def texts2tensor(self, texts):
"""
Tranform the texts(dict) to PaddleTensor
Args:
texts(dict): texts
Returns:
tensor(PaddleTensor): tensor with texts data
"""
lod = [0]
data = []
for i, text in enumerate(texts):
data += text['processed']
lod.append(len(text['processed']) + lod[i])
tensor = PaddleTensor(np.array(data).astype('int64'))
tensor.name = "words"
tensor.lod = [lod]
tensor.shape = [lod[-1], 1]
return tensor
def texts2tensor(self, texts):
"""
Tranform the texts(dict) to PaddleTensor
Args:
texts(list): each element is a dict that must have a named 'processed' key whose value is word_ids, such as
texts = [{'processed': [23, 89, 43, 906]}]
Returns:
tensor(PaddleTensor): tensor with texts data
"""
lod = [0]
data = []
for i, text in enumerate(texts):
data += text['processed']
lod.append(len(text['processed']) + lod[i])
tensor = PaddleTensor(np.array(data).astype('int64'))
tensor.name = "words"
tensor.lod = [lod]
tensor.shape = [lod[-1], 1]
return tensor
def texts2tensor(self, texts):
"""
Tranform the texts(list) to PaddleTensor
Args:
texts(list): texts
Returns:
tensor(PaddleTensor): tensor with texts data
"""
lod = [0]
data = []
for i, text in enumerate(texts):
text_inds = word_to_ids(text,
self.word2id_dict,
self.word_replace_dict,
oov_id=self.oov_id)
data += text_inds
lod.append(len(text_inds) + lod[i])
tensor = PaddleTensor(np.array(data).astype('int64'))
tensor.name = "words"
tensor.lod = [lod]
tensor.shape = [lod[-1], 1]
return tensor
