文本分类模型对比

使用kashgari快速搭建文本分类模型,对比各个模型间的正确率。
import kashgari
from kashgari.embeddings import BERTEmbedding
# chinese_roberta_wwm_large
bert_embed = BERTEmbedding('chinese_roberta_wwm_large', task=kashgari.CLASSIFICATION, sequence_length=256)
导入数据集
from kashgari.corpus import SMP2018ECDTCorpus

# 加载内置数据集
train_x, train_y = SMP2018ECDTCorpus.load_data('train')
valid_x, valid_y = SMP2018ECDTCorpus.load_data('valid')
test_x, test_y = SMP2018ECDTCorpus.load_data('test')
train_x[0:5]
[['中', '央', '十', '一', '台'],
 ['沙', '眼', '。'],
 ['我', '想', '知', '道', '科', '大', '讯', '飞', '的', '市', '值'],
 ['打', '开', 's', 'k', 'y', '电', '话'],
 ['上', '饶', '到', '南', '昌', '的', '火', '车', '票']]
train_y[0:5]
['tvchannel', 'health', 'stock', 'app', 'train']
set(train_y)
{'app',
 'bus',
 'calc',
 'chat',
 'cinemas',
 'contacts',
 'cookbook',
 'datetime',
 'email',
 'epg',
 'flight',
 'health',
 'lottery',
 'map',
 'match',
 'message',
 'music',
 'news',
 'novel',
 'poetry',
 'radio',
 'riddle',
 'schedule',
 'stock',
 'telephone',
 'train',
 'translation',
 'tvchannel',
 'video',
 'weather',
 'website'}
len(set(train_y))
31
本数据集共31个标签,是31分类任务。

