How to use the deepctr.layers.sequence.AttentionSequencePoolingLayer function in deepctr

tr_input = sess_interest_division(embedding_dict, user_behavior_input_dict, sparse_feature_columns,
                                      sess_feature_list, sess_max_count, bias_encoding=bias_encoding)

    Self_Attention = Transformer(att_embedding_size, att_head_num, dropout_rate=0, use_layer_norm=False,
                                 use_positional_encoding=(not bias_encoding), seed=seed, supports_masking=True,
                                 blinding=True)
    sess_fea = sess_interest_extractor(
        tr_input, sess_max_count, Self_Attention)

    interest_attention_layer = AttentionSequencePoolingLayer(att_hidden_units=(64, 16), weight_normalization=True,
                                                             supports_masking=False)(
        [query_emb, sess_fea, user_sess_length])

    lstm_outputs = BiLSTM(hist_emb_size,
                          layers=2, res_layers=0, dropout_rate=0.2, )(sess_fea)
    lstm_attention_layer = AttentionSequencePoolingLayer(att_hidden_units=(64, 16), weight_normalization=True)(
        [query_emb, lstm_outputs, user_sess_length])

    dnn_input_emb = Concatenate()(
        [dnn_input_emb, Flatten()(interest_attention_layer), Flatten()(lstm_attention_layer)])

    dnn_input_emb = combined_dnn_input([dnn_input_emb], dense_value_list)
    output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn,
                 dnn_dropout, dnn_use_bn, seed)(dnn_input_emb)
    output = Dense(1, use_bias=False, activation=None)(output)
    output = PredictionLayer(task)(output)

    sess_input_list = []
    # sess_input_length_list = []
    for i in range(sess_max_count):
        sess_name = "sess_" + str(i)
        sess_input_list.extend(get_inputs_list(

Transformer, DynamicGRU)
from .utils import NoMask, Hash,Linear,Add

custom_objects = {'tf': tf,
                  'InnerProductLayer': InnerProductLayer,
                  'OutterProductLayer': OutterProductLayer,
                  'DNN': DNN,
                  'PredictionLayer': PredictionLayer,
                  'FM': FM,
                  'AFMLayer': AFMLayer,
                  'CrossNet': CrossNet,
                  'BiInteractionPooling': BiInteractionPooling,
                  'LocalActivationUnit': LocalActivationUnit,
                  'Dice': Dice,
                  'SequencePoolingLayer': SequencePoolingLayer,
                  'AttentionSequencePoolingLayer': AttentionSequencePoolingLayer,
                  'CIN': CIN,
                  'InteractingLayer': InteractingLayer,
                  'LayerNormalization': LayerNormalization,
                  'BiLSTM': BiLSTM,
                  'Transformer': Transformer,
                  'NoMask': NoMask,
                  'BiasEncoding': BiasEncoding,
                  'KMaxPooling': KMaxPooling,
                  'FGCNNLayer': FGCNNLayer,
                  'Hash': Hash,
                  'Linear':Linear,
                  'DynamicGRU': DynamicGRU,
                  'SENETLayer':SENETLayer,
                  'BilinearInteraction':BilinearInteraction,
                  'WeightedSequenceLayer':WeightedSequenceLayer,
                  'Add':Add

deep_input_emb_list = get_embedding_vec_list(sparse_embedding_dict, sparse_input, feature_dim_dict["sparse"],
                                                 mask_feat_list=sess_feature_list)
    deep_input_emb = concat_fun(deep_input_emb_list)
    deep_input_emb = Flatten()(NoMask()(deep_input_emb))

    tr_input = sess_interest_division(sparse_embedding_dict, user_behavior_input_dict, feature_dim_dict['sparse'],
                                      sess_feature_list, sess_max_count, bias_encoding=bias_encoding)

