python - Model.fit() is returning "This model has not yet been built. Build the model first by calling `build()` or calling `fit()` with some data"

Question

When running a model.fit(train_ds, epochs=10, validation_data=val_ds), I'm receiving the error "ValueError: This model has not yet been built. Build the model first by calling build() or calling fit() with some data, or specify an input_shape argument in the first layer(s) for automatic build."

I'm very confused, because i'm trying to run exactly what the error is suggesting that needs to happen. I've followed the structured data tutorial to the T.

I've verified that the datasets I'm passing contain data

Any help would be greatly appreciated... I'm spinning my wheels. Tried both tf 2.3.* and 2.4.*

customersDf = pd.DataFrame({"Name":['joe','frank','bob','eleanore'],'target':[1,1,2,2,]})
train, test = train_test_split(customersDf, test_size = 0.2)
train, val = train_test_split(train, test_size = 0.2)
print(len(train))
print(len(test))
print(len(val))

batch_size = 2048

train_ds = df_to_dataset(train, batch_size=batch_size)

val_ds = df_to_dataset(val, shuffle=False, batch_size=batch_size)

test_ds = df_to_dataset(test, shuffle=False, batch_size=batch_size)

feature_columns = []

name1 = feature_column.categorical_column_with_vocabulary_list(
      'Name', customersDf.Name.unique())

name1_embedding = feature_column.embedding_column(name1, dimension=12)

feature_columns.append(name1_embedding)

feature_layer = tf.keras.layers.DenseFeatures(feature_columns)

model = tf.keras.Sequential([
  feature_layer,
  layers.Dense(128, activation='relu'),
  layers.Dense(128, activation='relu'),
  layers.Dropout(.1),
  layers.Dense(1)
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
              metrics=['accuracy'])
              
model.fit(train_ds, epochs=10, validation_data=val_ds)

Answer 1

等待大神答复