 Zobacz na TensorFlow.org |  Zobacz na GitHubie |  Pobierz notatnik |  Zobacz modele TF Hub |
W tym samouczku pokazano, jak wygenerować osadzenia z modułu TensorFlow Hub (TF-Hub) na podstawie danych wejściowych i zbudować przybliżony indeks najbliższych sąsiadów (ANN) przy użyciu wyodrębnionych osadów. Indeks można następnie wykorzystać do dopasowywania i wyszukiwania podobieństw w czasie rzeczywistym.
W przypadku dużego zbioru danych dokładne dopasowanie poprzez skanowanie całego repozytorium w celu znalezienia w czasie rzeczywistym elementów najbardziej podobnych do danego zapytania nie jest efektywne. Dlatego używamy przybliżonego algorytmu dopasowywania podobieństwa, który pozwala nam poświęcić odrobinę dokładności w znajdowaniu dokładnych dopasowań najbliższego sąsiada na rzecz znacznego zwiększenia szybkości.
W tym samouczku pokażemy przykład wyszukiwania tekstu w czasie rzeczywistym w korpusie nagłówków wiadomości, aby znaleźć nagłówki najbardziej podobne do zapytania. W przeciwieństwie do wyszukiwania słów kluczowych, wychwytuje to podobieństwo semantyczne zakodowane w osadzaniu tekstu.
Kroki tego samouczka są następujące:
- Pobierz przykładowe dane.
- Generuj osadzanie danych za pomocą modułu TF-Hub
- Zbuduj indeks ANN dla osadzania
- Użyj indeksu do dopasowania podobieństwa
Do generowania osadzania z modułu TF-Hub używamy Apache Beam z TensorFlow Transform (TF-Transform). Korzystamy również z biblioteki ANNOY Spotify, aby zbudować przybliżony indeks najbliższych sąsiadów. Możesz znaleźć testy porównawcze frameworku ANN w tym repozytorium Github .
Ten samouczek wykorzystuje TensorFlow 1.0 i działa tylko z modułami TF1 Hub z TF-Hub. Zobacz zaktualizowaną wersję tego poradnika dla TF2 .
Organizować coś
Zainstaluj wymagane biblioteki.
pip install -q apache_beampip install -q sklearnpip install -q annoy
Zaimportuj wymagane biblioteki
import os
import sys
import pathlib
import pickle
from collections import namedtuple
from datetime import datetime
import numpy as np
import apache_beam as beam
import annoy
from sklearn.random_projection import gaussian_random_matrix
import tensorflow.compat.v1 as tf
import tensorflow_hub as hub
# TFT needs to be installed afterwards
!pip install -q tensorflow_transform==0.24
import tensorflow_transform as tft
import tensorflow_transform.beam as tft_beam
print('TF version: {}'.format(tf.__version__))
print('TF-Hub version: {}'.format(hub.__version__))
print('TF-Transform version: {}'.format(tft.__version__))
print('Apache Beam version: {}'.format(beam.__version__))
TF version: 2.3.1 TF-Hub version: 0.10.0 TF-Transform version: 0.24.0 Apache Beam version: 2.25.0
1. Pobierz przykładowe dane
Zbiór danych Million News Headlines zawiera nagłówki wiadomości opublikowane w ciągu 15 lat i pochodzą od renomowanej firmy Australian Broadcasting Corp. (ABC). Ten zbiór wiadomości zawiera podsumowanie historycznych zapisów godnych uwagi wydarzeń na świecie od początku 2003 r. do końca 2017 r., ze szczególnym uwzględnieniem Australii.