Bert_BiLSTM_Model

from kashgari.tasks.classification import BiLSTM_Model
model_1 = BiLSTM_Model(bert_embed)
model_1.fit(train_x, train_y, valid_x, valid_y,epochs=2, batch_size=64)
result_1 = model_1.evaluate(test_x, test_y)
model_1.save('model/BERT_BiLSTM.h5')
Model: "model_4"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
Input-Token (InputLayer)        [(None, 128)]        0                                            
__________________________________________________________________________________________________
Input-Segment (InputLayer)      [(None, 128)]        0                                            
__________________________________________________________________________________________________
Embedding-Token (TokenEmbedding [(None, 128, 1024),  21635072    Input-Token[0][0]                
__________________________________________________________________________________________________
Embedding-Segment (Embedding)   (None, 128, 1024)    2048        Input-Segment[0][0]              
__________________________________________________________________________________________________
Embedding-Token-Segment (Add)   (None, 128, 1024)    0           Embedding-Token[0][0]            
                                                                 Embedding-Segment[0][0]          
__________________________________________________________________________________________________
Embedding-Position (PositionEmb (None, 128, 1024)    131072      Embedding-Token-Segment[0][0]    
__________________________________________________________________________________________________
Embedding-Dropout (Dropout)     (None, 128, 1024)    0           Embedding-Position[0][0]         
__________________________________________________________________________________________________
Embedding-Norm (LayerNormalizat (None, 128, 1024)    2048        Embedding-Dropout[0][0]          
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Embedding-Norm[0][0]             
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-1-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    0           Embedding-Norm[0][0]             
                                                                 Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-1-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-1-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-1-MultiHeadSelfAttention-
                                                                 Encoder-1-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-1-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-1-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-1-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-2-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-1-FeedForward-Norm[0][0] 
                                                                 Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-2-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-2-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-2-MultiHeadSelfAttention-
                                                                 Encoder-2-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-2-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-2-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-2-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-3-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-2-FeedForward-Norm[0][0] 
                                                                 Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-3-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-3-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-3-MultiHeadSelfAttention-
                                                                 Encoder-3-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-3-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-3-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-3-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-4-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-3-FeedForward-Norm[0][0] 
                                                                 Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-4-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-4-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-4-MultiHeadSelfAttention-
                                                                 Encoder-4-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-4-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-4-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-4-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-5-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-4-FeedForward-Norm[0][0] 
                                                                 Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-5-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-5-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-5-MultiHeadSelfAttention-
                                                                 Encoder-5-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-5-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-5-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-5-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-6-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-5-FeedForward-Norm[0][0] 
                                                                 Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-6-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-6-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-6-MultiHeadSelfAttention-
                                                                 Encoder-6-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-6-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-6-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-6-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-7-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-6-FeedForward-Norm[0][0] 
                                                                 Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-7-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-7-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-7-MultiHeadSelfAttention-
                                                                 Encoder-7-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-7-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-7-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-7-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-8-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-7-FeedForward-Norm[0][0] 
                                                                 Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-8-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-8-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-8-MultiHeadSelfAttention-
                                                                 Encoder-8-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-8-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-8-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-8-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-9-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-8-FeedForward-Norm[0][0] 
                                                                 Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-9-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-9-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-9-MultiHeadSelfAttention-
                                                                 Encoder-9-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-9-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-9-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-9-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-9-FeedForward-Norm[0][0] 
                                                                 Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-10-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-10-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-10-MultiHeadSelfAttention
                                                                 Encoder-10-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-10-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-10-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-10-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-10-FeedForward-Norm[0][0]
                                                                 Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-11-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-11-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-11-MultiHeadSelfAttention
                                                                 Encoder-11-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-11-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-11-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-11-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-11-FeedForward-Norm[0][0]
                                                                 Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-12-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-12-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-12-MultiHeadSelfAttention
                                                                 Encoder-12-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-12-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-12-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-12-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-12-FeedForward-Norm[0][0]
                                                                 Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-13-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-13-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-13-MultiHeadSelfAttention
                                                                 Encoder-13-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-13-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-13-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-13-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-13-FeedForward-Norm[0][0]
                                                                 Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-14-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-14-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-14-MultiHeadSelfAttention
                                                                 Encoder-14-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-14-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-14-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-14-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-14-FeedForward-Norm[0][0]
                                                                 Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-15-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-15-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-15-MultiHeadSelfAttention
                                                                 Encoder-15-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-15-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-15-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-15-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-15-FeedForward-Norm[0][0]
                                                                 Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-16-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-16-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-16-MultiHeadSelfAttention
                                                                 Encoder-16-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-16-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-16-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-16-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-16-FeedForward-Norm[0][0]
                                                                 Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-17-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-17-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-17-MultiHeadSelfAttention
                                                                 Encoder-17-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-17-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-17-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-17-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-17-FeedForward-Norm[0][0]
                                                                 Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-18-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-18-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-18-MultiHeadSelfAttention
                                                                 Encoder-18-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-18-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-18-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-18-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-18-FeedForward-Norm[0][0]
                                                                 Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-19-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-19-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-19-MultiHeadSelfAttention
                                                                 Encoder-19-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-19-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-19-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-19-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-19-FeedForward-Norm[0][0]
                                                                 Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-20-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-20-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-20-MultiHeadSelfAttention
                                                                 Encoder-20-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-20-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-20-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-20-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-20-FeedForward-Norm[0][0]
                                                                 Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-21-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-21-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-21-MultiHeadSelfAttention
                                                                 Encoder-21-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-21-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-21-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-21-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-21-FeedForward-Norm[0][0]
                                                                 Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-22-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-22-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-22-MultiHeadSelfAttention
                                                                 Encoder-22-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-22-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-22-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-22-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-22-FeedForward-Norm[0][0]
                                                                 Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-23-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-23-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-23-MultiHeadSelfAttention
                                                                 Encoder-23-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-23-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-23-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-23-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-23-FeedForward-Norm[0][0]
                                                                 Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-24-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-24-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-24-MultiHeadSelfAttention
                                                                 Encoder-24-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-24-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-24-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-Output (Concatenate)    (None, 128, 4096)    0           Encoder-21-FeedForward-Norm[0][0]
                                                                 Encoder-22-FeedForward-Norm[0][0]
                                                                 Encoder-23-FeedForward-Norm[0][0]
                                                                 Encoder-24-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
non_masking_layer (NonMaskingLa (None, 128, 4096)    0           Encoder-Output[0][0]             
__________________________________________________________________________________________________
bidirectional (Bidirectional)   (None, 256)          4326400     non_masking_layer[0][0]          
__________________________________________________________________________________________________
dense (Dense)                   (None, 31)           7967        bidirectional[0][0]              
==================================================================================================
Total params: 328,413,983
Trainable params: 4,334,367
Non-trainable params: 324,079,616
__________________________________________________________________________________________________
Epoch 1/2
30/30 [==============================] - 413s 14s/step - loss: 1.2704 - acc: 0.6885 - val_loss: 0.5361 - val_acc: 0.8517
Epoch 2/2
30/30 [==============================] - 410s 14s/step - loss: 0.3376 - acc: 0.9261 - val_loss: 0.3924 - val_acc: 0.9019
              precision    recall  f1-score   support

