零向量的Tensorflow错误:dims必须是int32的向量

时间:2016-06-08 03:40:58

标签: tensorflow

我试图在tensorflow中初始化零向量,如下所示:

InvalidArgumentError: dims must be a vector of int32.

但是,我收到以下错误:

$foods = (object)[
  "fruits" => (object)["apple" => 1, "banana" => 2, "cherry" => 3],
  "vegetables" => (object)["asparagus" => 4, "broccoli" => 5, "carrot" => 6]
];

你能帮我解决这个问题吗?

由于

1 个答案:

答案 0 :(得分:0)

如果你这样做,它对我有用

W = tf.zeros([784, 10])
b = tf.zeros([10])

init = tf.initialize_all_variables()
# Tensorflow run
sess =  tf.Session() 
sess.run(init)

另外,如果你按照自己的方式去做。你仍然需要稍后初始化W和b,因为下面的W不会被零张量初始化。

W = tf.Variable(tf.zeros([3,4]), name='x')
b = tf.Variable(x + 6, name='y')

model = tf.initialize_all_variables()

with tf.Session() as session:
    session.run(model)
#Error: Attempting to use uninitialized value b

上面的例子会给出错误,但下面的例子不会给出正确答案。

W = tf.zeros([3,4], name='x')
b = tf.Variable(x + 6, name='y')

model = tf.initialize_all_variables()

with tf.Session() as session:
    session.run(model)

如果你想以重量和偏见的方式做到这一点(我猜W和b代表)我建议看这里。 https://www.tensorflow.org/versions/r0.9/how_tos/variable_scope/index.html#variable-scope-example

如果您还有任何疑问,请与我们联系。