Format : Dane w dwóch kolumnach oddzielonych tabulatorami: 1) data publikacji i 2) tekst nagłówka. Nas interesuje tylko tekst nagłówka.
wget 'https://dataverse.harvard.edu/api/access/datafile/3450625?format=tab&gbrecs=true' -O raw.tsvwc -l raw.tsvhead raw.tsv
--2020-12-03 12:12:21-- https://dataverse.harvard.edu/api/access/datafile/3450625?format=tab&gbrecs=true Resolving dataverse.harvard.edu (dataverse.harvard.edu)... 206.191.184.198 Connecting to dataverse.harvard.edu (dataverse.harvard.edu)|206.191.184.198|:443... connected. HTTP request sent, awaiting response... 200 OK Length: 57600231 (55M) [text/tab-separated-values] Saving to: ‘raw.tsv’ raw.tsv 100%[===================>] 54.93M 15.1MB/s in 4.3s 2020-12-03 12:12:27 (12.7 MB/s) - ‘raw.tsv’ saved [57600231/57600231] 1103664 raw.tsv publish_date headline_text 20030219 "aba decides against community broadcasting licence" 20030219 "act fire witnesses must be aware of defamation" 20030219 "a g calls for infrastructure protection summit" 20030219 "air nz staff in aust strike for pay rise" 20030219 "air nz strike to affect australian travellers" 20030219 "ambitious olsson wins triple jump" 20030219 "antic delighted with record breaking barca" 20030219 "aussie qualifier stosur wastes four memphis match" 20030219 "aust addresses un security council over iraq"
Dla uproszczenia zachowujemy jedynie tekst nagłówka i usuwamy datę publikacji
!rm -r corpus
!mkdir corpus
with open('corpus/text.txt', 'w') as out_file:
with open('raw.tsv', 'r') as in_file:
for line in in_file:
headline = line.split('\t')[1].strip().strip('"')
out_file.write(headline+"\n")
rm: cannot remove 'corpus': No such file or directory
tail corpus/text.txtsevere storms forecast for nye in south east queensland snake catcher pleads for people not to kill reptiles south australia prepares for party to welcome new year strikers cool off the heat with big win in adelaide stunning images from the sydney to hobart yacht the ashes smiths warners near miss liven up boxing day test timelapse: brisbanes new year fireworks what 2017 meant to the kids of australia what the papodopoulos meeting may mean for ausus who is george papadopoulos the former trump campaign aide
Funkcja pomocnicza do ładowania modułu TF-Hub
def load_module(module_url):
embed_module = hub.Module(module_url)
placeholder = tf.placeholder(dtype=tf.string)
embed = embed_module(placeholder)
session = tf.Session()
session.run([tf.global_variables_initializer(), tf.tables_initializer()])
print('TF-Hub module is loaded.')
def _embeddings_fn(sentences):
computed_embeddings = session.run(
embed, feed_dict={placeholder: sentences})
return computed_embeddings
return _embeddings_fn
2. Wygeneruj osadzanie danych.
W tym samouczku użyjemy uniwersalnego kodera zdań do wygenerowania emebeddingów dla danych nagłówka. Osadzanie zdań można następnie łatwo wykorzystać do obliczenia podobieństwa znaczeń na poziomie zdań. Proces generowania osadzania prowadzimy przy użyciu Apache Beam i TF-Transform.