         app     1.0000    0.4444    0.6154        18
         bus     1.0000    0.5000    0.6667         8
        calc     1.0000    1.0000    1.0000         8
        chat     0.9490    0.9675    0.9582       154
     cinemas     0.6000    0.3750    0.4615         8
    contacts     1.0000    0.9000    0.9474        10
    cookbook     1.0000    1.0000    1.0000        89
    datetime     0.7500    1.0000    0.8571         6
       email     1.0000    0.7500    0.8571         8
         epg     0.8333    0.8333    0.8333        36
      flight     0.9524    0.9524    0.9524        21
      health     1.0000    1.0000    1.0000        19
     lottery     1.0000    1.0000    1.0000         8
         map     0.9130    0.9130    0.9130        23
       match     0.8889    1.0000    0.9412         8
     message     0.9545    1.0000    0.9767        21
       music     0.9130    0.9545    0.9333        22
        news     1.0000    0.8000    0.8889        20
       novel     0.7778    0.8750    0.8235         8
      poetry     0.9189    1.0000    0.9577        34
       radio     1.0000    0.7500    0.8571         8
      riddle     1.0000    1.0000    1.0000        11
    schedule     1.0000    0.7778    0.8750         9
       stock     1.0000    0.9583    0.9787        24
   telephone     1.0000    1.0000    1.0000        21
       train     0.8000    1.0000    0.8889        24
 translation     1.0000    0.9524    0.9756        21
   tvchannel     0.7895    0.6522    0.7143        23
       video     0.8226    0.8500    0.8361        60
     weather     0.9545    0.9545    0.9545        22
     website     0.5312    0.9444    0.6800        18

    accuracy                         0.9130       770
   macro avg     0.9145    0.8744    0.8821       770
weighted avg     0.9226    0.9130    0.9111       770

