我将tf.data.Dataset
API与tf.contrib.lookup.index_table_from_tensor
结合使用。
我的数据集是这样创建的:
dataset = tf.data.Dataset.from_tensor_slices(({'reviews': x}, y)))
这就是我在做什么:
data_table = tf.contrib.lookup.index_table_from_tensor(tf.constant(data_vocab))
labels_table = tf.contrib.lookup.index_table_from_tensor(tf.constant(labels_vocab))
然后我在dataset
上映射一个预处理函数:
def preprocess(x, y):
# split on whitespace
x['reviews'] = tf.string_split([x['reviews']])
# turn into integers
return data_table.lookup(x['reviews']), labels_table.lookup(y)
到目前为止一切都很好。但是,当我尝试将数据集传递给Keras模型进行训练时,我得到:
tensorflow.python.framework.errors_impl.FailedPreconditionError: Table not initialized.
我在Google上四处搜寻,人们建议我需要包括以下内容:
sess = tf.Session()
sess.run(tf.tables_initializer())
但是现在我得到了:
tensorflow.python.framework.errors_impl.FailedPreconditionError: Table not initialized.
[[Node: hash_table_Lookup = LookupTableFindV2[Tin=DT_STRING, Tout=DT_INT64](hash_table_lookup_placeholder, StringSplit:1, hash_table_lookup_placeholder_1)]]
[[Node: IteratorGetNext_1 = IteratorGetNext[output_shapes=[[?,?], [?,20]], output_types=[DT_INT64, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](Iterator_1)]]
任何想法为什么我的查询表仍为 尚未初始化/如何解决?
谢谢!
答案 0 :(得分:2)
您好,很奇怪,下面的示例可以为您提供帮助:
x = ['this is aswesome', 'i dont like it', 'i love it', 'i hate it']
y = ['positive','negative','positive','negative']
data_vocab = list({word for sentence in x for word in sentence.split(' ')})
label_vocab = list(set(y))
dataset = tf.data.Dataset.from_tensor_slices(({'reviews': x}, y))
data_table=tf.contrib.lookup.index_table_from_tensor(tf.constant(data_vocab))
labels_table = tf.contrib.lookup.index_table_from_tensor(tf.constant(label_vocab))
def preprocess(x, y):
# split on whitespace
x['reviews'] = tf.string_split([x['reviews']])
# turn into integers
return data_table.lookup(x['reviews']), labels_table.lookup(y)
preprocessed = dataset.map(preprocess)
it = preprocessed.make_initializable_iterator()
sess = tf.Session()
sess.run(it.initializer)
sess.run(tf.tables_initializer())
如果您致电sess.run(it.get_next())
,您会得到(SparseTensorValue(indices=array([[0, 0],
[0, 1],
[0, 2]]), values=array([2, 7, 4]), dense_shape=array([1, 3])), 1)
希望这对您有帮助!