~WhM!rdZddlmcmZddlmZddlmZedGddeZ dS)zAttention layer that can be used in sequence DNN/CNN models. This file follows the terminology of https://arxiv.org/abs/1706.03762 Figure 2. Attention is formed by three tensors: Query, Key and Value. N)BaseDenseAttention) keras_exportzkeras.layers.Attentionc>eZdZdZdfd ZfdZdZfdZxZS) AttentionaDot-product attention layer, a.k.a. Luong-style attention. Inputs are `query` tensor of shape `[batch_size, Tq, dim]`, `value` tensor of shape `[batch_size, Tv, dim]` and `key` tensor of shape `[batch_size, Tv, dim]`. The calculation follows the steps: 1. Calculate scores with shape `[batch_size, Tq, Tv]` as a `query`-`key` dot product: `scores = tf.matmul(query, key, transpose_b=True)`. 2. Use scores to calculate a distribution with shape `[batch_size, Tq, Tv]`: `distribution = tf.nn.softmax(scores)`. 3. Use `distribution` to create a linear combination of `value` with shape `[batch_size, Tq, dim]`: `return tf.matmul(distribution, value)`. Args: use_scale: If `True`, will create a scalar variable to scale the attention scores. dropout: Float between 0 and 1. Fraction of the units to drop for the attention scores. Defaults to 0.0. score_mode: Function to use to compute attention scores, one of `{"dot", "concat"}`. `"dot"` refers to the dot product between the query and key vectors. `"concat"` refers to the hyperbolic tangent of the concatenation of the query and key vectors. Call Args: inputs: List of the following tensors: * query: Query `Tensor` of shape `[batch_size, Tq, dim]`. * value: Value `Tensor` of shape `[batch_size, Tv, dim]`. * key: Optional key `Tensor` of shape `[batch_size, Tv, dim]`. If not given, will use `value` for both `key` and `value`, which is the most common case. mask: List of the following tensors: * query_mask: A boolean mask `Tensor` of shape `[batch_size, Tq]`. If given, the output will be zero at the positions where `mask==False`. * value_mask: A boolean mask `Tensor` of shape `[batch_size, Tv]`. If given, will apply the mask such that values at positions where `mask==False` do not contribute to the result. return_attention_scores: bool, it `True`, returns the attention scores (after masking and softmax) as an additional output argument. training: Python boolean indicating whether the layer should behave in training mode (adding dropout) or in inference mode (no dropout). use_causal_mask: Boolean. Set to `True` for decoder self-attention. Adds a mask such that position `i` cannot attend to positions `j > i`. This prevents the flow of information from the future towards the past. Defaults to `False`. Output: Attention outputs of shape `[batch_size, Tq, dim]`. [Optional] Attention scores after masking and softmax with shape `[batch_size, Tq, Tv]`. The meaning of `query`, `value` and `key` depend on the application. In the case of text similarity, for example, `query` is the sequence embeddings of the first piece of text and `value` is the sequence embeddings of the second piece of text. `key` is usually the same tensor as `value`. Here is a code example for using `Attention` in a CNN+Attention network: ```python # Variable-length int sequences. query_input = tf.keras.Input(shape=(None,), dtype='int32') value_input = tf.keras.Input(shape=(None,), dtype='int32') # Embedding lookup. token_embedding = tf.keras.layers.Embedding(input_dim=1000, output_dim=64) # Query embeddings of shape [batch_size, Tq, dimension]. query_embeddings = token_embedding(query_input) # Value embeddings of shape [batch_size, Tv, dimension]. value_embeddings = token_embedding(value_input) # CNN layer. cnn_layer = tf.keras.layers.Conv1D( filters=100, kernel_size=4, # Use 'same' padding so outputs have the same shape as inputs. padding='same') # Query encoding of shape [batch_size, Tq, filters]. query_seq_encoding = cnn_layer(query_embeddings) # Value encoding of shape [batch_size, Tv, filters]. value_seq_encoding = cnn_layer(value_embeddings) # Query-value attention of shape [batch_size, Tq, filters]. query_value_attention_seq = tf.keras.layers.Attention()( [query_seq_encoding, value_seq_encoding]) # Reduce over the sequence axis to produce encodings of shape # [batch_size, filters]. query_encoding = tf.keras.layers.GlobalAveragePooling1D()( query_seq_encoding) query_value_attention = tf.keras.layers.GlobalAveragePooling1D()( query_value_attention_seq) # Concatenate query and document encodings to produce a DNN input layer. input_layer = tf.keras.layers.Concatenate()( [query_encoding, query_value_attention]) # Add DNN layers, and create Model. # ... ``` Fdotc tjdi|||_||_|jdvrt d|ddS)N)rconcatzReceived: score_mode=z*. Acceptable values are: ["dot", "concat"])super__init__ use_scale score_mode ValueError)selfr rkwargs __class__s f/var/www/html/movieo_spanner_bot/venv/lib/python3.11/site-packages/keras/layers/attention/attention.pyr zAttention.__init__sl""6""""$ ?"3 3 3) )))  4 3c|jr%|ddd|jd|_nd|_|jdkr%|ddd|jd|_nd|_t |dS) zNCreates variable when `use_scale` is True or `score_mode` is `concat`.scaler onesT)nameshape initializerdtype trainableNr concat_score_weight)r add_weightrrrrr build)r input_shapers rrzAttention.builds > "j )DJJDJ ?h & &'+*"j (7((D $ $(,D $  k"""""rc|jdkr)tj||d}|j ||jz}n|jdkrtj|d}tj|d}|j<|jtjtj|j||zzd z}n3|jtjtj||zd z}|S) aCalculates attention scores as a query-key dot product. Args: query: Query tensor of shape `[batch_size, Tq, dim]`. key: Key tensor of shape `[batch_size, Tv, dim]`. Returns: Tensor of shape `[batch_size, Tq, Tv]`. rT) transpose_bNr )axis)rtfmatmulr expand_dimsr reduce_sumtanh)rquerykeyscores q_reshaped k_reshapeds r_calculate_scoreszAttention._calculate_scoress ?e # #Yuct<<rCs"!!!!!!!!JJJJJJ:99999&''mFmFmFmFmF"mFmF('mFmFmFr