Python tf.nn.log_poisson_loss用法及代碼示例

在給定 log_input 的情況下計算對數泊鬆損失。

用法

tf.nn.log_poisson_loss(
    targets, log_input, compute_full_loss=False, name=None
)

在假設目標具有泊鬆分布的情況下，給出預測和目標之間的log-likelihood 損失。警告：默認情況下，這不是確切的損失，而是損失減去常數項 [log(z!)]。這對優化沒有影響，但在相對損失比較中效果不佳。要計算對數階乘項的近似值，請指定 compute_full_loss=True 以啟用斯特林近似。

為簡潔起見，讓 c = log(x) = log_input , z = targets 。對數泊鬆損失為

-log(exp(-x) * (x^z) / z!)
= -log(exp(-x) * (x^z)) + log(z!)
~ -log(exp(-x)) - log(x^z) [+ z * log(z) - z + 0.5 * log(2 * pi * z)]
    [ Note the second term is the Stirling's Approximation for log(z!).
      It is invariant to x and does not affect optimization, though
      important for correct relative loss comparisons. It is only
      computed when compute_full_loss == True. ]
= x - z * log(x) [+ z * log(z) - z + 0.5 * log(2 * pi * z)]
= exp(c) - z * c [+ z * log(z) - z + 0.5 * log(2 * pi * z)]