Skip to content

M
models

PaddlePaddle / models
1 年多 前同步成功

通知 222
Star 6828
Fork 2962
M
models

Port sequence_tagging_for_ner to Python3 !1166

!1166 已合并 由 saxon_zh@saxon_zh 创建

Created by: velconia

What we get in Python3 env

[TestSet] pass_id:993 pass_precision:[1.] pass_recall:[0.0625] pass_f1_score:[0.11764706]                                                                                [266/1816]
[9.785494]                                                                                                                                                                         
Pass 994, Batch 0, Cost 9.785494, Precision 1.0, Recall 0.13333334, F1_score0.23529413                                                                                             
[TrainSet] pass_id:994 pass_precision:[1.] pass_recall:[0.13333334] pass_f1_score:[0.23529412]                                                                                     
[TestSet] pass_id:994 pass_precision:[0.] pass_recall:[0.] pass_f1_score:[0.]                                                                                                      
[9.235923]                                                                                                                                                                         
Pass 995, Batch 0, Cost 9.235923, Precision 0.6666667, Recall 0.13333334, F1_score0.22222224                                                                                       
[TrainSet] pass_id:995 pass_precision:[0.6666667] pass_recall:[0.13333334] pass_f1_score:[0.22222222]                                                                              
[TestSet] pass_id:995 pass_precision:[1.] pass_recall:[0.0625] pass_f1_score:[0.11764706]                                                                                          
[9.701894]                                                                                                                                                                         
Pass 996, Batch 0, Cost 9.701894, Precision 1.0, Recall 0.13333334, F1_score0.23529413                                                                                             
[TrainSet] pass_id:996 pass_precision:[1.] pass_recall:[0.13333334] pass_f1_score:[0.23529412]                
[TestSet] pass_id:996 pass_precision:[0.] pass_recall:[0.] pass_f1_score:[0.]    
[9.249712]                                                                    
Pass 997, Batch 0, Cost 9.249712, Precision 0.6666667, Recall 0.13333334, F1_score0.22222224                                                                              
[TrainSet] pass_id:997 pass_precision:[0.6666667] pass_recall:[0.13333334] pass_f1_score:[0.22222222]
[TestSet] pass_id:997 pass_precision:[1.] pass_recall:[0.0625] pass_f1_score:[0.11764706]                                                                                 
[9.772681]               
Pass 998, Batch 0, Cost 9.772681, Precision 1.0, Recall 0.13333334, F1_score0.23529413
[TrainSet] pass_id:998 pass_precision:[1.] pass_recall:[0.13333334] pass_f1_score:[0.23529412]
[TestSet] pass_id:998 pass_precision:[0.] pass_recall:[0.] pass_f1_score:[0.]                                                                                             
[9.213273]               
Pass 999, Batch 0, Cost 9.213273, Precision 0.6666667, Recall 0.13333334, F1_score0.22222224                                                                              
[TrainSet] pass_id:999 pass_precision:[0.6666667] pass_recall:[0.13333334] pass_f1_score:[0.22222222]
[TestSet] pass_id:999 pass_precision:[1.] pass_recall:[0.0625] pass_f1_score:[0.11764706

What we get in Python2

[TestSet] pass_id:993 pass_precision:[0.] pass_recall:[0.] pass_f1_score:[0.]
[9.699361]
Pass 994, Batch 0, Cost 9.699361, Precision 0.6666667, Recall 0.13333334, F1_score0.22222224
[TrainSet] pass_id:994 pass_precision:[0.6666667] pass_recall:[0.13333334] pass_f1_score:[0.22222222]
[TestSet] pass_id:994 pass_precision:[0.] pass_recall:[0.] pass_f1_score:[0.]
[9.390462]
Pass 995, Batch 0, Cost 9.390462, Precision 0.6666667, Recall 0.13333334, F1_score0.22222224
[TrainSet] pass_id:995 pass_precision:[0.6666667] pass_recall:[0.13333334] pass_f1_score:[0.22222222]
[TestSet] pass_id:995 pass_precision:[0.] pass_recall:[0.] pass_f1_score:[0.]
[9.693841]
Pass 996, Batch 0, Cost 9.693841, Precision 0.6666667, Recall 0.13333334, F1_score0.22222224
[TrainSet] pass_id:996 pass_precision:[0.6666667] pass_recall:[0.13333334] pass_f1_score:[0.22222222]
[TestSet] pass_id:996 pass_precision:[0.] pass_recall:[0.] pass_f1_score:[0.]
[9.384099]
Pass 997, Batch 0, Cost 9.384099, Precision 0.6666667, Recall 0.13333334, F1_score0.22222224
[TrainSet] pass_id:997 pass_precision:[0.6666667] pass_recall:[0.13333334] pass_f1_score:[0.22222222]
[TestSet] pass_id:997 pass_precision:[0.] pass_recall:[0.] pass_f1_score:[0.]
[9.6883335]
Pass 998, Batch 0, Cost 9.6883335, Precision 0.6666667, Recall 0.13333334, F1_score0.22222224
[TrainSet] pass_id:998 pass_precision:[0.6666667] pass_recall:[0.13333334] pass_f1_score:[0.22222222]
[TestSet] pass_id:998 pass_precision:[0.] pass_recall:[0.] pass_f1_score:[0.]
[9.377722]
Pass 999, Batch 0, Cost 9.377722, Precision 0.6666667, Recall 0.13333334, F1_score0.22222224
[TrainSet] pass_id:999 pass_precision:[0.6666667] pass_recall:[0.13333334] pass_f1_score:[0.22222222]
[TestSet] pass_id:999 pass_precision:[0.] pass_recall:[0.] pass_f1_score:[0.]