keras: perte lisse L1

Question

Essayez de personnaliser la fonction de perte (perte de L1 lisse) dans keras comme ci-dessous

ValueError: Shape must be rank 0 but is rank 5 for 'cond/Switch' (op: 'Switch') with input shapes: [?,24,24,24,?], [?,24,24,24,?].

from keras import backend as K 
import numpy as np 


def smooth_L1_loss(y_true, y_pred): 
    THRESHOLD = K.variable(1.0) 
    mae = K.abs(y_true-y_pred) 
    flag = K.greater(mae, THRESHOLD) 
    loss = K.mean(K.switch(flag, (mae - 0.5), K.pow(mae, 2)), axis=-1) 
    return loss 

Answer 1

Voici une implémentation de la perte lisse L1 en utilisant keras.backend:

HUBER_DELTA = 0.5 
def smoothL1(y_true, y_pred): 
    x = K.abs(y_true - y_pred) 
    x = K.switch(x < HUBER_DELTA, 0.5 * x ** 2, HUBER_DELTA * (x - 0.5 * HUBER_DELTA)) 
    return K.sum(x) 

Answer 2

def smoothL1(y_true, y_pred): 
    x = K.abs(y_true - y_pred) 
    if K._BACKEND == 'tensorflow': 
     import tensorflow as tf 
     x = tf.where(x < HUBER_DELTA, 0.5 * x ** 2, HUBER_DELTA * (x - 0.5 * HUBER_DELTA)) 
     return K.sum(x)