Upload 10 files

src/ml_ner.py

@@ -8,7 +8,7 @@ Created on Fri Jun 12 16:41:54 2020
 import io
 import time
 import numpy as np
-from keras import backend as K
+
 def ml_intext(infile):
     fin=open(infile,'r',encoding='utf-8')
     alltexts=fin.read().strip().split('\n\n')
@@ -462,7 +462,7 @@ def combine_strategy(test_decode_temp, T=0.8):
     return fout.getvalue() 
 
 
-def model_predict(session,ml_input,nn_model,ml_input_txt,ml_input_index,Threshold):
+def model_predict(ml_input,nn_model,ml_input_txt,ml_input_index,Threshold):
     if nn_model.model_type=='cnn':
         #startTime=time.time()
         test_set,test_label = ml_intext_fn(ml_input)
@@ -482,7 +482,6 @@ def model_predict(session,ml_input,nn_model,ml_input_txt,ml_input_index,Threshol
             input_test.append(test_x[3])
         # print('ml-model-represent:',time.time()-startTime)
         # startTime=time.time()
-        K.set_session(session)
         test_pre = nn_model.model.predict(input_test)
         # print('ml-model-predict:',time.time()-startTime)
     
@@ -492,10 +491,6 @@ def model_predict(session,ml_input,nn_model,ml_input_txt,ml_input_index,Threshol
         test_x,test_y=nn_model.rep.load_data(test_set,test_label,word_max_len=nn_model.maxlen)
         #print('ml-model-represent:',time.time()-startTime)
         #startTime=time.time()
-        #K.set_session(session)
-        #with session.as_default():
-            #with session.graph.as_default():
-                #print('......session')
         test_pre = nn_model.model.predict(test_x)
         #print('ml-model-modedpred:',time.time()-startTime)
     # startTime=time.time()
@@ -527,19 +522,15 @@ def model_predict_old(ml_input,nn_model,ml_input_txt,ml_input_index,Threshold):
 
         if nn_model.fea_dict['pos'] == 1:
             input_test.append(test_x[3])
-        K.set_session(nn_model.session)
-        with nn_model.session.as_default():
-            with nn_model.session.graph.as_default():
-                test_pre = nn_model.model.predict(input_test,batch_size=256)
+       
+        test_pre = nn_model.model.predict(input_test,batch_size=256)
 
     elif nn_model.model_type=='bert' or nn_model.model_type=='bioformer':
 
         test_set,test_label = ml_intext_fn(ml_input)
         test_x,test_y=nn_model.rep.load_data(test_set,test_label,word_max_len=nn_model.maxlen)
-        K.set_session(nn_model.session)
-        with nn_model.session.as_default():
-            with nn_model.session.graph.as_default():
-                test_pre = nn_model.model.predict(test_x,batch_size=128)
+       
+        test_pre = nn_model.model.predict(test_x,batch_size=128)
 
     test_score=output_result(test_pre, nn_model.rep.label_2_index,Top_N=3)
     #print('test_score:',test_score)
@@ -562,7 +553,7 @@ def output_txt(ml_input_txt):
 
     return fout.getvalue()
 
-def ml_tagging(session,ssplit_token,ml_model,Threshold):
+def ml_tagging(ssplit_token,ml_model,Threshold):
     # startTime=time.time()
     ml_input, ml_input_txt,ml_input_index=build_ngram_testset_filted(ssplit_token)
     # print('ml-ngrambuild:',time.time()-startTime)
@@ -570,7 +561,7 @@ def ml_tagging(session,ssplit_token,ml_model,Threshold):
     #print(ml_input)
     # startTime=time.time()
     if len(ml_input_index)>0:
-        ml_pre_tsv=model_predict(session,ml_input,ml_model,ml_input_txt,ml_input_index,Threshold)
+        ml_pre_tsv=model_predict(ml_input,ml_model,ml_input_txt,ml_input_index,Threshold)
     else:
         ml_pre_tsv=output_txt(ml_input_txt)
     # print('ml-modelpred:',time.time()-startTime)

src/nn_model.py

@@ -8,12 +8,10 @@ Created on Thu Mar 26 09:04:13 2020
 import time
 import sys
 import numpy as np
-import tensorflow as tf
 import keras
 from src.nn_represent import CNN_RepresentationLayer,BERT_RepresentationLayer
 from keras.layers import *
 from keras.models import Model
-from keras import backend as K
 from keras_bert import load_trained_model_from_checkpoint
 
 
@@ -37,7 +35,7 @@ class bioTag_CNN():
         self.charfile=model_files['charfile']
         self.labelfile=model_files['labelfile']
         self.posfile=model_files['posfile']
-        self.session = K.get_session()
+
         vocab={'char':self.charfile,'label':self.labelfile,'pos':self.posfile}
         print('loading w2v model.....') 
         self.rep = CNN_RepresentationLayer(self.w2vfile,vocab_file=vocab, frequency=400000)
@@ -94,8 +92,6 @@ class bioTag_CNN():
         self.model = Model(inputs=all_fea, outputs=output)
     def load_model(self,model_file):
         self.model.load_weights(model_file)
-        self.session = K.get_session()
-        print(self.session)
         #self.model.summary()        
         print('load cnn model done!')
 
@@ -107,7 +103,6 @@ class bioTag_BERT():
         checkpoint_path = model_files['checkpoint_path']
         vocab_path = model_files['vocab_path']
         self.label_file=model_files['labelfile']
-        self.session = tf.Session()
     
         self.rep = BERT_RepresentationLayer( vocab_path, self.label_file)
         
@@ -124,8 +119,6 @@ class bioTag_BERT():
 
     def load_model(self,model_file):
         self.model.load_weights(model_file)
-        self.session = K.get_session()
-        print(self.session)
         #self.model.summary()        
 
 class bioTag_Bioformer():
@@ -152,11 +145,6 @@ class bioTag_Bioformer():
 
     def load_model(self,model_file):
         self.model.load_weights(model_file)
-        #self.model._make_predict_function()
-        #session = K.get_session()
-        #print(session)
         #self.model.summary()
-        session=''   
-        return session
         print('load bioformer model done!')
       

src/tagging_text.py

@@ -18,7 +18,7 @@ import time
 import json
 
 #hybrid method
-def bioTag(session,text,biotag_dic,ml_model,onlyLongest=False, abbrRecog=False, Threshold=0.95):
+def bioTag(text,biotag_dic,ml_model,onlyLongest=False, abbrRecog=False, Threshold=0.95):
 
     # startTime=time.time()
     ssplit_token=ssplit_token_pos_lemma(text)
@@ -31,7 +31,7 @@ def bioTag(session,text,biotag_dic,ml_model,onlyLongest=False, abbrRecog=False,
     # print('dict ner:',time.time()-startTime)
   
     # startTime=time.time()
-    ml_tsv=ml_tagging(session,ssplit_token,ml_model,Threshold)
+    ml_tsv=ml_tagging(ssplit_token,ml_model,Threshold)
     #print('ml_tsv:\n',ml_tsv)
     # print('ml ner:',time.time()-startTime)