I’m trying to understand how to alter some code from the Tensorflow Recommenders tutorial. Specifically wanted to understand how to change references to embedding variables in the call function of the Movie Model
Movie Model:
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)
If I change the call function to:
def call(self, inputs):
return tf.concat([
self.title_embedding(inputs["movie_title"]),
self.title_text_embedding(inputs["movie_title"]),
], axis=1)
I get the error:
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)
When I run:
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"]})
I assumed that changing the input variable in the call function to something more specific wouldn’t change the output but for some reason this isn’t the case. I mirrored it to have similar structure to the UserModel and am not sure why it doesn’t work the same