def _predict(self,text_list):
if type(text_list)==type(""):
text_list=[text_list]
text_list = CategoryDataUtils.textListPreprocess(text_list) #clean str
vec=np.array(list(self.vocabproc.transform(text_list)))
feed_dict={
self.rcnn.input_text: vec,
self.rcnn.dropout_keep_prob:1.0
}
predictions,prob = self.sess.run([self.rcnn.predictions,self.rcnn.prob], feed_dict)
result=[]
for item in prob:
cur_article={}
for i in range(len(item)):
cur_article[self.idx2cat[i]]=item[i]
result.append(cur_article)
return result
def predict_split(self,text_list):
if type(text_list)==type(""):
text_list=[text_list]
text_list = CategoryDataUtils.textListPreprocess(text_list) #clean str
_vec=list(self.vocabproc.transform(text_list))
partNum=1
partSize=int(400/partNum)
vec=[]
for item in _vec:
for i in range(partNum):
tmp=item.copy()
for j in range(400):
if j>partSize*i and j< partSize*(i+1):
tmp[j]=0
vec.append(tmp)
vec=np.array(vec)
print(len(vec))
result=[]
print("[*]transform success");
for i in range(0,len(vec),500):
feed_dict={
self.rcnn.input_text: vec[i:i+500],
self.rcnn.dropout_keep_prob:1.0
}
predictions,prob = self.sess.run([self.rcnn.predictions,self.rcnn.prob], feed_dict)
for item in prob:
cur_article={}
for j in range(len(item)):
cur_article[self.idx2cat[j]]=item[j]
result.append(cur_article)
print("[*]progress:%d/%d" %(i,len(vec)))
#merge
_result=[]
for i in range(0,len(result),partNum):
_result.append(merge_result_mean(result[i:i+partNum]))
return _result