构建模型时需要定义命名空间 #1
Description
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)”