 Ver no TensorFlow.org |  Executar no Google Colab |  Ver fonte no GitHub |  Baixar caderno |
Neste tutorial, vamos treinar o mesmo modelo de recuperação como fizemos na recuperação básico tutorial, mas com estratégia de distribuição.
Estava indo para:
- Obtenha nossos dados e divida-os em um conjunto de treinamento e teste.
- Configure duas GPUs virtuais e o TensorFlow MirroredStrategy.
- Implemente um modelo de recuperação usando MirroredStrategy.
- Ajuste-o com MirrorredStrategy e avalie-o.
Importações
Vamos primeiro tirar nossas importações do caminho.
pip install -q tensorflow-recommenderspip install -q --upgrade tensorflow-datasets
import os
import pprint
import tempfile
from typing import Dict, Text
import numpy as np
import tensorflow as tf
import tensorflow_datasets as tfds
import tensorflow_recommenders as tfrs
Preparando o conjunto de dados
Nós preparamos o conjunto de dados exatamente da mesma forma como fazemos na recuperação básico tutorial.
# Ratings data.
ratings = tfds.load("movielens/100k-ratings", split="train")
# Features of all the available movies.
movies = tfds.load("movielens/100k-movies", split="train")
for x in ratings.take(1).as_numpy_iterator():
pprint.pprint(x)
for x in movies.take(1).as_numpy_iterator():
pprint.pprint(x)
ratings = ratings.map(lambda x: {
"movie_title": x["movie_title"],
"user_id": x["user_id"],
})
movies = movies.map(lambda x: x["movie_title"])
tf.random.set_seed(42)
shuffled = ratings.shuffle(100_000, seed=42, reshuffle_each_iteration=False)
train = shuffled.take(80_000)
test = shuffled.skip(80_000).take(20_000)
movie_titles = movies.batch(1_000)
user_ids = ratings.batch(1_000_000).map(lambda x: x["user_id"])
unique_movie_titles = np.unique(np.concatenate(list(movie_titles)))
unique_user_ids = np.unique(np.concatenate(list(user_ids)))
unique_movie_titles[:10]
{'bucketized_user_age': 45.0,
'movie_genres': array([7]),
'movie_id': b'357',
'movie_title': b"One Flew Over the Cuckoo's Nest (1975)",
'raw_user_age': 46.0,
'timestamp': 879024327,
'user_gender': True,
'user_id': b'138',
'user_occupation_label': 4,
'user_occupation_text': b'doctor',
'user_rating': 4.0,
'user_zip_code': b'53211'}
2021-10-14 11:16:44.748468: W tensorflow/core/kernels/data/cache_dataset_ops.cc:768] The calling iterator did not fully read the dataset being cached. In order to avoid unexpected truncation of the dataset, the partially cached contents of the dataset will be discarded. This can happen if you have an input pipeline similar to `dataset.cache().take(k).repeat()`. You should use `dataset.take(k).cache().repeat()` instead.
{'movie_genres': array([4]),
'movie_id': b'1681',
'movie_title': b'You So Crazy (1994)'}
2021-10-14 11:16:45.396856: W tensorflow/core/kernels/data/cache_dataset_ops.cc:768] The calling iterator did not fully read the dataset being cached. In order to avoid unexpected truncation of the dataset, the partially cached contents of the dataset will be discarded. This can happen if you have an input pipeline similar to `dataset.cache().take(k).repeat()`. You should use `dataset.take(k).cache().repeat()` instead.
array([b"'Til There Was You (1997)", b'1-900 (1994)',
b'101 Dalmatians (1996)', b'12 Angry Men (1957)', b'187 (1997)',
b'2 Days in the Valley (1996)',
b'20,000 Leagues Under the Sea (1954)',
b'2001: A Space Odyssey (1968)',
b'3 Ninjas: High Noon At Mega Mountain (1998)',
b'39 Steps, The (1935)'], dtype=object)
Configure duas GPUs virtuais
Se você não adicionou aceleradores de GPU ao seu Colab, desconecte o runtime do Colab e faça isso agora. Precisamos da GPU para executar o código abaixo:
gpus = tf.config.list_physical_devices("GPU")
if gpus:
# Create 2 virtual GPUs with 1GB memory each
try:
tf.config.set_logical_device_configuration(
gpus[0],
[tf.config.LogicalDeviceConfiguration(memory_limit=1024),
tf.config.LogicalDeviceConfiguration(memory_limit=1024)])
logical_gpus = tf.config.list_logical_devices("GPU")
print(len(gpus), "Physical GPU,", len(logical_gpus), "Logical GPUs")
except RuntimeError as e:
# Virtual devices must be set before GPUs have been initialized
print(e)
strategy = tf.distribute.MirroredStrategy()
Virtual devices cannot be modified after being initialized
INFO:tensorflow:Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:GPU:0',)
INFO:tensorflow:Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:GPU:0',)
Implementando um modelo
Implementamos as user_model, movie_model, métricas e tarefa da mesma forma como fazemos na recuperação básico tutorial, mas envolvê-los no âmbito estratégia de distribuição:
embedding_dimension = 32
with strategy.scope():
user_model = tf.keras.Sequential([
tf.keras.layers.StringLookup(
vocabulary=unique_user_ids, mask_token=None),
# We add an additional embedding to account for unknown tokens.
tf.keras.layers.Embedding(len(unique_user_ids) + 1, embedding_dimension)
])
movie_model = tf.keras.Sequential([
tf.keras.layers.StringLookup(
vocabulary=unique_movie_titles, mask_token=None),
tf.keras.layers.Embedding(len(unique_movie_titles) + 1, embedding_dimension)
])
metrics = tfrs.metrics.FactorizedTopK(
candidates=movies.batch(128).map(movie_model)
)
task = tfrs.tasks.Retrieval(
metrics=metrics
)
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
INFO:tensorflow:Reduce to /job:localhost/replica:0/task:0/device:CPU:0 then broadcast to ('/job:localhost/replica:0/task:0/device:CPU:0',).
