Cette page a été traduite par l'API Cloud Translation.
Switch to English

Recherche sémantique avec les voisins les plus proches approximatifs et les incorporations de texte

Voir sur TensorFlow.org Exécuter dans Google Colab Afficher sur GitHub Télécharger le carnet Voir le modèle TF Hub

Ce didacticiel montre comment générer des incorporations à partir d'un module TensorFlow Hub (TF-Hub) en fonction des données d'entrée et créer un index des voisins les plus proches approximatifs (ANN) à l'aide des incorporations extraites. L'index peut ensuite être utilisé pour la correspondance et la récupération de similarité en temps réel.

Lorsqu'il s'agit d'un grand corpus de données, il n'est pas efficace d'effectuer une correspondance exacte en analysant l'ensemble du référentiel pour trouver les éléments les plus similaires à une requête donnée en temps réel. Ainsi, nous utilisons un algorithme d'appariement de similarité approximative qui nous permet de troquer un peu de précision dans la recherche de correspondances exactes du plus proche voisin pour une augmentation significative de la vitesse.

Dans ce didacticiel, nous montrons un exemple de recherche de texte en temps réel sur un corpus de titres d'actualité pour trouver les titres les plus similaires à une requête. Contrairement à la recherche par mot-clé, cela capture la similitude sémantique encodée dans l'incorporation de texte.

Les étapes de ce tutoriel sont:

  1. Téléchargez des exemples de données.
  2. Générer des embeddings pour les données à l'aide d'un module TF-Hub
  3. Créer un index ANN pour les incorporations
  4. Utilisez l'index pour la correspondance de similarité

Nous utilisons Apache Beam pour générer les incorporations à partir du module TF-Hub. Nous utilisons également la bibliothèque ANNOY de Spotify pour créer l'index approximatif des voisins les plus proches.

Plus de modèles

Pour les modèles qui ont la même architecture mais qui ont été formés sur une langue différente, reportez-vous à cette collection. Ici vous pouvez trouver toutes les incorporations de texte qui sont actuellement hébergés sur tfhub.dev .

Installer

Installez les bibliothèques requises.

pip install -q apache_beam
pip install -q sklearn
pip install -q annoy

Importez les bibliothèques requises

import os
import sys
import pickle
from collections import namedtuple
from datetime import datetime
import numpy as np
import apache_beam as beam
from apache_beam.transforms import util
import tensorflow as tf
import tensorflow_hub as hub
import annoy
from sklearn.random_projection import gaussian_random_matrix
print('TF version: {}'.format(tf.__version__))
print('TF-Hub version: {}'.format(hub.__version__))
print('Apache Beam version: {}'.format(beam.__version__))
TF version: 2.3.1
TF-Hub version: 0.9.0
Apache Beam version: 2.24.0

1. Télécharger des exemples de données

Un ensemble de données Million News Headlines contient des titres d'actualité publiés sur une période de 15 ans provenant de la réputée Australian Broadcasting Corp. (ABC). Cet ensemble de données d'actualités contient un récapitulatif historique des événements marquants dans le monde du début 2003 à la fin 2017, avec un accent plus granulaire sur l'Australie.

Format : Données à deux colonnes séparées par des tabulations: 1) date de publication et 2) texte du titre. Nous ne sommes intéressés que par le texte du titre.

wget 'https://dataverse.harvard.edu/api/access/datafile/3450625?format=tab&gbrecs=true' -O raw.tsv
wc -l raw.tsv
head raw.tsv
--2020-10-02 12:26:52--  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  27.0MB/s    in 2.0s    

2020-10-02 12:26:55 (27.0 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"

Pour plus de simplicité, nous ne conservons que le texte du titre et supprimons la date de publication

!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.txt
severe 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

2. Générez des incorporations pour les données.

Dans ce didacticiel, nous utilisons le modèle de langage de réseau neuronal (NNLM) pour générer des incorporations pour les données de titre. Les enchaînements de phrases peuvent ensuite être facilement utilisés pour calculer la similitude de signification au niveau de la phrase. Nous exécutons le processus de génération d'incorporation à l'aide d'Apache Beam.

Méthode d'extraction intégrée

embed_fn = None

def generate_embeddings(text, module_url, random_projection_matrix=None):
  # Beam will run this function in different processes that need to
  # import hub and load embed_fn (if not previously loaded)
  global embed_fn
  if embed_fn is None:
    embed_fn = hub.load(module_url)
  embedding = embed_fn(text).numpy()
  if random_projection_matrix is not None:
    embedding = embedding.dot(random_projection_matrix)
  return text, embedding

