了解Tensorflow Recommenders嵌入模型

我试图了解如何修改Tensorflow Recommenders教程中的一些代码。特别想了解如何更改对Movie模型调用函数中嵌入变量的引用

电影模型

class MovieModel(tf.keras.Model):

  def __init__(self):
    super().__init__()

    max_tokens = 10_000

    self.title_embedding = tf.keras.Sequential([
      tf.keras.layers.StringLookup(
          vocabulary=unique_movie_titles, mask_token=None),
      tf.keras.layers.Embedding(len(unique_movie_titles) + 1, 32)
    ])

    self.title_vectorizer = tf.keras.layers.TextVectorization(
        max_tokens=max_tokens)

    self.title_text_embedding = tf.keras.Sequential([
      self.title_vectorizer,
      tf.keras.layers.Embedding(max_tokens, 32, mask_zero=True),
      tf.keras.layers.GlobalAveragePooling1D(),
    ])

    self.title_vectorizer.adapt(movies)

  def call(self, titles):
    return tf.concat([
        self.title_embedding(titles),
        self.title_text_embedding(titles),
    ], axis=1)

如果我改变：

  def call(self, titles):
    return tf.concat([
        self.title_embedding(titles),
        self.title_text_embedding(titles),
    ], axis=1)

至：

  def call(self, inputs):
    return tf.concat([
        self.title_embedding(inputs["movie_title"]),
        self.title_text_embedding(inputs["movie_title"]),
    ], axis=1)

我得到了错误：

TypeError: Only integers, slices (`:`), ellipsis (`...`), tf.newaxis (`None`) and scalar tf.int32/tf.int64 tensors are valid indices, got 'movie_title'


Call arguments received:
  • inputs=tf.Tensor(shape=(None,), dtype=string)

当我运行组合的用户和电影模型时：

class MovielensModel(tfrs.models.Model):

  def __init__(self, use_timestamps):
    super().__init__()
    self.query_model = tf.keras.Sequential([
      UserModel(use_timestamps),
      tf.keras.layers.Dense(32)
    ])
    self.candidate_model = tf.keras.Sequential([
      MovieModel(),
      tf.keras.layers.Dense(32)
    ])
    self.task = tfrs.tasks.Retrieval(
        metrics=tfrs.metrics.FactorizedTopK(
            candidates=movies.batch(128).map(self.candidate_model),
        ),
    )

  def compute_loss(self, features, training=False):
    # We only pass the user id and timestamp features into the query model. This
    # is to ensure that the training inputs would have the same keys as the
    # query inputs. Otherwise the discrepancy in input structure would cause an
    # error when loading the query model after saving it.
    query_embeddings = self.query_model({
        "user_id": features["user_id"],
        "timestamp": features["timestamp"],
    })
    movie_embeddings = self.candidate_model({"movie_title":features["movie_title"]})

    return self.task(query_embeddings, movie_embeddings)

我假设将调用函数中的输入变量更改为更具体的变量不会更改输出，但出于某种原因，情况并非如此。我将其镜像为具有与UserModel相似的结构，但不确定为什么它不能以相同的方式工作

用户模型：

class UserModel(tf.keras.Model):

  def __init__(self, use_timestamps):
    super().__init__()

    self._use_timestamps = use_timestamps

    self.user_embedding = tf.keras.Sequential([
        tf.keras.layers.StringLookup(
            vocabulary=unique_user_ids, mask_token=None),
        tf.keras.layers.Embedding(len(unique_user_ids) + 1, 32),
    ])

    if use_timestamps:
      self.timestamp_embedding = tf.keras.Sequential([
          tf.keras.layers.Discretization(timestamp_buckets.tolist()),
          tf.keras.layers.Embedding(len(timestamp_buckets) + 1, 32),
      ])
      self.normalized_timestamp = tf.keras.layers.Normalization(
          axis=None
      )

      self.normalized_timestamp.adapt(timestamps)

  def call(self, inputs):
    if not self._use_timestamps:
      return self.user_embedding(inputs["user_id"])

    return tf.concat([
        self.user_embedding(inputs["user_id"]),
        self.timestamp_embedding(inputs["timestamp"]),
        tf.reshape(self.normalized_timestamp(inputs["timestamp"]), (-1, 1)),
    ], axis=1)