Bert_BiGRU_Model

from kashgari.tasks.classification import BiGRU_Model
model_2 = BiGRU_Model(bert_embed)
model_2.fit(train_x, train_y, valid_x, valid_y,epochs=2, batch_size=64)
result_2 = model_2.evaluate(test_x, test_y)
model_2.save('model/BERT_BiGRU.h5')
Model: "model_5"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
Input-Token (InputLayer)        [(None, 128)]        0                                            
__________________________________________________________________________________________________
Input-Segment (InputLayer)      [(None, 128)]        0                                            
__________________________________________________________________________________________________
Embedding-Token (TokenEmbedding [(None, 128, 1024),  21635072    Input-Token[0][0]                
__________________________________________________________________________________________________
Embedding-Segment (Embedding)   (None, 128, 1024)    2048        Input-Segment[0][0]              
__________________________________________________________________________________________________
Embedding-Token-Segment (Add)   (None, 128, 1024)    0           Embedding-Token[0][0]            
                                                                 Embedding-Segment[0][0]          
__________________________________________________________________________________________________
Embedding-Position (PositionEmb (None, 128, 1024)    131072      Embedding-Token-Segment[0][0]    
__________________________________________________________________________________________________
Embedding-Dropout (Dropout)     (None, 128, 1024)    0           Embedding-Position[0][0]         
__________________________________________________________________________________________________
Embedding-Norm (LayerNormalizat (None, 128, 1024)    2048        Embedding-Dropout[0][0]          
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Embedding-Norm[0][0]             
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-1-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    0           Embedding-Norm[0][0]             
                                                                 Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-1-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-1-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-1-MultiHeadSelfAttention-
                                                                 Encoder-1-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-1-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-1-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-1-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-2-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-1-FeedForward-Norm[0][0] 
                                                                 Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-2-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-2-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-2-MultiHeadSelfAttention-
                                                                 Encoder-2-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-2-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-2-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-2-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-3-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-2-FeedForward-Norm[0][0] 
                                                                 Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-3-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-3-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-3-MultiHeadSelfAttention-
                                                                 Encoder-3-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-3-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-3-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-3-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-4-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-3-FeedForward-Norm[0][0] 
                                                                 Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-4-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-4-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-4-MultiHeadSelfAttention-
                                                                 Encoder-4-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-4-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-4-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-4-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-5-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-4-FeedForward-Norm[0][0] 
                                                                 Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-5-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-5-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-5-MultiHeadSelfAttention-
                                                                 Encoder-5-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-5-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-5-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-5-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-6-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-5-FeedForward-Norm[0][0] 
                                                                 Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-6-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-6-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-6-MultiHeadSelfAttention-
                                                                 Encoder-6-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-6-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-6-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-6-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-7-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-6-FeedForward-Norm[0][0] 
                                                                 Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-7-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-7-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-7-MultiHeadSelfAttention-
                                                                 Encoder-7-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-7-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-7-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-7-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-8-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-7-FeedForward-Norm[0][0] 
                                                                 Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-8-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-8-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-8-MultiHeadSelfAttention-
                                                                 Encoder-8-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-8-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-8-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-8-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-9-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-8-FeedForward-Norm[0][0] 
                                                                 Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-9-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-9-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-9-MultiHeadSelfAttention-
                                                                 Encoder-9-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-9-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-9-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-9-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-9-FeedForward-Norm[0][0] 
                                                                 Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-10-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-10-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-10-MultiHeadSelfAttention
                                                                 Encoder-10-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-10-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-10-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-10-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-10-FeedForward-Norm[0][0]
                                                                 Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-11-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-11-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-11-MultiHeadSelfAttention
                                                                 Encoder-11-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-11-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-11-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-11-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-11-FeedForward-Norm[0][0]
                                                                 Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-12-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-12-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-12-MultiHeadSelfAttention
                                                                 Encoder-12-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-12-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-12-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-12-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-12-FeedForward-Norm[0][0]
                                                                 Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-13-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-13-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-13-MultiHeadSelfAttention
                                                                 Encoder-13-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-13-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-13-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-13-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-13-FeedForward-Norm[0][0]
                                                                 Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-14-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-14-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-14-MultiHeadSelfAttention
                                                                 Encoder-14-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-14-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-14-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-14-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-14-FeedForward-Norm[0][0]
                                                                 Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-15-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-15-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-15-MultiHeadSelfAttention
                                                                 Encoder-15-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-15-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-15-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-15-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-15-FeedForward-Norm[0][0]
                                                                 Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-16-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-16-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-16-MultiHeadSelfAttention
                                                                 Encoder-16-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-16-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-16-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-16-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-16-FeedForward-Norm[0][0]
                                                                 Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-17-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-17-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-17-MultiHeadSelfAttention
                                                                 Encoder-17-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-17-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-17-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-17-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-17-FeedForward-Norm[0][0]
                                                                 Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-18-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-18-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-18-MultiHeadSelfAttention
                                                                 Encoder-18-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-18-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-18-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-18-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-18-FeedForward-Norm[0][0]
                                                                 Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-19-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-19-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-19-MultiHeadSelfAttention
                                                                 Encoder-19-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-19-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-19-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-19-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-19-FeedForward-Norm[0][0]
                                                                 Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-20-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-20-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-20-MultiHeadSelfAttention
                                                                 Encoder-20-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-20-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-20-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-20-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-20-FeedForward-Norm[0][0]
                                                                 Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-21-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-21-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-21-MultiHeadSelfAttention
                                                                 Encoder-21-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-21-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-21-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-21-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-21-FeedForward-Norm[0][0]
                                                                 Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-22-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-22-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-22-MultiHeadSelfAttention
                                                                 Encoder-22-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-22-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-22-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-22-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-22-FeedForward-Norm[0][0]
                                                                 Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-23-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-23-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-23-MultiHeadSelfAttention
                                                                 Encoder-23-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-23-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-23-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-23-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-23-FeedForward-Norm[0][0]
                                                                 Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-24-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-24-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-24-MultiHeadSelfAttention
                                                                 Encoder-24-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-24-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-24-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-Output (Concatenate)    (None, 128, 4096)    0           Encoder-21-FeedForward-Norm[0][0]
                                                                 Encoder-22-FeedForward-Norm[0][0]
                                                                 Encoder-23-FeedForward-Norm[0][0]
                                                                 Encoder-24-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
non_masking_layer (NonMaskingLa (None, 128, 4096)    0           Encoder-Output[0][0]             
__________________________________________________________________________________________________
bidirectional_1 (Bidirectional) (None, 256)          3244800     non_masking_layer[0][0]          
__________________________________________________________________________________________________
dense_1 (Dense)                 (None, 31)           7967        bidirectional_1[0][0]            
==================================================================================================
Total params: 327,332,383
Trainable params: 3,252,767
Non-trainable params: 324,079,616
__________________________________________________________________________________________________
Epoch 1/2
30/30 [==============================] - 413s 14s/step - loss: 1.3147 - acc: 0.6805 - val_loss: 0.4360 - val_acc: 0.8923
Epoch 2/2
30/30 [==============================] - 410s 14s/step - loss: 0.2226 - acc: 0.9452 - val_loss: 0.2943 - val_acc: 0.9282
              precision    recall  f1-score   support

