你需要tf.map_fn
实现循环和tf.py_func
结束nbinom.pmf
。例如:
from scipy.stats import nbinom
import tensorflow as tf
def loss_neg_bin(y_pred, y_true):
result = 0.0
for p, t in zip(y_pred, y_true):
result += -nbinom.pmf(t, p[0], min(0.99, p[1]))
return result
y_pred= [[0.4, 0.4],[0.5, 0.5]]
y_true= [[1, 2],[1, 2]]
print('your version:\n',loss_neg_bin(y_pred, y_true))
def loss_neg_bin_tf(y_pred, y_true):
result = tf.map_fn(lambda x:tf.py_func(lambda p,t:-nbinom.pmf(t, p[0], min(0.99,p[1]))
,x
,tf.float64)
,(y_pred,y_true)
,dtype=tf.float64)
result = tf.reduce_sum(result,axis=0)
return result
y_pred_tf = tf.placeholder(shape=(None,2),dtype=tf.float64)
y_true_tf = tf.placeholder(shape=(None,2),dtype=tf.float64)
loss = loss_neg_bin_tf(y_pred_tf, y_true_tf)
with tf.Session() as sess:
print('tensorflow version:\n',sess.run(loss,feed_dict={y_pred_tf:y_pred,y_true_tf:y_true}))
# print
your version:
[-0.34313146 -0.13616026]
tensorflow version:
[-0.34313146 -0.13616026]
另外,如果你使用tf.py_func
负二项式计算概率质量函数作为损失反馈模型,你需要自己定义梯度函数。
更新——添加可微负二项式损失
的概率质量函数为nbinom
:
nbinom.pmf(k) = choose(k+n-1, n-1) * p**n * (1-p)**k
k >= 0
根据scipy.stats.nbinom。_
所以我添加了可微分负二项式损失版本。
import tensorflow as tf
def nbinom_pmf_tf(x,n,p):
coeff = tf.lgamma(n + x) - tf.lgamma(x + 1) - tf.lgamma(n)
return tf.cast(tf.exp(coeff + n * tf.log(p) + x * tf.log(1 - p)),dtype=tf.float64)
def loss_neg_bin_tf_differentiable(y_pred, y_true):
result = tf.map_fn(lambda x: -nbinom_pmf_tf(x[1]
, x[0][0]
, tf.minimum(tf.constant(0.99,dtype=tf.float64),x[0][1]))
,(y_pred,y_true)
,dtype=tf.float64)
result = tf.reduce_sum(result,axis=0)
return result
y_pred_tf = tf.placeholder(shape=(None,2),dtype=tf.float64)
y_true_tf = tf.placeholder(shape=(None,2),dtype=tf.float64)
loss = loss_neg_bin_tf_differentiable(y_pred_tf, y_true_tf)
grads = tf.gradients(loss,y_pred_tf)
y_pred= [[0.4, 0.4],[0.5, 0.5]]
y_true= [[1, 2],[1, 2]]
with tf.Session() as sess:
print('tensorflow differentiable version:')
loss_val,grads_val = sess.run([loss,grads],feed_dict={y_pred_tf:y_pred,y_true_tf:y_true})
print(loss_val)
print(grads_val)
# print
tensorflow differentiable version:
[-0.34313146 -0.13616026]
[array([[-0.42401619, 0.27393084],
[-0.36184822, 0.37565048]])]