[英]Shifted gradient with TensorFlow
I am new to TensorFlow, and I am struggling a bit with the following: Given 我是TensorFlow的新手,但我在以下方面苦苦挣扎:
and
和
, I would like to compute
,我想计算
.
。
I understand how to compute the gradient without the shift, and how I can numerically evaluate the gradient with the shift, but I do not see how to compute 我了解如何在不发生偏移的情况下计算梯度,以及如何通过偏移在数值上评估梯度,但是我看不到如何计算
symbolically.
象征性地。
import tensorflow as tf
x = tf.placeholder(tf.float32)
f = (x + 1.0)**2
s = tf.constant(1.0, tf.float32)
# Gradient of f(.)
grad_f = tf.gradients(f, x)[0]
# Gradient of f(. + s)
grad_f_shifted = ?
Note that I do not know the definition of 请注意,我不知道
, so I cannot simply define
,所以我不能简单地定义
f_shifted = (x + s + 1.0)**2
or at least I do not know how. 或者至少我不知道如何。
I think I found a solution: My goal was to compute the term 我想我找到了一个解决方案:我的目标是计算条件
, and I tried to compute it symbolically and then evaluate
,我尝试进行符号计算,然后求值
.
。 However, after looking at my problem again, I realized that I only need the value of
但是,再次看完我的问题后,我意识到我只需要
for a specific
对于特定
and not as a function of
而不是作为
.
。 Hence, I can compute
因此,我可以计算
in the following way:
通过以下方式:
x = tf.Variable(0.0, tf.float32)
f = (x + 1.0)**2.0
grad_f = tf.gradients(f, x)[0]
y = tf.Variable(0.0, tf.float32)
x0 = tf.constant(1.0, tf.float32)
s = tf.constant(1.0, tf.float32)
tensors = []
tensors.append(tf.assign(x, x0))
tensors.append(tf.assign(y, -grad_f))
tensors.append(tf.assign(x, x0 + s))
# Coming from a numerical background, the line below confused me a bit,
# because the dependency of grad_f on x is not "visible" in the code.
tensors.append(tf.assign_add(y, grad_f))
with tf.Session():
for t in tensors:
t.eval()
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.