我使用下面的简化代码：
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
embeddings = model.encode(sentences)其中sentences是一个PandasSeries，包含我想要转换的句子。
然后我得到了以下错误Traceback
embeddings = model.encode(sentences)
File "/anaconda/envs/topics/lib/python3.8/site-packages/sentence_transformers/SentenceTransformer.py", line 157, in encode
sentences_sorted = [sentences[idx] for idx in length_sorted_idx]
File "/anaconda/envs/topics/lib/python3.8/site-packages/sentence_transformers/SentenceTransformer.py", line 157, in <listcomp>
sentences_sorted = [sentences[idx] for idx in length_sorted_idx]
File "/anaconda/envs/topics/lib/python3.8/site-packages/pandas/core/series.py", line 942, in
__getitem__
return self._get_value(key)
File "/anaconda/envs/topics/lib/python3.8/site-packages/pandas/core/series.py", line 1051, in
_get_value
loc = self.index.get_loc(label)
File "/anaconda/envs/topics/lib/python3.8/site-packages/pandas/core/indexes/base.py", line 3363, in get_loc
raise KeyError(key) from err
KeyError: 144
2条答案
按热度按时间wsewodh21#
实际的解决方案是将Pandas
Series转换为numpy数组：omqzjyyz2#
该嵌入式将给予在数组或Tensor形式的形式，所以使用下面的代码来解决这个问题
嵌入=模型.编码（句子，转换为Tensor=真）
[或]
嵌入=模型.编码（句子，转换为numpy=True）