一、梯度下降
1.1、什麼是梯度?
1.2、梯度到底代表什麼意思?
1.3、如何搜索loss最小值
1.4、tensorflow自動求導機制
import tensorflow as tf
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
w = tf.constant(1.)
x = tf.constant(2.) #注意這裏只能是浮點數,是整數的話結果返回None。
y = x*w
#梯度的計算過程要包在這個裏面。
with tf.GradientTape() as tape:
tape.watch([w])
y2 = x*w
#[grad1] = tape.gradient(y, [w]) #這裏參數[w]爲list列表。最終返回的也是list類型。
#print(grad1) #這裏返回的爲None,爲什麼呢?因爲tape.gradient()中藥求解的y,並沒有包在裏面,而是y2
[grad2] = tape.gradient(y2, [w]) #這裏參數[w]爲list列表。最終返回的也是list類型。y2放進去了
print(grad2)
ssh://[email protected]:22/home/zhangkf/anaconda3/envs/tf2.0/bin/python -u /home/zhangkf/tmp/pycharm_project_258/demo/TF2/out.py
None
Process finished with exit code 0
1.4.1、補充知識:二階梯度!
import tensorflow as tf
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
w = tf.Variable(1.) #只能是小數
b = tf.Variable(2.)
x = tf.Variable(3.)
with tf.GradientTape() as tape1:
with tf.GradientTape() as tape2:
y = x*w +b
#dy_dw, dy_db = tape2.gradient(y, [w, b]) #都可以
[dy_dw, dy_db] = tape2.gradient(y, [w, b])
#d2y_d2w = tape1.gradient(dy_dw, [w]) #都可以
d2y_d2w = tape1.gradient(dy_dw, w)
print(dy_dw)
print(dy_db)
print(d2y_d2w)
ssh://[email protected]:22/home/zhangkf/anaconda3/envs/tf2.0/bin/python -u /home/zhangkf/tmp/pycharm_project_258/demo/TF2/out.py
tf.Tensor(3.0, shape=(), dtype=float32)
tf.Tensor(1.0, shape=(), dtype=float32)
[None]
Process finished with exit code 0