tf.nn.embedding_lookup在Tensorflow中不起作用

Question

我正在与tf.nn.embeddding_lookup()一起工作，但是没有工作。我正在尝试找出问题，但我无法做到这是我的代码

import tensorflow as tf

batchSize = 24
lstmUnits = 64
numClasses = 2
iterations = 10000
maxSeqLength=250

tf.reset_default_graph()

labels = tf.placeholder(tf.float32, [batchSize, numClasses])
input_data = tf.placeholder(tf.float32, [batchSize, maxSeqLength])
data = tf.Variable(tf.zeros([batchSize, maxSeqLength, numDimensions]),dtype=tf.float32)
data = tf.nn.embedding_lookup(wordVectors,input_data)
print(wordVectors)
print(input_data)

wordVectors的输出为

[[[    0     1]]

 [[    1     1]]

 [[    2     1]]

 ...

 [[14784     1]]

 [[14784     1]]

，input_data的输出为

Tensor("Placeholder_1:0", shape=(24, 250), dtype=float32)

运行tf.nn.embedding_lookup函数时出现此错误

 Value passed to parameter 'indices' has DataType float32 not in list of allowed values: int32, int64