model_entailment.py 文件源码

def define_attention_model(self):
        # Take necessary parts out of the entailment model to get OntoLSTM attention.
        if not self.model:
            raise RuntimeError, "Model not trained yet!"
        # We need just one input to get attention. input_shape_at(0) gives a list with two shapes.
        input_shape = self.model.get_input_shape_at(0)[0]
        input_layer = Input(input_shape[1:], dtype='int32')  # removing batch size
        embedding_layer = None
        encoder_layer = None
        for layer in self.model.layers:
            if layer.name == "embedding":
                embedding_layer = layer
            elif layer.name == "encoder":
                # We need to redefine the OntoLSTM layer with the learned weights and set return attention to True.
                # Assuming we'll want attention values for all words (return_sequences = True)
                encoder_layer = OntoAttentionLSTM(input_dim=self.embed_dim,
                                                  output_dim=self.embed_dim, num_senses=self.num_senses,
                                                  num_hyps=self.num_hyps, use_attention=True,
                                                  return_attention=True, return_sequences=True,
                                                  weights=layer.get_weights())
        if not embedding_layer or not encoder_layer:
            raise RuntimeError, "Required layers not found!"
        attention_output = encoder_layer(embedding_layer(input_layer))
        self.attention_model = Model(input=input_layer, output=attention_output)
        self.attention_model.compile(loss="mse", optimizer="sgd")  # Loss and optimizer do not matter!