Agora podemos colocar tudo junto em um modelo. Este é exatamente o mesmo que na recuperação básico tutorial.
class MovielensModel(tfrs.Model):
def __init__(self, user_model, movie_model):
super().__init__()
self.movie_model: tf.keras.Model = movie_model
self.user_model: tf.keras.Model = user_model
self.task: tf.keras.layers.Layer = task
def compute_loss(self, features: Dict[Text, tf.Tensor], training=False) -> tf.Tensor:
# We pick out the user features and pass them into the user model.
user_embeddings = self.user_model(features["user_id"])
# And pick out the movie features and pass them into the movie model,
# getting embeddings back.
positive_movie_embeddings = self.movie_model(features["movie_title"])
# The task computes the loss and the metrics.
return self.task(user_embeddings, positive_movie_embeddings)
Ajustando e avaliando
Agora instanciamos e compilamos o modelo dentro do escopo da estratégia de distribuição.
Note que estamos usando Adam otimizador aqui em vez de Adagrad como na recuperação básico tutorial desde Adagrad não é suportado aqui.
with strategy.scope():
model = MovielensModel(user_model, movie_model)
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.1))
Em seguida, embaralhe, agrupe e armazene em cache os dados de treinamento e avaliação.
cached_train = train.shuffle(100_000).batch(8192).cache()
cached_test = test.batch(4096).cache()
Em seguida, treine o modelo:
model.fit(cached_train, epochs=3)
2021-10-14 11:16:50.692190: W tensorflow/core/grappler/optimizers/data/auto_shard.cc:461] The `assert_cardinality` transformation is currently not handled by the auto-shard rewrite and will be removed. Epoch 1/3 10/10 [==============================] - 8s 328ms/step - factorized_top_k/top_1_categorical_accuracy: 5.0000e-05 - factorized_top_k/top_5_categorical_accuracy: 8.2500e-04 - factorized_top_k/top_10_categorical_accuracy: 0.0025 - factorized_top_k/top_50_categorical_accuracy: 0.0220 - factorized_top_k/top_100_categorical_accuracy: 0.0537 - loss: 70189.8047 - regularization_loss: 0.0000e+00 - total_loss: 70189.8047 Epoch 2/3 10/10 [==============================] - 3s 329ms/step - factorized_top_k/top_1_categorical_accuracy: 3.3750e-04 - factorized_top_k/top_5_categorical_accuracy: 0.0113 - factorized_top_k/top_10_categorical_accuracy: 0.0251 - factorized_top_k/top_50_categorical_accuracy: 0.1268 - factorized_top_k/top_100_categorical_accuracy: 0.2325 - loss: 66736.4560 - regularization_loss: 0.0000e+00 - total_loss: 66736.4560 Epoch 3/3 10/10 [==============================] - 3s 332ms/step - factorized_top_k/top_1_categorical_accuracy: 0.0012 - factorized_top_k/top_5_categorical_accuracy: 0.0198 - factorized_top_k/top_10_categorical_accuracy: 0.0417 - factorized_top_k/top_50_categorical_accuracy: 0.1834 - factorized_top_k/top_100_categorical_accuracy: 0.3138 - loss: 64871.2997 - regularization_loss: 0.0000e+00 - total_loss: 64871.2997 <keras.callbacks.History at 0x7fb74c479190>
Você pode ver no log de treinamento que o TFRS está usando ambas as GPUs virtuais.
Finalmente, podemos avaliar nosso modelo no conjunto de teste:
model.evaluate(cached_test, return_dict=True)
2021-10-14 11:17:05.371963: W tensorflow/core/grappler/optimizers/data/auto_shard.cc:461] The `assert_cardinality` transformation is currently not handled by the auto-shard rewrite and will be removed.
5/5 [==============================] - 4s 193ms/step - factorized_top_k/top_1_categorical_accuracy: 5.0000e-05 - factorized_top_k/top_5_categorical_accuracy: 0.0013 - factorized_top_k/top_10_categorical_accuracy: 0.0043 - factorized_top_k/top_50_categorical_accuracy: 0.0639 - factorized_top_k/top_100_categorical_accuracy: 0.1531 - loss: 32404.8092 - regularization_loss: 0.0000e+00 - total_loss: 32404.8092
{'factorized_top_k/top_1_categorical_accuracy': 4.999999873689376e-05,
'factorized_top_k/top_5_categorical_accuracy': 0.0013000000035390258,
'factorized_top_k/top_10_categorical_accuracy': 0.00430000014603138,
'factorized_top_k/top_50_categorical_accuracy': 0.06385000050067902,
'factorized_top_k/top_100_categorical_accuracy': 0.1530500054359436,
'loss': 29363.98046875,
'regularization_loss': 0,
'total_loss': 29363.98046875}
Isso conclui a recuperação com o tutorial de estratégia de distribuição.