构建模型时需要定义命名空间

[charmpeng]

在effective-tf.md中定义模型函数的时候，

import numpy as np
import TensorFlow as tf
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
w = tf.get_variable("w", shape=[3, 1])
f = tf.stack([tf.square(x), x, tf.ones_like(x)], 1)
yhat = tf.squeeze(tf.matmul(f, w), 1)
loss = tf.nn.l2_loss(yhat - y) + 0.1 * tf.nn.l2_loss(w)
train_op = tf.train.AdamOptimizer(0.1).minimize(loss)

代码会报错，说“ValueError: Variable w already exists, disallowed. ” 需要显示的说明，完成变量共享。即在前面加上“tf.variable_scope("f", reuse=tf.AUTO_REUSE)”

[FesianXu]

Hi, i have tried your code and there is not any error. My tensorflow is version 1.8.0. Also import TensorFlow as tf should be import tensorflow as tf. Please check out your version and have another try.