         app     0.8235    0.7778    0.8000        18
         bus     1.0000    0.8750    0.9333         8
        calc     1.0000    1.0000    1.0000         8
        chat     0.9671    0.9545    0.9608       154
     cinemas     0.5714    0.5000    0.5333         8
    contacts     0.8333    1.0000    0.9091        10
    cookbook     1.0000    1.0000    1.0000        89
    datetime     0.7500    1.0000    0.8571         6
       email     0.8750    0.8750    0.8750         8
         epg     0.8857    0.8611    0.8732        36
      flight     0.9545    1.0000    0.9767        21
      health     1.0000    1.0000    1.0000        19
     lottery     1.0000    1.0000    1.0000         8
         map     0.8846    1.0000    0.9388        23
       match     0.8000    1.0000    0.8889         8
     message     0.9545    1.0000    0.9767        21
       music     0.8636    0.8636    0.8636        22
        news     0.8636    0.9500    0.9048        20
       novel     1.0000    0.8750    0.9333         8
      poetry     0.9167    0.9706    0.9429        34
       radio     1.0000    0.7500    0.8571         8
      riddle     1.0000    1.0000    1.0000        11
    schedule     1.0000    0.7778    0.8750         9
       stock     1.0000    0.9583    0.9787        24
   telephone     1.0000    1.0000    1.0000        21
       train     0.9600    1.0000    0.9796        24
 translation     0.9091    0.9524    0.9302        21
   tvchannel     0.8421    0.6957    0.7619        23
       video     0.9153    0.9000    0.9076        60
     weather     0.9545    0.9545    0.9545        22
     website     0.8333    0.8333    0.8333        18

    accuracy                         0.9338       770
   macro avg     0.9148    0.9137    0.9112       770
weighted avg     0.9347    0.9338    0.9329       770

