欧美bbbwbbbw肥妇,免费乱码人妻系列日韩,一级黄片

python人工智能tensorflow函數(shù)tf.assign使用方法

 更新時(shí)間:2022年05月05日 14:44:31   作者:Bubbliiiing  
這篇文章主要為大家介紹了python人工智能tensorflow函數(shù)tf.assign使用方法,有需要的朋友可以借鑒參考下,希望能夠有所幫助,祝大家多多進(jìn)步,早日升職加薪

參數(shù)數(shù)量及其作用

該函數(shù)共有五個(gè)參數(shù),分別是:

  • 被賦值的變量 ref
  • 要分配給變量的值 value、
  • 是否驗(yàn)證形狀 validate_shape
  • 是否進(jìn)行鎖定保護(hù) use_locking
  • 名稱 name
def assign(ref, value, validate_shape=None, use_locking=None, name=None)
Update 'ref' by assigning 'value' to it.
This operation outputs a Tensor that holds the new value of 'ref' after 
the value has been assigned. This makes it easier to chain operations  
that need to use the reset value.  
Args:
  ref: A mutable `Tensor`.  
	Should be from a `Variable` node. May be uninitialized.  
  value: A `Tensor`. Must have the same type as `ref`.  
    The value to be assigned to the variable.  
  validate_shape: An optional `bool`. Defaults to `True`.  
    If true, the operation will validate that the shape  
    of 'value' matches the shape of the Tensor being assigned to.  If false,  
    'ref' will take on the shape of 'value'.  
  use_locking: An optional `bool`. Defaults to `True`.  
    If True, the assignment will be protected by a lock;  
    otherwise the behavior is undefined, but may exhibit less contention.  
  name: A name for the operation (optional).  
Returns:
  A `Tensor` that will hold the new value of 'ref' after  
  the assignment has completed.    

該函數(shù)的作用是將一個(gè)要分配給變量的值value賦予被賦值的變量ref,用于tensorflow各個(gè)參數(shù)的變量賦值。

例子

該例子將舉例如何進(jìn)行變量之間的數(shù)據(jù)賦值和如何進(jìn)行集合間的數(shù)據(jù)賦值。

import tensorflow as tf;  
import numpy as np;  
c1 = ['c1', tf.GraphKeys.GLOBAL_VARIABLES]
c2 = ['c2', tf.GraphKeys.GLOBAL_VARIABLES]
#常量初始化器
v1_cons = tf.get_variable('v1_cons',dtype = tf.float32,shape=[1,4], initializer=tf.constant_initializer(), collections = c1)
v2_cons = tf.get_variable('v2_cons',dtype = tf.float32,shape=[1,4], initializer=tf.constant_initializer(9), collections = c1)
#正太分布初始化器
v1_nor = tf.get_variable('v1_nor',dtype = tf.float32, shape=[1,4], initializer=tf.random_normal_initializer(mean=0, stddev=5), collections = c2)
v2_nor = tf.get_variable('v2_nor',dtype = tf.float32, shape=[1,4], initializer=tf.random_normal_initializer(mean=0, stddev=5), collections = c2)
assign1 = tf.assign(v1_cons,v2_cons)    #將v2_cons賦予v1_cons
c1_get = tf.get_collection('c1')        #獲得c1集合
c2_get = tf.get_collection('c2')        #獲得c2集合
assign2 = [tf.assign(cg1,cg2) for cg1,cg2 in zip(c1_get,c2_get) ]   #將c2賦予c1
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print("v1_cons:",sess.run(v1_cons))
    print("v2_cons:",sess.run(v2_cons))
    print(sess.run(assign1))            #顯示賦值后的結(jié)果
    print("將v2_cons賦予v1_cons:",sess.run(v1_cons))
    print("c1_get_collection:",sess.run(c1_get))
    print("c2_get_collection:",sess.run(c2_get))
    print(sess.run(assign2))            #顯示賦值后的結(jié)果
    print("將c2賦予c1:",sess.run(c1_get))

其輸出為:

v1_cons: [[0. 0. 0. 0.]]
v2_cons: [[9. 9. 9. 9.]]
[[9. 9. 9. 9.]]
將v2_cons賦予v1_cons: [[9. 9. 9. 9.]]
c1_get_collection: [array([[9., 9., 9., 9.]], dtype=float32), array([[9., 9., 9., 9.]], dtype=float32)]
c2_get_collection: [array([[-3.9746916, -7.5332146,  2.4480317, -1.3282107]], dtype=float32), array([[10.687443 ,  3.6653206,  1.7079141, -4.524155 ]], dtype=float32)]
[array([[-3.9746916, -7.5332146,  2.4480317, -1.3282107]], dtype=float32), array([[10.687443 ,  3.6653206,  1.7079141, -4.524155 ]], dtype=float32)]
將c2賦予c1: [array([[-3.9746916, -7.5332146,  2.4480317, -1.3282107]], dtype=float32), array([[10.687443 ,  3.6653206,  1.7079141, -4.524155 ]], dtype=float32)]

以上就是python人工智能tensorflow函數(shù)tf.assign使用方法的詳細(xì)內(nèi)容,更多關(guān)于tensorflow函數(shù)tf.assign的資料請(qǐng)關(guān)注腳本之家其它相關(guān)文章!

相關(guān)文章

最新評(píng)論