o i e?@sdZddlmZddlmZddlmZddlmmZddl m Z ddl m Z ddl mZdd lmZed gd Gd d d e jZGdddejjjZejddZdS)zHA layer that produces a dense `Tensor` based on given `feature_columns`.)absolute_import)division)print_functionN)base_feature_layer)dense_features) tf_contextlib) keras_exportzkeras.layers.DenseFeatures)v1cs.eZdZdZdfdd ZfddZZS) DenseFeaturesa0A layer that produces a dense `Tensor` based on given `feature_columns`. Generally a single example in training data is described with FeatureColumns. At the first layer of the model, this column oriented data should be converted to a single `Tensor`. This layer can be called multiple times with different features. This is the V2 version of this layer that uses name_scopes to create variables instead of variable_scopes. But this approach currently lacks support for partitioned variables. In that case, use the V1 version instead. Example: ```python price = tf.feature_column.numeric_column('price') keywords_embedded = tf.feature_column.embedding_column( tf.feature_column.categorical_column_with_hash_bucket("keywords", 10000), dimensions=16) columns = [price, keywords_embedded, ...] feature_layer = tf.keras.layers.DenseFeatures(columns) features = tf.io.parse_example( ..., features=tf.feature_column.make_parse_example_spec(columns)) dense_tensor = feature_layer(features) for units in [128, 64, 32]: dense_tensor = tf.keras.layers.Dense(units, activation='relu')( dense_tensor) prediction = tf.keras.layers.Dense(1)(dense_tensor) ``` TNc s,tjd|||d|t||j|_dS)a&Creates a DenseFeatures object. Args: feature_columns: An iterable containing the FeatureColumns to use as inputs to your model. All items should be instances of classes derived from `DenseColumn` such as `numeric_column`, `embedding_column`, `bucketized_column`, `indicator_column`. If you have categorical features, you can wrap them with an `embedding_column` or `indicator_column`. trainable: Boolean, whether the layer's variables will be updated via gradient descent during training. name: Name to give to the DenseFeatures. **kwargs: Keyword arguments to construct a layer. Raises: ValueError: if an item in `feature_columns` is not a `DenseColumn`. )feature_columns trainablenameN)super__init___StateManagerImplV2r _state_manager)selfr r r kwargs __class__rY/var/www/myenv/lib/python3.10/site-packages/keras/src/feature_column/dense_features_v2.pyrBszDenseFeatures.__init__c sZ|jD]}t|j||jWdn1swYqttj| ddS)N) _feature_columnstf name_scoper create_staterrkfc_BaseFeaturesLayerbuild)r_columnrrrr\s zDenseFeatures.build)TN)__name__ __module__ __qualname____doc__rr __classcell__rrrrr s!r c@s"eZdZdZ    dddZdS)rz#Manages the state of DenseFeatures.NTc Cs||j|vr tdt|j|jj|||||jo||d}Wdn1s*wYt|tjj j rC|j ||j d|||j||<|S)NzVariable already exists.)r shapedtype initializerr use_resource/) _cols_to_vars_map ValueError#no_manual_dependency_tracking_scope_layer add_weight _trainable isinstancer __internal__tracking Trackable_track_trackabler ) rfeature_columnr r&r'r r)r(varrrrcreate_variablehs    z#_StateManagerImplV2.create_variable)NTTN)r!r"r#r$r8rrrrresrccs0t|dd}d|_z dVW||_dS||_w)aA context that disables manual dependency tracking for the given `obj`. Sometimes library methods might track objects on their own and we might want to disable that and do the tracking on our own. One can then use this context manager to disable the tracking the library method does and do your own tracking. For example: class TestLayer(tf.keras.Layer): def build(): with no_manual_dependency_tracking_scope(self): var = self.add_weight("name1") # Creates a var and doesn't track it # We track variable with name `name2` self._track_trackable("name2", var) Args: obj: A trackable object. Yields: a scope in which the object doesn't track dependencies manually. _manual_trackingTFN)getattrr9)objprevious_valuerrrr-s  r-)r$ __future__rrrtensorflow.compat.v2compatv2rkeras.src.feature_columnrrrkeras.src.utilsr tensorflow.python.util.tf_exportrr r2r6 StateManagerrcontextmanagerr-rrrrs        E!