Metoda ekstrakcji osadzającej
encoder = None
def embed_text(text, module_url, random_projection_matrix):
# Beam will run this function in different processes that need to
# import hub and load embed_fn (if not previously loaded)
global encoder
if not encoder:
encoder = hub.Module(module_url)
embedding = encoder(text)
if random_projection_matrix is not None:
# Perform random projection for the embedding
embedding = tf.matmul(
embedding, tf.cast(random_projection_matrix, embedding.dtype))
return embedding
Utwórz metodę preprocess_fn TFT
def make_preprocess_fn(module_url, random_projection_matrix=None):
'''Makes a tft preprocess_fn'''
def _preprocess_fn(input_features):
'''tft preprocess_fn'''
text = input_features['text']
# Generate the embedding for the input text
embedding = embed_text(text, module_url, random_projection_matrix)
output_features = {
'text': text,
'embedding': embedding
}
return output_features
return _preprocess_fn
Utwórz metadane zestawu danych
def create_metadata():
'''Creates metadata for the raw data'''
from tensorflow_transform.tf_metadata import dataset_metadata
from tensorflow_transform.tf_metadata import schema_utils
feature_spec = {'text': tf.FixedLenFeature([], dtype=tf.string)}
schema = schema_utils.schema_from_feature_spec(feature_spec)
metadata = dataset_metadata.DatasetMetadata(schema)
return metadata
Rurociąg belkowy
def run_hub2emb(args):
'''Runs the embedding generation pipeline'''
options = beam.options.pipeline_options.PipelineOptions(**args)
args = namedtuple("options", args.keys())(*args.values())
raw_metadata = create_metadata()
converter = tft.coders.CsvCoder(
column_names=['text'], schema=raw_metadata.schema)
with beam.Pipeline(args.runner, options=options) as pipeline:
with tft_beam.Context(args.temporary_dir):
# Read the sentences from the input file
sentences = (
pipeline
| 'Read sentences from files' >> beam.io.ReadFromText(
file_pattern=args.data_dir)
| 'Convert to dictionary' >> beam.Map(converter.decode)
)
sentences_dataset = (sentences, raw_metadata)
preprocess_fn = make_preprocess_fn(args.module_url, args.random_projection_matrix)
# Generate the embeddings for the sentence using the TF-Hub module
embeddings_dataset, _ = (
sentences_dataset
| 'Extract embeddings' >> tft_beam.AnalyzeAndTransformDataset(preprocess_fn)
)
embeddings, transformed_metadata = embeddings_dataset
# Write the embeddings to TFRecords files
embeddings | 'Write embeddings to TFRecords' >> beam.io.tfrecordio.WriteToTFRecord(
file_path_prefix='{}/emb'.format(args.output_dir),
file_name_suffix='.tfrecords',
coder=tft.coders.ExampleProtoCoder(transformed_metadata.schema))
Generowanie macierzy losowej projekcji
Rzutowanie losowe to prosta, ale potężna technika stosowana w celu zmniejszenia wymiarowości zbioru punktów leżących w przestrzeni euklidesowej. Tło teoretyczne można znaleźć w lemacie Johnsona-Lindenstraussa .
Zmniejszenie wymiarowości osadzania za pomocą losowej projekcji oznacza mniej czasu potrzebnego na budowanie i sprawdzanie indeksu SSN.
W tym samouczku używamy losowej projekcji Gaussa z biblioteki Scikit-learn .
def generate_random_projection_weights(original_dim, projected_dim):
random_projection_matrix = None
if projected_dim and original_dim > projected_dim:
random_projection_matrix = gaussian_random_matrix(
n_components=projected_dim, n_features=original_dim).T
print("A Gaussian random weight matrix was creates with shape of {}".format(random_projection_matrix.shape))
print('Storing random projection matrix to disk...')
with open('random_projection_matrix', 'wb') as handle:
pickle.dump(random_projection_matrix,
handle, protocol=pickle.HIGHEST_PROTOCOL)
return random_projection_matrix
Ustaw parametry
Jeśli chcesz zbudować indeks przy użyciu oryginalnej przestrzeni do osadzania bez losowej projekcji, ustaw parametr projected_dim na None . Należy pamiętać, że spowolni to etap indeksowania w przypadku osadzania wielowymiarowego.
module_url = 'https://tfhub.dev/google/universal-sentence-encoder/2'
projected_dim = 64
Uruchom potok
import tempfile
output_dir = pathlib.Path(tempfile.mkdtemp())
temporary_dir = pathlib.Path(tempfile.mkdtemp())
g = tf.Graph()
with g.as_default():
original_dim = load_module(module_url)(['']).shape[1]
random_projection_matrix = None
if projected_dim:
random_projection_matrix = generate_random_projection_weights(
original_dim, projected_dim)
args = {
'job_name': 'hub2emb-{}'.format(datetime.utcnow().strftime('%y%m%d-%H%M%S')),
'runner': 'DirectRunner',
'batch_size': 1024,
'data_dir': 'corpus/*.txt',
'output_dir': output_dir,
'temporary_dir': temporary_dir,
'module_url': module_url,
'random_projection_matrix': random_projection_matrix,
}
print("Pipeline args are set.")
args
INFO:tensorflow:Saver not created because there are no variables in the graph to restore
INFO:tensorflow:Saver not created because there are no variables in the graph to restore
TF-Hub module is loaded.