Bert_CNN_Model

from kashgari.tasks.classification import CNN_Model
model_3 = CNN_Model(bert_embed)
model_3.fit(train_x, train_y, valid_x, valid_y,epochs=2, batch_size=64)
result_3 = model_3.evaluate(test_x, test_y)
model_3.save('model/BERT_CNN.h5')
Model: "model_6"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
Input-Token (InputLayer)        [(None, 128)]        0                                            
__________________________________________________________________________________________________
Input-Segment (InputLayer)      [(None, 128)]        0                                            
__________________________________________________________________________________________________
Embedding-Token (TokenEmbedding [(None, 128, 1024),  21635072    Input-Token[0][0]                
__________________________________________________________________________________________________
Embedding-Segment (Embedding)   (None, 128, 1024)    2048        Input-Segment[0][0]              
__________________________________________________________________________________________________
Embedding-Token-Segment (Add)   (None, 128, 1024)    0           Embedding-Token[0][0]            
                                                                 Embedding-Segment[0][0]          
__________________________________________________________________________________________________
Embedding-Position (PositionEmb (None, 128, 1024)    131072      Embedding-Token-Segment[0][0]    
__________________________________________________________________________________________________
Embedding-Dropout (Dropout)     (None, 128, 1024)    0           Embedding-Position[0][0]         
__________________________________________________________________________________________________
Embedding-Norm (LayerNormalizat (None, 128, 1024)    2048        Embedding-Dropout[0][0]          
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Embedding-Norm[0][0]             
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-1-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    0           Embedding-Norm[0][0]             
                                                                 Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-1-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-1-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-1-MultiHeadSelfAttention-
                                                                 Encoder-1-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-1-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-1-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-1-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-2-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-1-FeedForward-Norm[0][0] 
                                                                 Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-2-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-2-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-2-MultiHeadSelfAttention-
                                                                 Encoder-2-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-2-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-2-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-2-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-3-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-2-FeedForward-Norm[0][0] 
                                                                 Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-3-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-3-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-3-MultiHeadSelfAttention-
                                                                 Encoder-3-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-3-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-3-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-3-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-4-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-3-FeedForward-Norm[0][0] 
                                                                 Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-4-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-4-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-4-MultiHeadSelfAttention-
                                                                 Encoder-4-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-4-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-4-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-4-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-5-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-4-FeedForward-Norm[0][0] 
                                                                 Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-5-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-5-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-5-MultiHeadSelfAttention-
                                                                 Encoder-5-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-5-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-5-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-5-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-6-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-5-FeedForward-Norm[0][0] 
                                                                 Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-6-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-6-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-6-MultiHeadSelfAttention-
                                                                 Encoder-6-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-6-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-6-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-6-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-7-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-6-FeedForward-Norm[0][0] 
                                                                 Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-7-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-7-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-7-MultiHeadSelfAttention-
                                                                 Encoder-7-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-7-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-7-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-7-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-8-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-7-FeedForward-Norm[0][0] 
                                                                 Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-8-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-8-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-8-MultiHeadSelfAttention-
                                                                 Encoder-8-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-8-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-8-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-8-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-9-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-8-FeedForward-Norm[0][0] 
                                                                 Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-9-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-9-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-9-MultiHeadSelfAttention-
                                                                 Encoder-9-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-9-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-9-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-9-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-9-FeedForward-Norm[0][0] 
                                                                 Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-10-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-10-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-10-MultiHeadSelfAttention
                                                                 Encoder-10-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-10-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-10-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-10-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-10-FeedForward-Norm[0][0]
                                                                 Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-11-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-11-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-11-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-11-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-11-MultiHeadSelfAttention
                                                                 Encoder-11-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-11-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-11-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-11-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-11-FeedForward-Norm[0][0]
                                                                 Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-12-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-12-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-12-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-12-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-12-MultiHeadSelfAttention
                                                                 Encoder-12-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-12-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-12-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-12-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-12-FeedForward-Norm[0][0]
                                                                 Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-13-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-13-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-13-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-13-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-13-MultiHeadSelfAttention
                                                                 Encoder-13-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-13-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-13-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-13-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-13-FeedForward-Norm[0][0]
                                                                 Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-14-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-14-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-14-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-14-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-14-MultiHeadSelfAttention
                                                                 Encoder-14-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-14-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-14-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-14-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-14-FeedForward-Norm[0][0]
                                                                 Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-15-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-15-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-15-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-15-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-15-MultiHeadSelfAttention
                                                                 Encoder-15-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-15-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-15-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-15-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-15-FeedForward-Norm[0][0]
                                                                 Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-16-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-16-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-16-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-16-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-16-MultiHeadSelfAttention
                                                                 Encoder-16-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-16-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-16-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-16-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-16-FeedForward-Norm[0][0]
                                                                 Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-17-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-17-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-17-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-17-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-17-MultiHeadSelfAttention
                                                                 Encoder-17-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-17-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-17-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-17-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-17-FeedForward-Norm[0][0]
                                                                 Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-18-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-18-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-18-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-18-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-18-MultiHeadSelfAttention
                                                                 Encoder-18-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-18-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-18-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-18-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-18-FeedForward-Norm[0][0]
                                                                 Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-19-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-19-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-19-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-19-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-19-MultiHeadSelfAttention
                                                                 Encoder-19-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-19-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-19-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-19-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-19-FeedForward-Norm[0][0]
                                                                 Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-20-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-20-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-20-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-20-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-20-MultiHeadSelfAttention
                                                                 Encoder-20-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-20-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-20-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-20-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-20-FeedForward-Norm[0][0]
                                                                 Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-21-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-21-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-21-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-21-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-21-MultiHeadSelfAttention
                                                                 Encoder-21-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-21-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-21-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-21-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-21-FeedForward-Norm[0][0]
                                                                 Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-22-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-22-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-22-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-22-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-22-MultiHeadSelfAttention
                                                                 Encoder-22-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-22-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-22-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-22-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-22-FeedForward-Norm[0][0]
                                                                 Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-23-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-23-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-23-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-23-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-23-MultiHeadSelfAttention
                                                                 Encoder-23-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-23-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-23-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-23-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-23-FeedForward-Norm[0][0]
                                                                 Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-24-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-24-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-24-FeedForward[0][0]     
__________________________________________________________________________________________________
Encoder-24-FeedForward-Add (Add (None, 128, 1024)    0           Encoder-24-MultiHeadSelfAttention
                                                                 Encoder-24-FeedForward-Dropout[0]
__________________________________________________________________________________________________
Encoder-24-FeedForward-Norm (La (None, 128, 1024)    2048        Encoder-24-FeedForward-Add[0][0] 
__________________________________________________________________________________________________
Encoder-Output (Concatenate)    (None, 128, 4096)    0           Encoder-21-FeedForward-Norm[0][0]
                                                                 Encoder-22-FeedForward-Norm[0][0]
                                                                 Encoder-23-FeedForward-Norm[0][0]
                                                                 Encoder-24-FeedForward-Norm[0][0]
__________________________________________________________________________________________________
non_masking_layer (NonMaskingLa (None, 128, 4096)    0           Encoder-Output[0][0]             
__________________________________________________________________________________________________
conv1d (Conv1D)                 (None, 124, 128)     2621568     non_masking_layer[0][0]          
__________________________________________________________________________________________________
global_max_pooling1d (GlobalMax (None, 128)          0           conv1d[0][0]                     
__________________________________________________________________________________________________
dense_2 (Dense)                 (None, 64)           8256        global_max_pooling1d[0][0]       
__________________________________________________________________________________________________
dense_3 (Dense)                 (None, 31)           2015        dense_2[0][0]                    
==================================================================================================
Total params: 326,711,455
Trainable params: 2,631,839
Non-trainable params: 324,079,616
__________________________________________________________________________________________________
Epoch 1/2
30/30 [==============================] - 372s 12s/step - loss: 2.0315 - acc: 0.5742 - val_loss: 0.7069 - val_acc: 0.8254
Epoch 2/2
30/30 [==============================] - 369s 12s/step - loss: 0.3203 - acc: 0.9187 - val_loss: 0.4566 - val_acc: 0.8900
              precision    recall  f1-score   support

