tensorflow更改变量的值实例
如下所示:
from__future__importprint_function,division importtensorflowastf #createaVariable w=tf.Variable(initial_value=[[1,2],[3,4]],dtype=tf.float32) x=tf.Variable(initial_value=[[1,1],[1,1]],dtype=tf.float32,validate_shape=False) init_op=tf.global_variables_initializer() update=tf.assign(x,[[1,2],[1,2]]) withtf.Session()assession: session.run(init_op) session.run(update) x=session.run(x) print(x)
实验结果:
[[1.2.] [1.2.]]
tensorflow使用assign(variable,new_value)来更改变量的值,但是真正作用在garph中,必须要调用gpu或者cpu运行这个更新过程。
session.run(update)
tensorflow不支持直接对变量进行赋值更改
from__future__importprint_function,division importtensorflowastf #createaVariable x=tf.Variable(initial_value=[[1,1],[1,1]],dtype=tf.float32,validate_shape=False) x=[[1,3],[2,4]] init_op=tf.global_variables_initializer() update=tf.assign(x,[[1,2],[1,2]]) withtf.Session()assession: session.run(init_op) session.run(update) print(session.run(x))
error:
"C:\ProgramFiles\Anaconda3\python.exe"D:/pycharmprogram/tensorflow_learn/assign_learn/assign_learn.py Traceback(mostrecentcalllast): File"D:/pycharmprogram/tensorflow_learn/assign_learn/assign_learn.py",line8,inupdate=tf.assign(x,[[1,2],[1,2]]) File"C:\ProgramFiles\Anaconda3\lib\site-packages\tensorflow\python\ops\state_ops.py",line271,inassign ifref.dtype._is_ref_dtype: AttributeError:'list'objecthasnoattribute'dtype' Processfinishedwithexitcode1
以上这篇tensorflow更改变量的值实例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持毛票票。