Polecane przez TensorFlow: Szybki start

Zobacz na TensorFlow.org Uruchom w Google Colab Wyświetl źródło na GitHub Pobierz notatnik

W tym samouczku zbudować prosty model faktoryzacji macierzy przy użyciu zestawu danych MovieLens 100K z TFRS. Możemy wykorzystać ten model do polecania filmów dla danego użytkownika.

Importuj TFRS

Najpierw zainstaluj i zaimportuj TFRS:

pip install -q tensorflow-recommenders
pip install -q --upgrade tensorflow-datasets
from typing import Dict, Text

import numpy as np
import tensorflow as tf

import tensorflow_datasets as tfds
import tensorflow_recommenders as tfrs

Przeczytaj dane

# Ratings data.
ratings = tfds.load('movielens/100k-ratings', split="train")
# Features of all the available movies.
movies = tfds.load('movielens/100k-movies', split="train")

# Select the basic features.
ratings = ratings.map(lambda x: {
    "movie_title": x["movie_title"],
    "user_id": x["user_id"]
})
movies = movies.map(lambda x: x["movie_title"])
2021-10-02 12:07:32.719766: E tensorflow/stream_executor/cuda/cuda_driver.cc:271] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected

Twórz słowniki, aby konwertować identyfikatory użytkowników i tytuły filmów na indeksy liczb całkowitych w celu osadzania warstw:

user_ids_vocabulary = tf.keras.layers.StringLookup(mask_token=None)
user_ids_vocabulary.adapt(ratings.map(lambda x: x["user_id"]))

movie_titles_vocabulary = tf.keras.layers.StringLookup(mask_token=None)
movie_titles_vocabulary.adapt(movies)

Zdefiniuj model

Możemy zdefiniować model TFRS przez dziedziczenie z tfrs.Model i wdrażaniu compute_loss metodę:

class MovieLensModel(tfrs.Model):
  # We derive from a custom base class to help reduce boilerplate. Under the hood,
  # these are still plain Keras Models.

  def __init__(
      self,
      user_model: tf.keras.Model,
      movie_model: tf.keras.Model,
      task: tfrs.tasks.Retrieval):
    super().__init__()

    # Set up user and movie representations.
    self.user_model = user_model
    self.movie_model = movie_model

    # Set up a retrieval task.
    self.task = task

  def compute_loss(self, features: Dict[Text, tf.Tensor], training=False) -> tf.Tensor:
    # Define how the loss is computed.

    user_embeddings = self.user_model(features["user_id"])
    movie_embeddings = self.movie_model(features["movie_title"])

    return self.task(user_embeddings, movie_embeddings)

Zdefiniuj dwa modele i zadanie pobierania.

# Define user and movie models.
user_model = tf.keras.Sequential([
    user_ids_vocabulary,
    tf.keras.layers.Embedding(user_ids_vocabulary.vocab_size(), 64)
])
movie_model = tf.keras.Sequential([
    movie_titles_vocabulary,
    tf.keras.layers.Embedding(movie_titles_vocabulary.vocab_size(), 64)
])

# Define your objectives.
task = tfrs.tasks.Retrieval(metrics=tfrs.metrics.FactorizedTopK(
    movies.batch(128).map(movie_model)
  )
)
WARNING:tensorflow:vocab_size is deprecated, please use vocabulary_size.
WARNING:tensorflow:vocab_size is deprecated, please use vocabulary_size.
WARNING:tensorflow:vocab_size is deprecated, please use vocabulary_size.
WARNING:tensorflow:vocab_size is deprecated, please use vocabulary_size.

Dopasuj i oceń to.

Utwórz model, wytrenuj go i wygeneruj prognozy:

# Create a retrieval model.
model = MovieLensModel(user_model, movie_model, task)
model.compile(optimizer=tf.keras.optimizers.Adagrad(0.5))

# Train for 3 epochs.
model.fit(ratings.batch(4096), epochs=3)

# Use brute-force search to set up retrieval using the trained representations.
index = tfrs.layers.factorized_top_k.BruteForce(model.user_model)
index.index_from_dataset(
    movies.batch(100).map(lambda title: (title, model.movie_model(title))))

# Get some recommendations.
_, titles = index(np.array(["42"]))
print(f"Top 3 recommendations for user 42: {titles[0, :3]}")
Epoch 1/3
25/25 [==============================] - 6s 194ms/step - factorized_top_k/top_1_categorical_accuracy: 3.0000e-05 - factorized_top_k/top_5_categorical_accuracy: 0.0016 - factorized_top_k/top_10_categorical_accuracy: 0.0052 - factorized_top_k/top_50_categorical_accuracy: 0.0442 - factorized_top_k/top_100_categorical_accuracy: 0.1010 - loss: 33092.9163 - regularization_loss: 0.0000e+00 - total_loss: 33092.9163
Epoch 2/3
25/25 [==============================] - 5s 194ms/step - factorized_top_k/top_1_categorical_accuracy: 1.7000e-04 - factorized_top_k/top_5_categorical_accuracy: 0.0052 - factorized_top_k/top_10_categorical_accuracy: 0.0148 - factorized_top_k/top_50_categorical_accuracy: 0.1054 - factorized_top_k/top_100_categorical_accuracy: 0.2114 - loss: 31008.8447 - regularization_loss: 0.0000e+00 - total_loss: 31008.8447
Epoch 3/3
25/25 [==============================] - 5s 193ms/step - factorized_top_k/top_1_categorical_accuracy: 3.4000e-04 - factorized_top_k/top_5_categorical_accuracy: 0.0086 - factorized_top_k/top_10_categorical_accuracy: 0.0222 - factorized_top_k/top_50_categorical_accuracy: 0.1438 - factorized_top_k/top_100_categorical_accuracy: 0.2694 - loss: 30417.8776 - regularization_loss: 0.0000e+00 - total_loss: 30417.8776
Top 3 recommendations for user 42: [b'Rent-a-Kid (1995)' b'Just Cause (1995)'
 b'Land Before Time III: The Time of the Great Giving (1995) (V)']