         app     0.8182    0.5000    0.6207        18
         bus     1.0000    1.0000    1.0000         8
        calc     1.0000    0.8750    0.9333         8
        chat     0.9551    0.9675    0.9613       154
     cinemas     0.5000    0.5000    0.5000         8
    contacts     1.0000    1.0000    1.0000        10
    cookbook     1.0000    1.0000    1.0000        89
    datetime     0.7143    0.8333    0.7692         6
       email     0.7500    0.7500    0.7500         8
         epg     0.8000    0.8889    0.8421        36
      flight     0.9091    0.9524    0.9302        21
      health     1.0000    0.9474    0.9730        19
     lottery     1.0000    1.0000    1.0000         8
         map     0.9565    0.9565    0.9565        23
       match     0.7273    1.0000    0.8421         8
     message     0.9524    0.9524    0.9524        21
       music     0.9286    0.5909    0.7222        22
        news     0.9091    1.0000    0.9524        20
       novel     1.0000    0.8750    0.9333         8
      poetry     0.8500    1.0000    0.9189        34
       radio     1.0000    0.6250    0.7692         8
      riddle     1.0000    1.0000    1.0000        11
    schedule     1.0000    0.7778    0.8750         9
       stock     1.0000    0.9583    0.9787        24
   telephone     1.0000    1.0000    1.0000        21
       train     0.9600    1.0000    0.9796        24
 translation     1.0000    0.9524    0.9756        21
   tvchannel     0.7391    0.7391    0.7391        23
       video     0.8103    0.7833    0.7966        60
     weather     0.9524    0.9091    0.9302        22
     website     0.6154    0.8889    0.7273        18

    accuracy                         0.9091       770
   macro avg     0.8983    0.8782    0.8816       770
weighted avg     0.9143    0.9091    0.9076       770

