Tensorflow:恢复的变量具有意外的形状

时间:2019-03-05 05:01:38

标签: python-3.x tensorflow

当我保存并恢复它的tensorflow模型时,它的形状变量错误,我不知道为什么。

这是我的代码:

import os
import tensorflow as tf
X = tf.placeholder(tf.float32, shape=[None, 2], name="X")
Y = tf.placeholder(tf.float32, shape=[None, 1], name="Y")
W = tf.Variable(tf.random_normal([2, 1]), name="weight")
b = tf.Variable(tf.random_normal([1]), name="bias")

hypo = tf.sigmoid(tf.matmul(X, W) +b)

cost = -tf.reduce_mean(Y*(tf.log*(hypo)) + (1-Y)*(tf.log(1-hypo)))
optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-3)
train = optimizer.minimize(cost)

#### Saving model
SAVER_DIR = "model"
saver = tf.train.Saver()
checkpoint_path = os.path.join(SAVER_DIR, "model")
ckpt = tf.train.get_checkpoint_state(SAVER_DIR)

sess = tf.Session()
sess.run(tf.global_variables_initializer())
for step in range(2001):
    cost_val, hy_val, _ = sess.run([cost, hypo, train], feed_dict={X:x_dat, Y=y_dat})

saver.save(sess, checkpoint_path, global_step=step)

输入数据“ x_dat”由两列组成,而“ y_dat”是单列。

我制作了[?,2]形的占位符“ X”和[2,1]变量“ W”。

之后,我恢复了模型并使用以下代码检查了形状:

#### Restoring model
sess = tf.Session()
sess.run(tf.global_variables_initializer())
saver = tf.train.import_meta_graph('./model/model-2000.meta')
saver.restore(sess,'./model/model-2000')

op = sess.graph.get_operations()
for m in op :
    print(m.values())

结果:

(<tf.Tensor 'X:0' shape=(?, 1) dtpye=float32>,)
(<tf.Tensor 'Y:0' shape=(?, 1) dtpye=float32>,)
...
(<tf.Tensor 'weight:0' shape=(1, 1) dtpye=float32_ref>,)
...
(<tf.Tensor 'bias:0' shape=(1,) dtpye=float32_ref>,)

为什么X和重量张量的形状与我保存的模型相比有所不同? 以及如何将输入数据用作关于此还原模型的两列?

0 个答案:

没有答案