TensorFlow基本概念
1 基本概念
2 变量
常量：tf.constant()
变量：tf.Variable()
mport tensorflow as tf
import os
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2" # 忽略tensorflow警告信息
x = tf.Variable(0)
new_x = tf.add(x,1)
update = tf.assign(x,new_x) #x必须是通过tf.Variable()创建的tensor,不能是常量
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
for _ in range(5):
print(sess.run(x))
sess.run(update)
变量可以被赋值，tf.assign操作。常量不行