我想在训练、验证和推理阶段使用 TensorFlow Transform 将标记转换为词向量。
我遵循了这个StackOverflow 帖子并实现了从标记到向量的初始转换。转换按预期工作,我获得EMB_DIM
了每个令牌的向量。
import numpy as np
import tensorflow as tf
tf.reset_default_graph()
EMB_DIM = 10
def load_pretrained_glove():
tokens = ["a", "cat", "plays", "piano"]
return tokens, np.random.rand(len(tokens), EMB_DIM)
# sample string
string_tensor = tf.constant(["plays", "piano", "unknown_token", "another_unknown_token"])
pretrained_vocab, pretrained_embs = load_pretrained_glove()
vocab_lookup = tf.contrib.lookup.index_table_from_tensor(
mapping = tf.constant(pretrained_vocab),
default_value = len(pretrained_vocab))
string_tensor = vocab_lookup.lookup(string_tensor)
# define the word embedding
pretrained_embs = tf.get_variable(
name="embs_pretrained",
initializer=tf.constant_initializer(np.asarray(pretrained_embs), dtype=tf.float32),
shape=pretrained_embs.shape,
trainable=False)
unk_embedding = tf.get_variable(
name="unk_embedding",
shape=[1, EMB_DIM],
initializer=tf.random_uniform_initializer(-0.04, 0.04),
trainable=False)
embeddings = tf.cast(tf.concat([pretrained_embs, unk_embedding], axis=0), tf.float32)
word_vectors = tf.nn.embedding_lookup(embeddings, string_tensor)
with tf.Session() as sess:
tf.tables_initializer().run()
tf.global_variables_initializer().run()
print(sess.run(word_vectors))
当我重构代码以作为 TFX 变换图运行时,我收到以下错误ConversionError
。
import pprint
import tempfile
import numpy as np
import tensorflow as tf
import tensorflow_transform as tft
import tensorflow_transform.beam.impl as beam_impl
from tensorflow_transform.tf_metadata import dataset_metadata
from tensorflow_transform.tf_metadata import dataset_schema
tf.reset_default_graph()
EMB_DIM = 10
def load_pretrained_glove():
tokens = ["a", "cat", "plays", "piano"]
return tokens, np.random.rand(len(tokens), EMB_DIM)
def embed_tensor(string_tensor, trainable=False):
"""
Convert List of strings into list of indices then into EMB_DIM vectors
"""
pretrained_vocab, pretrained_embs = load_pretrained_glove()
vocab_lookup = tf.contrib.lookup.index_table_from_tensor(
mapping=tf.constant(pretrained_vocab),
default_value=len(pretrained_vocab))
string_tensor = vocab_lookup.lookup(string_tensor)
pretrained_embs = tf.get_variable(
name="embs_pretrained",
initializer=tf.constant_initializer(np.asarray(pretrained_embs), dtype=tf.float32),
shape=pretrained_embs.shape,
trainable=trainable)
unk_embedding = tf.get_variable(
name="unk_embedding",
shape=[1, EMB_DIM],
initializer=tf.random_uniform_initializer(-0.04, 0.04),
trainable=False)
embeddings = tf.cast(tf.concat([pretrained_embs, unk_embedding], axis=0), tf.float32)
return tf.nn.embedding_lookup(embeddings, string_tensor)
def preprocessing_fn(inputs):
input_string = tf.string_split(inputs['sentence'], delimiter=" ")
return {'word_vectors': tft.apply_function(embed_tensor, input_string)}
raw_data = [{'sentence': 'This is a sample sentence'},]
raw_data_metadata = dataset_metadata.DatasetMetadata(dataset_schema.Schema({
'sentence': dataset_schema.ColumnSchema(
tf.string, [], dataset_schema.FixedColumnRepresentation())
}))
with beam_impl.Context(temp_dir=tempfile.mkdtemp()):
transformed_dataset, transform_fn = ( # pylint: disable=unused-variable
(raw_data, raw_data_metadata) | beam_impl.AnalyzeAndTransformDataset(
preprocessing_fn))
transformed_data, transformed_metadata = transformed_dataset # pylint: disable=unused-variable
pprint.pprint(transformed_data)
错误信息
TypeError: Failed to convert object of type <class
'tensorflow.python.framework.sparse_tensor.SparseTensor'> to Tensor.
Contents: SparseTensor(indices=Tensor("StringSplit:0", shape=(?, 2),
dtype=int64), values=Tensor("hash_table_Lookup:0", shape=(?,),
dtype=int64), dense_shape=Tensor("StringSplit:2", shape=(2,),
dtype=int64)). Consider casting elements to a supported type.
问题
- 为什么 TF 变换步骤需要额外的转换/转换?
- 这种将标记转换为词向量的方法可行吗?词向量在内存中可能有数 GB。Apache Beam 如何处理向量?如果 Beam 在分布式设置中,是否需要工人数量
N x vector memory
?N