Python layers.TimeDistributed方法代码示例

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import TimeDistributed [as 别名]
def conv_unit(inp, n_gram, no_word=200, window=2):
    out = Conv1D(no_word, window, strides=1, padding="valid", activation='relu')(inp)
    out = TimeDistributed(Dense(5, input_shape=(n_gram, no_word)))(out)
    out = ZeroPadding1D(padding=(0, window - 1))(out)
    return out 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import TimeDistributed [as 别名]
def _create_keras_model(self):
        # Each input sample consists of a bag of x`MAX_CONTEXTS` tuples (source_terminal, path, target_terminal).
        # The valid mask indicates for each context whether it actually exists or it is just a padding.
        path_source_token_input = Input((self.config.MAX_CONTEXTS,), dtype=tf.int32)
        path_input = Input((self.config.MAX_CONTEXTS,), dtype=tf.int32)
        path_target_token_input = Input((self.config.MAX_CONTEXTS,), dtype=tf.int32)
        context_valid_mask = Input((self.config.MAX_CONTEXTS,))

        # Input paths are indexes, we embed these here.
        paths_embedded = Embedding(
            self.vocabs.path_vocab.size, self.config.PATH_EMBEDDINGS_SIZE, name='path_embedding')(path_input)

        # Input terminals are indexes, we embed these here.
        token_embedding_shared_layer = Embedding(
            self.vocabs.token_vocab.size, self.config.TOKEN_EMBEDDINGS_SIZE, name='token_embedding')
        path_source_token_embedded = token_embedding_shared_layer(path_source_token_input)
        path_target_token_embedded = token_embedding_shared_layer(path_target_token_input)

        # `Context` is a concatenation of the 2 terminals & path embedding.
        # Each context is a vector of size 3 * EMBEDDINGS_SIZE.
        context_embedded = Concatenate()([path_source_token_embedded, paths_embedded, path_target_token_embedded])
        context_embedded = Dropout(1 - self.config.DROPOUT_KEEP_RATE)(context_embedded)

        # Lets get dense: Apply a dense layer for each context vector (using same weights for all of the context).
        context_after_dense = TimeDistributed(
            Dense(self.config.CODE_VECTOR_SIZE, use_bias=False, activation='tanh'))(context_embedded)

        # The final code vectors are received by applying attention to the "densed" context vectors.
        code_vectors, attention_weights = AttentionLayer(name='attention')(
            [context_after_dense, context_valid_mask])

        # "Decode": Now we use another dense layer to get the target word embedding from each code vector.
        target_index = Dense(
            self.vocabs.target_vocab.size, use_bias=False, activation='softmax', name='target_index')(code_vectors)

        # Wrap the layers into a Keras model, using our subtoken-metrics and the CE loss.
        inputs = [path_source_token_input, path_input, path_target_token_input, context_valid_mask]
        self.keras_train_model = keras.Model(inputs=inputs, outputs=target_index)

        # Actual target word predictions (as strings). Used as a second output layer.
        # Used for predict() and for the evaluation metrics calculations.
        topk_predicted_words, topk_predicted_words_scores = TopKWordPredictionsLayer(
            self.config.TOP_K_WORDS_CONSIDERED_DURING_PREDICTION,
            self.vocabs.target_vocab.get_index_to_word_lookup_table(),
            name='target_string')(target_index)

        # We use another dedicated Keras model for evaluation.
        # The evaluation model outputs the `topk_predicted_words` as a 2nd output.
        # The separation between train and eval models is for efficiency.
        self.keras_eval_model = keras.Model(
            inputs=inputs, outputs=[target_index, topk_predicted_words], name="code2vec-keras-model")

        # We use another dedicated Keras function to produce predictions.
        # It have additional outputs than the original model.
        # It is based on the trained layers of the original model and uses their weights.
        predict_outputs = tuple(KerasPredictionModelOutput(
            target_index=target_index, code_vectors=code_vectors, attention_weights=attention_weights,
            topk_predicted_words=topk_predicted_words, topk_predicted_words_scores=topk_predicted_words_scores))
        self.keras_model_predict_function = K.function(inputs=inputs, outputs=predict_outputs)