TensorFlow 基础

技术分享 手册留言
44

参考 https://tf.wiki/zh_hans/basic/basic.html#zh-hans-optimizer ，指定待求导的函数 f 和求导的变量 x （也就是，哪个函数对哪个变量求导， \frac{\partial f}{\partial x} ），即可自动计算梯度。

45

计算loss的时候为什么不计算平均loss呢，而是总的损失？

46

两者没有本质区别，参考注释4

1 Like
47

懂了，非常感谢

50

我的电脑是集成显卡，code如下

import tensorflow as tf
x = tf.Variable(initial_value=3.)
with tf.GradientTape() as tape:
    y = tf.square(x)
y_grad = tape.gradient(y, x)
print(y, y_grad)

运行后结果没问题，但出现了一些提示，费解！请问是怎么回事呢？
tf.Tensor(9.0, shape=(), dtype=float32) tf.Tensor(6.0, shape=(), dtype=float32)
2021-03-09 13:56:02.374852: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set
2021-03-09 13:56:02.375186: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.

51

其实就是英文所表述的字面意思，一般而言可以忽略。参考 Tensorflow issues: Not creating XLA devices, tf_xla_enable_xla_devices not set, This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. · Issue #46479 · tensorflow/tensorflow · GitHub

52

请问一下，这里如果手工计算L关于w、b的偏导数，该如何计算呢？

image
image881×198 29.2 KB

53

\frac{\partial L(w,b)}{\partial w} = 2X^\top(Xw+b-y) = \begin{bmatrix}1 & 3 \\ 2 & 4\end{bmatrix}\begin{bmatrix}10 \\ 20\end{bmatrix} = \begin{bmatrix}70 \\ 100\end{bmatrix}

\frac{\partial L(w,b)}{\partial b} = 2\begin{bmatrix}1 & 1\end{bmatrix}(Xw+b-y) = \begin{bmatrix}1 & 1\end{bmatrix}\begin{bmatrix}10 \\ 20\end{bmatrix} = 30

参考 Matrix calculus - Wikipedia