Convertir en méthode tf.Example

def to_tf_example(entries):
  examples = []

  text_list, embedding_list = entries
  for i in range(len(text_list)):
    text = text_list[i]
    embedding = embedding_list[i]

    features = {
        'text': tf.train.Feature(
            bytes_list=tf.train.BytesList(value=[text.encode('utf-8')])),
        'embedding': tf.train.Feature(
            float_list=tf.train.FloatList(value=embedding.tolist()))
    }

    example = tf.train.Example(
        features=tf.train.Features(
            feature=features)).SerializeToString(deterministic=True)

    examples.append(example)

  return examples

Pipeline de poutre

def run_hub2emb(args):
  '''Runs the embedding generation pipeline'''

  options = beam.options.pipeline_options.PipelineOptions(**args)
  args = namedtuple("options", args.keys())(*args.values())

  with beam.Pipeline(args.runner, options=options) as pipeline:
    (
        pipeline
        | 'Read sentences from files' >> beam.io.ReadFromText(
            file_pattern=args.data_dir)
        | 'Batch elements' >> util.BatchElements(
            min_batch_size=args.batch_size, max_batch_size=args.batch_size)
        | 'Generate embeddings' >> beam.Map(
            generate_embeddings, args.module_url, args.random_projection_matrix)
        | 'Encode to tf example' >> beam.FlatMap(to_tf_example)
        | 'Write to TFRecords files' >> beam.io.WriteToTFRecord(
            file_path_prefix='{}/emb'.format(args.output_dir),
            file_name_suffix='.tfrecords')
    )

Génération d'une matrice de poids de projection aléatoire

La projection aléatoire est une technique simple mais puissante utilisée pour réduire la dimensionnalité d'un ensemble de points qui se trouvent dans l'espace euclidien. Pour un contexte théorique, voir le lemme de Johnson-Lindenstrauss .

La réduction de la dimensionnalité des plongements avec une projection aléatoire signifie moins de temps nécessaire pour créer et interroger l'index ANN.

Dans ce didacticiel, nous utilisons la projection aléatoire gaussienne de la bibliothèqueScikit-learn .

def generate_random_projection_weights(original_dim, projected_dim):
  random_projection_matrix = None
  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

Définir les paramètres

Si vous souhaitez créer un index à l'aide de l'espace d'incorporation d'origine sans projection aléatoire, définissez le paramètre projected_dim sur None . Notez que cela ralentira l'étape d'indexation pour les incorporations de grande dimension.

Exécuter le pipeline

import tempfile

output_dir = tempfile.mkdtemp()
original_dim = hub.load(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,
    'module_url': module_url,
    'random_projection_matrix': random_projection_matrix,
}

print("Pipeline args are set.")
args
A Gaussian random weight matrix was creates with shape of (128, 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-201002-122712',
 'runner': 'DirectRunner',
 'batch_size': 1024,
 'data_dir': 'corpus/*.txt',
 'output_dir': '/tmp/tmp5jrvr165',
 'module_url': 'https://tfhub.dev/google/tf2-preview/nnlm-en-dim128/1',
 'random_projection_matrix': array([[-0.23496406, -0.05090818, -0.0451953 , ...,  0.12301853,
         -0.17872473,  0.16310186],
        [ 0.06431372,  0.18794477,  0.06454892, ...,  0.03056835,
          0.04524009,  0.01850725],
        [-0.12029645,  0.22026643,  0.0286414 , ...,  0.09062128,
         -0.12451738, -0.08198714],
        ...,
        [-0.07137172, -0.0165681 , -0.09059493, ...,  0.08598557,
         -0.2998788 , -0.07498167],
        [-0.08950686,  0.03670846,  0.03048793, ..., -0.1782675 ,
          0.11021995, -0.19888922],
        [-0.01926155, -0.00277134,  0.0535409 , ..., -0.00921094,
          0.23301195,  0.04889218]])}
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:5 out of the last 5 calls to <function recreate_function.<locals>.restored_function_body at 0x7f70cc0bee18> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for  more details.

Warning:tensorflow:5 out of the last 5 calls to <function recreate_function.<locals>.restored_function_body at 0x7f70cc0bee18> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for  more details.

Warning:tensorflow:6 out of the last 6 calls to <function recreate_function.<locals>.restored_function_body at 0x7f70cc0be488> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for  more details.

Warning:tensorflow:6 out of the last 6 calls to <function recreate_function.<locals>.restored_function_body at 0x7f70cc0be488> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for  more details.

Warning:tensorflow:7 out of the last 7 calls to <function recreate_function.<locals>.restored_function_body at 0x7f70cc1099d8> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for  more details.

Warning:tensorflow:7 out of the last 7 calls to <function recreate_function.<locals>.restored_function_body at 0x7f70cc1099d8> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
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 9min 13s, sys: 9min 51s, total: 19min 4s
Wall time: 2min 29s
Pipeline is done.

ls {output_dir}
emb-00000-of-00001.tfrecords

Lisez quelques-uns des intégrations générées ...

