很好的tuto，谢谢你，但是我有一个问题，保存模型重用它。我有这个错误
文件“C：\用户\guera\应用程序数据\本地\程序\Python\Python 310\lib\站点包\keras\实用程序\跟踪返回实用程序.py”，第67行，在错误处理程序中引发e.with_traceback（filtered_tb）来自无文件“C：\用户\guera\应用程序数据\本地\程序\Python\Python 310\lib\站点包\keras\保存\保存. py”，第142行，在保存模型中引发未实现错误（未实现错误：将模型保存为HDF5格式要求模型为函数模型或序列模型。它不适用于子类模型，因为此类模型是通过Python方法的主体定义的，无法安全地进行序列化。请考虑保存为Tensorflow SavedModel格式（通过设置save_format=“tf”）或使用save_weights。
那么如何解决它们呢？
这是我的源代码：

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 joblib

import tensorflow_recommenders as tfrs
from src.models.movie_lens import MovieLensModel

def content_based_filtering(user_id, table1, table2, user_id_label, target_label):
    # Ratings data.
    ratings = tfds.load(table1, split="train")
    # Features of all the available movies.
    movies = tfds.load(table2, split="train")
    
    # Select the basic features.
    ratings = ratings.map(lambda x: {
        "{}".format(target_label): x[target_label],
        "{}".format(user_id_label): x[user_id_label]
    })
    movies = movies.map(lambda x: x[target_label])
    
    user_ids_vocabulary = tf.keras.layers.StringLookup(mask_token=None)
    user_ids_vocabulary.adapt(ratings.map(lambda x: x[user_id_label]))

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

    model.save('content_model.h5')
    # 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([str(user_id)]))
    # print('Recommendation content based filtering\n')
    return titles[0, :3].numpy()

影片镜头型号：

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

class MovieLensModel(tfrs.Model):
    
  def __init__(self, user_model, movie_model, task):
    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)

图像错误：