) / m

我尝试了运行 Python 中的代码，但它显然不是内置函数。我尝试搜索该函数，但只在 Python.

中获得了有关 'round()' 函数的结果

所以我的问题是：这个函数有什么作用？它属于哪个模块？

Link 代码：https://github.com/google/qkeras/blob/master/qkeras/quantizers.py#L489

如有任何帮助，我们将不胜感激！

Answer 1

如果你点击GitHub中的函数，它会告诉你这个函数是从哪里来的。在这种情况下，the function is defined at line 271.

def _round_through(x, use_stochastic_rounding=False, precision=0.5):
  """Rounds x but using straight through estimator.
  We use the trick from [Sergey Ioffe](
  Straight through estimator is a biased estimator for the rounding
  operation defined by Hinton"s Coursera Lecture 9c where dL/dx is made
  equal to dL/dy for y = f(x) during gradient computation, where f(x) is
  a non-derivable function. In that case, we assume df/dx = 1 in:
  dL   dL df   dL
  -- = -- -- = --
  dx   df dx   dy
  (https://www.youtube.com/watch?v=LN0xtUuJsEI&list=PLoRl3Ht4JOcdU872GhiYWf6jwrk_SNhz9&index=41)
  Arguments:
    x: tensor to perform round operation with straight through gradient.
    use_stochastic_rounding: if true, we perform stochastic rounding.
    precision: by default we will use 0.5 as precision, but that can overriden
      by the user.
  Returns:
    Rounded tensor.
  """
  if use_stochastic_rounding:
    output = tf_utils.smart_cond(
        K.learning_phase(),
        lambda: x + tf.stop_gradient(-x + stochastic_round(x, precision)),
        lambda: x + tf.stop_gradient(-x + tf.round(x)))
  else:
    output = x + tf.stop_gradient(-x + tf.round(x))
  return output

QKeras/Python中的round through函数是什么？

What is the round through function in QKeras/Python?

python

rounding

quantization

tensorflow