A Gaussian random weight matrix was creates with shape of (512, 64)
Storing random projection matrix to disk...
Pipeline args are set.
/home/kbuilder/.local/lib/python3.6/site-packages/sklearn/utils/deprecation.py:86: FutureWarning: Function gaussian_random_matrix is deprecated; gaussian_random_matrix is deprecated in 0.22 and will be removed in version 0.24.
warnings.warn(msg, category=FutureWarning)
{'job_name': 'hub2emb-201203-121305',
'runner': 'DirectRunner',
'batch_size': 1024,
'data_dir': 'corpus/*.txt',
'output_dir': PosixPath('/tmp/tmp3_9agsp3'),
'temporary_dir': PosixPath('/tmp/tmp75ty7xfk'),
'module_url': 'https://tfhub.dev/google/universal-sentence-encoder/2',
'random_projection_matrix': array([[ 0.21470759, -0.05258816, -0.0972597 , ..., 0.04385087,
-0.14274348, 0.11220471],
[ 0.03580492, -0.16426251, -0.14089037, ..., 0.0101535 ,
-0.22515438, -0.21514454],
[-0.15639698, 0.01808027, -0.13684782, ..., 0.11841098,
-0.04303762, 0.00745478],
...,
[-0.18584684, 0.14040793, 0.18339619, ..., 0.13763638,
-0.13028201, -0.16183348],
[ 0.20997704, -0.2241034 , -0.12709368, ..., -0.03352462,
0.11281993, -0.16342795],
[-0.23761595, 0.00275779, -0.1585855 , ..., -0.08995121,
0.1475089 , -0.26595401]])}
!rm -r {output_dir}
!rm -r {temporary_dir}
print("Running pipeline...")
%time run_hub2emb(args)
print("Pipeline is done.")
WARNING:apache_beam.runners.interactive.interactive_environment:Dependencies required for Interactive Beam PCollection visualization are not available, please use: `pip install apache-beam[interactive]` to install necessary dependencies to enable all data visualization features. Running pipeline... Warning:tensorflow:Tensorflow version (2.3.1) found. Note that Tensorflow Transform support for TF 2.0 is currently in beta, and features such as tf.function may not work as intended. Warning:tensorflow:Tensorflow version (2.3.1) found. Note that Tensorflow Transform support for TF 2.0 is currently in beta, and features such as tf.function may not work as intended. Warning:tensorflow:Tensorflow version (2.3.1) found. Note that Tensorflow Transform support for TF 2.0 is currently in beta, and features such as tf.function may not work as intended. Warning:tensorflow:Tensorflow version (2.3.1) found. Note that Tensorflow Transform support for TF 2.0 is currently in beta, and features such as tf.function may not work as intended. Warning:tensorflow:You are passing instance dicts and DatasetMetadata to TFT which will not provide optimal performance. Consider following the TFT guide to upgrade to the TFXIO format (Apache Arrow RecordBatch). Warning:tensorflow:You are passing instance dicts and DatasetMetadata to TFT which will not provide optimal performance. Consider following the TFT guide to upgrade to the TFXIO format (Apache Arrow RecordBatch). INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore Warning:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow/python/saved_model/signature_def_utils_impl.py:201: build_tensor_info (from tensorflow.python.saved_model.utils_impl) is deprecated and will be removed in a future version. Instructions for updating: This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.utils.build_tensor_info or tf.compat.v1.saved_model.build_tensor_info. Warning:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow/python/saved_model/signature_def_utils_impl.py:201: build_tensor_info (from tensorflow.python.saved_model.utils_impl) is deprecated and will be removed in a future version. Instructions for updating: This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.utils.build_tensor_info or tf.compat.v1.saved_model.build_tensor_info. INFO:tensorflow:Assets added to graph. INFO:tensorflow:Assets added to graph. INFO:tensorflow:No assets to write. INFO:tensorflow:No assets to write. INFO:tensorflow:SavedModel written to: /tmp/tmp75ty7xfk/tftransform_tmp/0839c04b1a8d4dd0b3d2832fbe9f5904/saved_model.pb INFO:tensorflow:SavedModel written to: /tmp/tmp75ty7xfk/tftransform_tmp/0839c04b1a8d4dd0b3d2832fbe9f5904/saved_model.pb Warning:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_transform/tf_utils.py:218: Tensor.experimental_ref (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version. Instructions for updating: Use ref() instead. Warning:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_transform/tf_utils.py:218: Tensor.experimental_ref (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version. Instructions for updating: Use ref() instead. Warning:tensorflow:Tensorflow version (2.3.1) found. Note that Tensorflow Transform support for TF 2.0 is currently in beta, and features such as tf.function may not work as intended. Warning:tensorflow:Tensorflow version (2.3.1) found. Note that Tensorflow Transform support for TF 2.0 is currently in beta, and features such as tf.function may not work as intended. Warning:tensorflow:You are passing instance dicts and DatasetMetadata to TFT which will not provide optimal performance. Consider following the TFT guide to upgrade to the TFXIO format (Apache Arrow RecordBatch). Warning:tensorflow:You are passing instance dicts and DatasetMetadata to TFT which will not provide optimal performance. Consider following the TFT guide to upgrade to the TFXIO format (Apache Arrow RecordBatch). WARNING:apache_beam.io.tfrecordio:Couldn't find python-snappy so the implementation of _TFRecordUtil._masked_crc32c is not as fast as it could be. CPU times: user 2min 50s, sys: 6.6 s, total: 2min 57s Wall time: 2min 40s Pipeline is done.
ls {output_dir}emb-00000-of-00001.tfrecords
Przeczytaj niektóre wygenerowane osadzania...
import itertools
embed_file = os.path.join(output_dir, 'emb-00000-of-00001.tfrecords')
sample = 5
record_iterator = tf.io.tf_record_iterator(path=embed_file)
for string_record in itertools.islice(record_iterator, sample):
example = tf.train.Example()
example.ParseFromString(string_record)
text = example.features.feature['text'].bytes_list.value
embedding = np.array(example.features.feature['embedding'].float_list.value)
print("Embedding dimensions: {}".format(embedding.shape[0]))
print("{}: {}".format(text, embedding[:10]))
WARNING:tensorflow:From <ipython-input-1-3d6f4d54c65b>:5: tf_record_iterator (from tensorflow.python.lib.io.tf_record) is deprecated and will be removed in a future version. Instructions for updating: Use eager execution and: `tf.data.TFRecordDataset(path)` Warning:tensorflow:From <ipython-input-1-3d6f4d54c65b>:5: tf_record_iterator (from tensorflow.python.lib.io.tf_record) is deprecated and will be removed in a future version. Instructions for updating: Use eager execution and: `tf.data.TFRecordDataset(path)` Embedding dimensions: 64 [b'headline_text']: [-0.04724706 0.27573067 -0.02340046 0.12461437 0.04809146 0.00246292 0.15367804 -0.17551982 -0.02778188 -0.185176 ] Embedding dimensions: 64 [b'aba decides against community broadcasting licence']: [-0.0466345 0.00110549 -0.08875479 0.05938878 0.01933165 -0.05704207 0.18913773 -0.12833942 0.1816328 0.06035798] Embedding dimensions: 64 [b'act fire witnesses must be aware of defamation']: [-0.31556517 -0.07618773 -0.14239314 -0.14500496 0.04438541 -0.00983415 0.01349827 -0.15908629 -0.12947078 0.31871504] Embedding dimensions: 64 [b'a g calls for infrastructure protection summit']: [ 0.15422247 -0.09829048 -0.16913125 -0.17129296 0.01204466 -0.16008876 -0.00540507 -0.20552996 0.11388192 -0.03878446] Embedding dimensions: 64 [b'air nz staff in aust strike for pay rise']: [ 0.13039729 -0.06921542 -0.08830801 -0.09704516 -0.05936369 -0.13036506 -0.16644046 -0.06228216 0.00742535 -0.13592219]
3. Zbuduj indeks SNN dla osadzania
ANNOY (Approximate Nearest Neighbours Oh Yeah) to biblioteka C++ z powiązaniami z Pythonem, służąca do wyszukiwania punktów w przestrzeni znajdujących się blisko danego punktu zapytania. Tworzy również duże struktury danych oparte na plikach tylko do odczytu, które są mapowane w pamięci. Jest zbudowany i używany przez Spotify do rekomendacji muzycznych.