embed_file = os.path.join(output_dir, 'emb-00000-of-00001.tfrecords')
sample = 5

# Create a description of the features.
feature_description = {
    'text': tf.io.FixedLenFeature([], tf.string),
    'embedding': tf.io.FixedLenFeature([projected_dim], tf.float32)
}

def _parse_example(example):
  # Parse the input `tf.Example` proto using the dictionary above.
  return tf.io.parse_single_example(example, feature_description)

dataset = tf.data.TFRecordDataset(embed_file)
for record in dataset.take(sample).map(_parse_example):
  print("{}: {}".format(record['text'].numpy().decode('utf-8'), record['embedding'].numpy()[:10]))
headline_text: [ 0.1652589  -0.06406656  0.06406891 -0.14836317 -0.04433651 -0.01402062
 -0.04169092  0.03712815 -0.05279795 -0.06765237]
aba decides against community broadcasting licence: [-0.20160258  0.00256393  0.01182815  0.1255717  -0.08481464  0.13993788
 -0.00667449 -0.14515129  0.26369372 -0.03051737]
act fire witnesses must be aware of defamation: [-0.17959927 -0.20737727  0.15803404  0.250352    0.05415684 -0.0414118
 -0.08157488  0.05439697  0.31761077  0.00750144]
a g calls for infrastructure protection summit: [-0.306443    0.03760489  0.05141833  0.10717567 -0.09257486  0.05315739
  0.08237746  0.04033889  0.04984799 -0.04539666]
air nz staff in aust strike for pay rise: [-0.17491291 -0.04590164  0.04062048  0.1097874   0.06837258  0.23613107
 -0.17138828  0.2218      0.10151701 -0.12856439]

3. Créez l'index ANN pour les incorporations

ANNOY (Approximate Nearest Neighbors Oh Yeah) est une bibliothèque C ++ avec des liaisons Python pour rechercher des points dans l'espace proches d'un point de requête donné. Il crée également de grandes structures de données basées sur des fichiers en lecture seule qui sont mmappées en mémoire. Il est construit et utilisé par Spotify pour les recommandations musicales.

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.io.gfile.glob(embedding_files_pattern)
  num_files = len(embed_files)
  print('Found {} embedding file(s).'.format(num_files))

  item_counter = 0
  for i, embed_file in enumerate(embed_files):
    print('Loading embeddings in file {} of {}...'.format(i+1, num_files))
    dataset = tf.data.TFRecordDataset(embed_file)
    for record in dataset.map(_parse_example):
      text = record['text'].numpy().decode("utf-8")
      embedding = record['embedding'].numpy()
      mapping[item_counter] = text
      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: 1.6 GB
Saving mapping to disk...
Mapping is saved to disk.
Mapping file size: 50.61 MB
CPU times: user 9min 58s, sys: 55.4 s, total: 10min 54s
Wall time: 5min 13s

ls
corpus         random_projection_matrix
index          raw.tsv
index.mapping  tf2_semantic_approximate_nearest_neighbors.ipynb

4. Utilisez l'index pour la correspondance de similarité

Nous pouvons maintenant utiliser l'index ANN pour trouver des titres d'actualité sémantiquement proches d'une requête d'entrée.

Chargez l'index et les fichiers de mappage

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.

Méthode de correspondance de similarité

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

Extraire l'incorporation d'une requête donnée

# Load the TF-Hub module
print("Loading the TF-Hub module...")
%time embed_fn = hub.load(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].numpy()
  if random_projection_matrix is not None:
    query_embedding = query_embedding.dot(random_projection_matrix)
  return query_embedding
Loading the TF-Hub module...
CPU times: user 799 ms, sys: 643 ms, total: 1.44 s
Wall time: 1.43 s
TF-Hub module is loaded.
Loading random projection matrix...
random projection matrix is loaded.

extract_embeddings("Hello Machine Learning!")[:10]
WARNING:tensorflow:5 out of the last 1082 calls to <function recreate_function.<locals>.restored_function_body at 0x7f70cc04f7b8> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for  more details.

Warning:tensorflow:5 out of the last 1082 calls to <function recreate_function.<locals>.restored_function_body at 0x7f70cc04f7b8> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for  more details.

array([ 0.1089144 ,  0.05490944,  0.05110935, -0.15313255, -0.16363258,
        0.05206677, -0.1233749 , -0.26143147, -0.08646249, -0.22889622])

Entrez une requête pour trouver les éléments les plus similaires

Generating embedding for the query...
CPU times: user 2.4 ms, sys: 3.15 ms, total: 5.55 ms
Wall time: 3.08 ms

Finding relevant items in the index...
CPU times: user 540 µs, sys: 305 µs, total: 845 µs
Wall time: 571 µs

Results:
=========
confronting global challenges
conference examines challenges facing major cities
beef industry facing challenges
readfearn a two faced approach to cutting global emissions
industry challenges
european organic foods facing credibility crisis
regional tourism faces challenges
climate delegates ponder developing world hurdles
global food crisis sparks us survivalist resurgence
study highlights global food wastage

Envie d'en savoir plus?

Vous pouvez en savoir plus sur TensorFlow sur tensorflow.org et consulter la documentation de l'API TF-Hub sur tensorflow.org/hub . Trouvez les modules TensorFlow Hub disponibles sur tfhub.dev, y compris plus de modules d'intégration de texte et de modules vectoriels de fonctionnalités d'image.

Consultez également le cours d' initiation au machine learning, une introduction pratique et rapide de Google à l'apprentissage automatique.