    Self_Attention = Transformer(att_embedding_size, att_head_num, dropout_rate=0, use_layer_norm=False,
                                 use_positional_encoding=(not bias_encoding), seed=seed, supports_masking=True,
                                 blinding=True)
    sess_fea = sess_interest_extractor(
        tr_input, sess_max_count, Self_Attention)

    interest_attention_layer = AttentionSequencePoolingLayer(att_hidden_units=(64, 16), weight_normalization=True,
                                                             supports_masking=False)(
        [query_emb, sess_fea, user_sess_length])

    lstm_outputs = BiLSTM(len(sess_feature_list) * embedding_size,
                          layers=2, res_layers=0, dropout_rate=0.2, )(sess_fea)
    lstm_attention_layer = AttentionSequencePoolingLayer(att_hidden_units=(64, 16), weight_normalization=True)(
        [query_emb, lstm_outputs, user_sess_length])

    deep_input_emb = Concatenate()(
        [deep_input_emb, Flatten()(interest_attention_layer), Flatten()(lstm_attention_layer)])
    if len(dense_input) > 0:
        deep_input_emb = Concatenate()(
            [deep_input_emb] + list(dense_input.values()))

    output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn,
                 dnn_dropout, dnn_use_bn, seed)(deep_input_emb)

tr_input = sess_interest_division(sparse_embedding_dict, user_behavior_input_dict, feature_dim_dict['sparse'],
                                      sess_feature_list, sess_max_count, bias_encoding=bias_encoding)

    Self_Attention = Transformer(att_embedding_size, att_head_num, dropout_rate=0, use_layer_norm=False,
                                 use_positional_encoding=(not bias_encoding), seed=seed, supports_masking=True,
                                 blinding=True)
    sess_fea = sess_interest_extractor(
        tr_input, sess_max_count, Self_Attention)

    interest_attention_layer = AttentionSequencePoolingLayer(att_hidden_units=(64, 16), weight_normalization=True,
                                                             supports_masking=False)(
        [query_emb, sess_fea, user_sess_length])

    lstm_outputs = BiLSTM(len(sess_feature_list) * embedding_size,
                          layers=2, res_layers=0, dropout_rate=0.2, )(sess_fea)
    lstm_attention_layer = AttentionSequencePoolingLayer(att_hidden_units=(64, 16), weight_normalization=True)(
        [query_emb, lstm_outputs, user_sess_length])

    deep_input_emb = Concatenate()(
        [deep_input_emb, Flatten()(interest_attention_layer), Flatten()(lstm_attention_layer)])
    if len(dense_input) > 0:
        deep_input_emb = Concatenate()(
            [deep_input_emb] + list(dense_input.values()))

    output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn,
                 dnn_dropout, dnn_use_bn, seed)(deep_input_emb)
    output = Dense(1, use_bias=False, activation=None)(output)
    output = PredictionLayer(task)(output)

    sess_input_list = []
    # sess_input_length_list = []
    for i in range(sess_max_count):

if gru_type == "GRU":
        rnn_outputs2 = DynamicGRU(embedding_size, return_sequence=True,
                                  name="gru2")([rnn_outputs, user_behavior_length])
        # attention_score = AttentionSequencePoolingLayer(hidden_size=att_hidden_size, activation=att_activation, weight_normalization=att_weight_normalization, return_score=True)([
        #     deep_input_item, rnn_outputs2, user_behavior_length])
        # outputs = Lambda(lambda x: tf.matmul(x[0], x[1]))(
        #     [attention_score, rnn_outputs2])
        # hist = outputs
        hist = AttentionSequencePoolingLayer(att_hidden_units=att_hidden_size, att_activation=att_activation,
                                             weight_normalization=att_weight_normalization, return_score=False)([
            deep_input_item, rnn_outputs2, user_behavior_length])

    else:  # AIGRU AGRU AUGRU

        scores = AttentionSequencePoolingLayer(att_hidden_units=att_hidden_size, att_activation=att_activation,
                                               weight_normalization=att_weight_normalization, return_score=True)([
            deep_input_item, rnn_outputs, user_behavior_length])

        if gru_type == "AIGRU":
            hist = multiply([rnn_outputs, Permute([2, 1])(scores)])
            final_state2 = DynamicGRU(embedding_size, gru_type="GRU", return_sequence=False, name='gru2')(
                [hist, user_behavior_length])
        else:  # AGRU AUGRU
            final_state2 = DynamicGRU(embedding_size, gru_type=gru_type, return_sequence=False,
                                      name='gru2')([rnn_outputs, user_behavior_length, Permute([2, 1])(scores)])
        hist = final_state2
    return hist, aux_loss_1

if gru_type == "AUGRU" and use_neg:
        aux_loss_1 = auxiliary_loss(rnn_outputs[:, :-1, :], concat_behavior[:, 1:, :],