def build_index(embedding_files_pattern, index_filename, vector_length,
metric='angular', num_trees=100):
'''Builds an ANNOY index'''
annoy_index = annoy.AnnoyIndex(vector_length, metric=metric)
# Mapping between the item and its identifier in the index
mapping = {}
embed_files = tf.gfile.Glob(embedding_files_pattern)
print('Found {} embedding file(s).'.format(len(embed_files)))
item_counter = 0
for f, embed_file in enumerate(embed_files):
print('Loading embeddings in file {} of {}...'.format(
f+1, len(embed_files)))
record_iterator = tf.io.tf_record_iterator(
path=embed_file)
for string_record in record_iterator:
example = tf.train.Example()
example.ParseFromString(string_record)
text = example.features.feature['text'].bytes_list.value[0].decode("utf-8")
mapping[item_counter] = text
embedding = np.array(
example.features.feature['embedding'].float_list.value)
annoy_index.add_item(item_counter, embedding)
item_counter += 1
if item_counter % 100000 == 0:
print('{} items loaded to the index'.format(item_counter))
print('A total of {} items added to the index'.format(item_counter))
print('Building the index with {} trees...'.format(num_trees))
annoy_index.build(n_trees=num_trees)
print('Index is successfully built.')
print('Saving index to disk...')
annoy_index.save(index_filename)
print('Index is saved to disk.')
print("Index file size: {} GB".format(
round(os.path.getsize(index_filename) / float(1024 ** 3), 2)))
annoy_index.unload()
print('Saving mapping to disk...')
with open(index_filename + '.mapping', 'wb') as handle:
pickle.dump(mapping, handle, protocol=pickle.HIGHEST_PROTOCOL)
print('Mapping is saved to disk.')
print("Mapping file size: {} MB".format(
round(os.path.getsize(index_filename + '.mapping') / float(1024 ** 2), 2)))
embedding_files = "{}/emb-*.tfrecords".format(output_dir)
embedding_dimension = projected_dim
index_filename = "index"
!rm {index_filename}
!rm {index_filename}.mapping
%time build_index(embedding_files, index_filename, embedding_dimension)
rm: cannot remove 'index': No such file or directory rm: cannot remove 'index.mapping': No such file or directory Found 1 embedding file(s). Loading embeddings in file 1 of 1... 100000 items loaded to the index 200000 items loaded to the index 300000 items loaded to the index 400000 items loaded to the index 500000 items loaded to the index 600000 items loaded to the index 700000 items loaded to the index 800000 items loaded to the index 900000 items loaded to the index 1000000 items loaded to the index 1100000 items loaded to the index A total of 1103664 items added to the index Building the index with 100 trees... Index is successfully built. Saving index to disk... Index is saved to disk. Index file size: 1.66 GB Saving mapping to disk... Mapping is saved to disk. Mapping file size: 50.61 MB CPU times: user 6min 10s, sys: 3.7 s, total: 6min 14s Wall time: 1min 36s
lscorpus index.mapping raw.tsv index random_projection_matrix semantic_approximate_nearest_neighbors.ipynb
4. Użyj indeksu do dopasowywania podobieństw
Teraz możemy użyć indeksu ANN, aby znaleźć nagłówki wiadomości, które są semantycznie zbliżone do zapytania wejściowego.
