Tensorflow中的Wepe Mape

我在超市預測日常銷售額，並將其作爲損失函數使用體積加權mape。Tensorflow中的Wepe Mape

總和是在輸出節點。

我tensorflow實現這一點：

import tensorflow as tf 

def weighted_mape_tf(y_true,y_pred): 
tot = tf.reduce_sum(y_true) 
wmape = tf.realdiv(tf.reduce_sum(tf.abs(tf.subtract(y_true,y_pred))),tot)*100 


return(wmape)

不幸的是我的輸出是：

Epoch 4/800 
0s - loss: 69.3939 - mean_squared_error: 819.6549 - mean_absolute_error: 14.0599 
Epoch 5/800 
0s - loss: 66.0676 - mean_squared_error: 768.5440 - mean_absolute_error: 13.4120 
Epoch 6/800 
0s - loss: 63.3000 - mean_squared_error: 728.7665 - mean_absolute_error: 12.8934 
Epoch 7/800 
0s - loss: 62.0189 - mean_squared_error: 704.7637 - mean_absolute_error: 12.5851 
Epoch 8/800 
0s - loss: 60.4229 - mean_squared_error: 682.0646 - mean_absolute_error: 12.2814 
Epoch 9/800 
0s - loss: 59.6329 - mean_squared_error: 674.8835 - mean_absolute_error: 12.1172 
Epoch 10/800 
0s - loss: 58.5069 - mean_squared_error: 656.2922 - mean_absolute_error: 11.9073 
Epoch 11/800 
0s - loss: 58.0447 - mean_squared_error: 643.9082 - mean_absolute_error: 11.7542 
Epoch 12/800 
0s - loss: 56.9352 - mean_squared_error: 628.5248 - mean_absolute_error: 11.5936 
Epoch 13/800 
0s - loss: 56.3520 - mean_squared_error: 620.7517 - mean_absolute_error: 11.4170 
Epoch 14/800 
0s - loss: 55.8395 - mean_squared_error: 610.4476 - mean_absolute_error: 11.2979 
Epoch 15/800 
0s - loss: inf - mean_squared_error: 611.3271 - mean_absolute_error: 11.2931 
Epoch 16/800 
0s - loss: nan - mean_squared_error: nan - mean_absolute_error: nan 
Epoch 17/800 
0s - loss: nan - mean_squared_error: nan - mean_absolute_error: nan 
Epoch 18/800 
0s - loss: nan - mean_squared_error: nan - mean_absolute_error: nan 
Epoch 19/800

正如你看到的一段時間就變成始終NaN的後。我猜錯誤是當tot == 0，但是當我插入一個簡單的if轉換 tot時，我仍然得到NaNs。

您對此問題有任何經驗嗎？

預先感謝您

來源

2017-03-14 Tommaso Guerrini

幾分鐘後，我找到了答案，我的問題：

import tensorflow as tf 

def weighted_mape_tf(y_true,y_pred): 
    tot = tf.reduce_sum(y_true) 
    tot = tf.clip_by_value(tot, clip_value_min=1,clip_value_max=1000) 
    wmape = tf.realdiv(tf.reduce_sum(tf.abs(tf.subtract(y_true,y_pred))),tot)*100#/tot 


    return(wmape)

我用clip_by_value糾正0

來源

2017-03-14 09:23:35

Tensorflow中的Wepe Mape

回答

相關問題