在Tensorflow中通过字符串选择不同的模式

时间:2018-12-17 07:51:56

标签: python tensorflow

我正在尝试建立一个VAE网络,在该网络中,我希望模型以不同的方式执行不同的操作。我有三种模式:“训练”,“相同”和“不同”,一个名为插值(模式)的函数根据该模式执行不同的操作。我的代码如下:

import tensorflow as tf

### some code here

mode = tf.placeholder(dtype = tf.string, name = "mode")

def interpolation(mode):
  if mode == "train":
    # do something
    print("enter train mode")
  elif mode == "same":
    # do other things
    print("enter same mode")
  else:
    # do other things
    print("enter different mode")

# some other code here

sess.run(feed_dict = {mode: "train"})
sess.run(feed_dict = {mode: "same"})
sess.run(feed_dict = {mode: "different"})

但是输出看起来像:

enter different mode
enter different mode
enter different mode

表示传入的模式不会更改条件。我做错了什么?如何通过字符串参数选择模式?

1 个答案:

答案 0 :(得分:3)

第一种方法:您可以使用本机Tensorflow switch-case选择其他模式。例如,假设您有三种情况,则可以执行以下操作:

import tensorflow as tf

mode = tf.placeholder(tf.string, shape=[], name="mode")


def cond1():
    return tf.constant('same')


def cond2():
    return tf.constant('train')


def cond3():
    return tf.constant('diff')


def cond4():
    return tf.constant('default')


y = tf.case({tf.equal(mode, 'same'): cond1,
             tf.equal(mode, 'train'): cond2,
             tf.equal(mode, 'diff'): cond3},
            default=cond4, exclusive=True)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print(sess.run(y, feed_dict={mode: "train"}))
    print(sess.run(y, feed_dict={mode: "same"}))

第二种方法:这是使用新的AutoGraph API的另一种方法:

import tensorflow as tf
from tensorflow.contrib import autograph as ag

m = tf.placeholder(dtype=tf.string, name='mode')


def interpolation(mode):
    if mode == "train":
        return 'I am train'
    elif mode == "same":
        return 'I am same'
    else:
        return 'I am different'


cond_func = ag.to_graph(interpolation)(m)
with tf.Session() as sess:
    print(sess.run(cond_func, feed_dict={m: 'same'}))