Załaduj indeks i pliki mapowania
index = annoy.AnnoyIndex(embedding_dimension)
index.load(index_filename, prefault=True)
print('Annoy index is loaded.')
with open(index_filename + '.mapping', 'rb') as handle:
mapping = pickle.load(handle)
print('Mapping file is loaded.')
Annoy index is loaded. /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/ipykernel_launcher.py:1: FutureWarning: The default argument for metric will be removed in future version of Annoy. Please pass metric='angular' explicitly. """Entry point for launching an IPython kernel. Mapping file is loaded.
Metoda dopasowywania podobieństw
def find_similar_items(embedding, num_matches=5):
'''Finds similar items to a given embedding in the ANN index'''
ids = index.get_nns_by_vector(
embedding, num_matches, search_k=-1, include_distances=False)
items = [mapping[i] for i in ids]
return items
Wyodrębnij osadzanie z danego zapytania
# Load the TF-Hub module
print("Loading the TF-Hub module...")
g = tf.Graph()
with g.as_default():
embed_fn = load_module(module_url)
print("TF-Hub module is loaded.")
random_projection_matrix = None
if os.path.exists('random_projection_matrix'):
print("Loading random projection matrix...")
with open('random_projection_matrix', 'rb') as handle:
random_projection_matrix = pickle.load(handle)
print('random projection matrix is loaded.')
def extract_embeddings(query):
'''Generates the embedding for the query'''
query_embedding = embed_fn([query])[0]
if random_projection_matrix is not None:
query_embedding = query_embedding.dot(random_projection_matrix)
return query_embedding
Loading the TF-Hub module... INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore TF-Hub module is loaded. TF-Hub module is loaded. Loading random projection matrix... random projection matrix is loaded.
extract_embeddings("Hello Machine Learning!")[:10]
array([-0.06277051, 0.14012653, -0.15893948, 0.15775941, -0.1226441 ,
-0.11202384, 0.07953477, -0.08003543, 0.03763271, 0.0302215 ])
Wprowadź zapytanie, aby znaleźć najbardziej podobne elementy
query = "confronting global challenges"
print("Generating embedding for the query...")
%time query_embedding = extract_embeddings(query)
print("")
print("Finding relevant items in the index...")
%time items = find_similar_items(query_embedding, 10)
print("")
print("Results:")
print("=========")
for item in items:
print(item)
Generating embedding for the query... CPU times: user 32.9 ms, sys: 19.8 ms, total: 52.7 ms Wall time: 6.96 ms Finding relevant items in the index... CPU times: user 7.19 ms, sys: 370 µs, total: 7.56 ms Wall time: 953 µs Results: ========= confronting global challenges downer challenges un to follow aust example fairfax loses oshane challenge jericho social media and the border farce territory on search for raw comedy talent interview gred jericho interview: josh frydenberg; environment and energy interview: josh frydenberg; environment and energy world science festival music and climate change interview with aussie bobsledder
Chcesz dowiedzieć się więcej?
Możesz dowiedzieć się więcej o TensorFlow na tensorflow.org i zapoznać się z dokumentacją API TF-Hub na tensorflow.org/hub . Znajdź dostępne moduły TensorFlow Hub na tfhub.dev, w tym więcej modułów do osadzania tekstu i modułów wektorów funkcji obrazu.
Zapoznaj się także z przyspieszonym kursem uczenia maszynowego , który stanowi szybkie, praktyczne wprowadzenie Google do uczenia maszynowego.