Bert_CNN_LSTM_Model

from kashgari.tasks.classification import CNN_LSTM_Model
model_4 = CNN_LSTM_Model(bert_embed)
model_4.fit(train_x, train_y, valid_x, valid_y,epochs=2, batch_size=64)
result_4 = model_4.evaluate(test_x, test_y)
model_4.save('model/BERT_CNN_LSTM_Model.h5')
Model: "model_7"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
Input-Token (InputLayer)        [(None, 128)]        0                                            
__________________________________________________________________________________________________
Input-Segment (InputLayer)      [(None, 128)]        0                                            
__________________________________________________________________________________________________
Embedding-Token (TokenEmbedding [(None, 128, 1024),  21635072    Input-Token[0][0]                
__________________________________________________________________________________________________
Embedding-Segment (Embedding)   (None, 128, 1024)    2048        Input-Segment[0][0]              
__________________________________________________________________________________________________
Embedding-Token-Segment (Add)   (None, 128, 1024)    0           Embedding-Token[0][0]            
                                                                 Embedding-Segment[0][0]          
__________________________________________________________________________________________________
Embedding-Position (PositionEmb (None, 128, 1024)    131072      Embedding-Token-Segment[0][0]    
__________________________________________________________________________________________________
Embedding-Dropout (Dropout)     (None, 128, 1024)    0           Embedding-Position[0][0]         
__________________________________________________________________________________________________
Embedding-Norm (LayerNormalizat (None, 128, 1024)    2048        Embedding-Dropout[0][0]          
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Embedding-Norm[0][0]             
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-1-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    0           Embedding-Norm[0][0]             
                                                                 Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-1-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-1-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-1-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-1-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-1-MultiHeadSelfAttention-
                                                                 Encoder-1-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-1-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-1-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-1-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-2-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-1-FeedForward-Norm[0][0] 
                                                                 Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-2-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-2-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-2-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-2-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-2-MultiHeadSelfAttention-
                                                                 Encoder-2-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-2-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-2-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-2-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-3-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-2-FeedForward-Norm[0][0] 
                                                                 Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-3-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-3-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-3-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-3-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-3-MultiHeadSelfAttention-
                                                                 Encoder-3-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-3-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-3-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-3-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-4-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-3-FeedForward-Norm[0][0] 
                                                                 Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-4-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-4-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-4-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-4-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-4-MultiHeadSelfAttention-
                                                                 Encoder-4-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-4-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-4-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-4-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-5-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-4-FeedForward-Norm[0][0] 
                                                                 Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-5-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-5-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-5-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-5-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-5-MultiHeadSelfAttention-
                                                                 Encoder-5-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-5-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-5-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-5-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-6-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-5-FeedForward-Norm[0][0] 
                                                                 Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-6-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-6-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-6-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-6-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-6-MultiHeadSelfAttention-
                                                                 Encoder-6-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-6-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-6-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-6-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-7-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-6-FeedForward-Norm[0][0] 
                                                                 Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-7-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-7-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-7-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-7-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-7-MultiHeadSelfAttention-
                                                                 Encoder-7-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-7-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-7-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-7-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-8-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-7-FeedForward-Norm[0][0] 
                                                                 Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-8-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-8-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-8-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-8-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-8-MultiHeadSelfAttention-
                                                                 Encoder-8-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-8-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-8-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    4198400     Encoder-8-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-9-MultiHeadSelfAttention[
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    0           Encoder-8-FeedForward-Norm[0][0] 
                                                                 Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-MultiHeadSelfAttentio (None, 128, 1024)    2048        Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-FeedForward (FeedForw (None, 128, 1024)    8393728     Encoder-9-MultiHeadSelfAttention-
__________________________________________________________________________________________________
Encoder-9-FeedForward-Dropout ( (None, 128, 1024)    0           Encoder-9-FeedForward[0][0]      
__________________________________________________________________________________________________
Encoder-9-FeedForward-Add (Add) (None, 128, 1024)    0           Encoder-9-MultiHeadSelfAttention-
                                                                 Encoder-9-FeedForward-Dropout[0][
__________________________________________________________________________________________________
Encoder-9-FeedForward-Norm (Lay (None, 128, 1024)    2048        Encoder-9-FeedForward-Add[0][0]  
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    4198400     Encoder-9-FeedForward-Norm[0][0] 
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    0           Encoder-9-FeedForward-Norm[0][0] 
                                                                 Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-MultiHeadSelfAttenti (None, 128, 1024)    2048        Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-FeedForward (FeedFor (None, 128, 1024)    8393728     Encoder-10-MultiHeadSelfAttention
__________________________________________________________________________________________________
Encoder-10-FeedForward-Dropout  (None, 128, 1024)    0           Encoder-10-FeedForward[0][0]     
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值