                                    neg_concat_behavior[:, 1:, :],

                                    tf.subtract(user_behavior_length, 1), stag="gru")  # [:, 1:]

    if gru_type == "GRU":
        rnn_outputs2 = DynamicGRU(embedding_size, return_sequence=True,
                                  name="gru2")([rnn_outputs, user_behavior_length])
        # attention_score = AttentionSequencePoolingLayer(hidden_size=att_hidden_size, activation=att_activation, weight_normalization=att_weight_normalization, return_score=True)([
        #     deep_input_item, rnn_outputs2, user_behavior_length])
        # outputs = Lambda(lambda x: tf.matmul(x[0], x[1]))(
        #     [attention_score, rnn_outputs2])
        # hist = outputs
        hist = AttentionSequencePoolingLayer(att_hidden_units=att_hidden_size, att_activation=att_activation,
                                             weight_normalization=att_weight_normalization, return_score=False)([
            deep_input_item, rnn_outputs2, user_behavior_length])

    else:  # AIGRU AGRU AUGRU

        scores = AttentionSequencePoolingLayer(att_hidden_units=att_hidden_size, att_activation=att_activation,
                                               weight_normalization=att_weight_normalization, return_score=True)([
            deep_input_item, rnn_outputs, user_behavior_length])

        if gru_type == "AIGRU":
            hist = multiply([rnn_outputs, Permute([2, 1])(scores)])
            final_state2 = DynamicGRU(embedding_size, gru_type="GRU", return_sequence=False, name='gru2')(
                [hist, user_behavior_length])
        else:  # AGRU AUGRU
            final_state2 = DynamicGRU(embedding_size, gru_type=gru_type, return_sequence=False,
                                      name='gru2')([rnn_outputs, user_behavior_length, Permute([2, 1])(scores)])

dense_value_list = get_dense_input(features, dense_feature_columns)

    query_emb = concat_func(query_emb_list, mask=True)

    dnn_input_emb = Flatten()(concat_func(dnn_input_emb_list))

    tr_input = sess_interest_division(embedding_dict, user_behavior_input_dict, sparse_feature_columns,
                                      sess_feature_list, sess_max_count, bias_encoding=bias_encoding)

    Self_Attention = Transformer(att_embedding_size, att_head_num, dropout_rate=0, use_layer_norm=False,
                                 use_positional_encoding=(not bias_encoding), seed=seed, supports_masking=True,
                                 blinding=True)
    sess_fea = sess_interest_extractor(
        tr_input, sess_max_count, Self_Attention)

    interest_attention_layer = AttentionSequencePoolingLayer(att_hidden_units=(64, 16), weight_normalization=True,
                                                             supports_masking=False)(
        [query_emb, sess_fea, user_sess_length])

    lstm_outputs = BiLSTM(hist_emb_size,
                          layers=2, res_layers=0, dropout_rate=0.2, )(sess_fea)
    lstm_attention_layer = AttentionSequencePoolingLayer(att_hidden_units=(64, 16), weight_normalization=True)(
        [query_emb, lstm_outputs, user_sess_length])

    dnn_input_emb = Concatenate()(
        [dnn_input_emb, Flatten()(interest_attention_layer), Flatten()(lstm_attention_layer)])

    dnn_input_emb = combined_dnn_input([dnn_input_emb], dense_value_list)
    output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn,
                 dnn_dropout, dnn_use_bn, seed)(dnn_input_emb)
    output = Dense(1, use_bias=False, activation=None)(output)
    output = PredictionLayer(task)(output)