KeyError在汇流变压器管道中使用非默认模型时的应用
KeyError在汇流变压器管道中使用非默认模型时的应用
提问于 2020-06-10 10:01:46
在情感分析管道中使用默认模型没有问题。
# Allocate a pipeline for sentiment-analysis
nlp = pipeline('sentiment-analysis')
nlp('I am a black man.')
>>>[{'label': 'NEGATIVE', 'score': 0.5723695158958435}]但是，当我试图通过添加一个特定的模型来定制管道时。它抛出一个KeyError。
nlp = pipeline('sentiment-analysis',
tokenizer = AutoTokenizer.from_pretrained("DeepPavlov/bert-base-cased-conversational"),
model = AutoModelWithLMHead.from_pretrained("DeepPavlov/bert-base-cased-conversational"))
nlp('I am a black man.')
>>>---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-55-af7e46d6c6c9> in <module>
3 tokenizer = AutoTokenizer.from_pretrained("DeepPavlov/bert-base-cased-conversational"),
4 model = AutoModelWithLMHead.from_pretrained("DeepPavlov/bert-base-cased-conversational"))
----> 5 nlp('I am a black man.')
6
7
~/opt/anaconda3/lib/python3.7/site-packages/transformers/pipelines.py in __call__(self, *args, **kwargs)
721 outputs = super().__call__(*args, **kwargs)
722 scores = np.exp(outputs) / np.exp(outputs).sum(-1, keepdims=True)
--> 723 return [{"label": self.model.config.id2label[item.argmax()], "score": item.max().item()} for item in scores]
724
725
~/opt/anaconda3/lib/python3.7/site-packages/transformers/pipelines.py in <listcomp>(.0)
721 outputs = super().__call__(*args, **kwargs)
722 scores = np.exp(outputs) / np.exp(outputs).sum(-1, keepdims=True)
--> 723 return [{"label": self.model.config.id2label[item.argmax()], "score": item.max().item()} for item in scores]
724
725
KeyError: 58129回答 1
Stack Overflow用户
发布于 2020-09-30 20:24:42
我也面临着同样的问题。我正在使用squadv2数据集(“a-ware/xlmroberta- set 2”)微调XML的模型。就我而言，KeyError是16岁。
Link
想要在这个问题上寻求帮助，我发现了以下信息：链接，我希望你发现它有帮助。
答案(来自链接)
当模型预测不属于文档一部分的令牌时，管道会抛出异常(例如，最终的特殊令牌SEP)。
我的问题
from transformers import XLMRobertaTokenizer, XLMRobertaForQuestionAnswering
from transformers import pipeline
nlp = pipeline('question-answering',
model = XLMRobertaForQuestionAnswering.from_pretrained('a-ware/xlmroberta-squadv2'),
tokenizer= XLMRobertaTokenizer.from_pretrained('a-ware/xlmroberta-squadv2'))nlp(question = "Who was Jim Henson?", context ="Jim Henson was a nice puppet")
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-15-b5a8ece5e525> in <module>()
1 context = "Jim Henson was a nice puppet"
2 # --------------- CON INTERROGACIONES
----> 3 nlp(question = "Who was Jim Henson?", context =context)
1 frames
/usr/local/lib/python3.6/dist-packages/transformers/pipelines.py in <listcomp>(.0)
1745 ),
1746 }
-> 1747 for s, e, score in zip(starts, ends, scores)
1748 ]
1749
KeyError: 16解决方案1:在上下文的末尾添加标点符号
为了避免试图提取最终令牌(可能是SEP的特殊标记)的错误，我在上下文末尾添加了一个元素(在本例中是标点符号)：
nlp(question = "Who was Jim Henson?", context ="Jim Henson was a nice puppet.")
[OUT]
{'answer': 'nice puppet.', 'end': 28, 'score': 0.5742837190628052, 'start': 17}解决方案2:不要使用管道()
原始模型可以自行处理，以检索正确的令牌索引。
from transformers import XLMRobertaTokenizer, XLMRobertaForQuestionAnswering
import torch
tokenizer = XLMRobertaTokenizer.from_pretrained('a-ware/xlmroberta-squadv2')
model = XLMRobertaForQuestionAnswering.from_pretrained('a-ware/xlmroberta-squadv2')
question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
encoding = tokenizer(question, text, return_tensors='pt')
input_ids = encoding['input_ids']
attention_mask = encoding['attention_mask']
start_scores, end_scores = model(input_ids, attention_mask=attention_mask, output_attentions=False)[:2]
all_tokens = tokenizer.convert_ids_to_tokens(input_ids[0])
answer = ' '.join(all_tokens[torch.argmax(start_scores) : torch.argmax(end_scores)+1])
answer = tokenizer.convert_tokens_to_ids(answer.split())
answer = tokenizer.decode(answer)更新
更详细地看一下您的情况，我发现管道中会话任务的默认模型是distilbert-base-cased (源代码)。
我发布的第一个解决方案确实不是一个很好的解决方案。尝试其他问题我也犯了同样的错误。但是，管道外的模型本身工作正常(如我在解决方案2中所示)。因此，我相信并非所有的模式都可以采用。如果有人对此有更多的了解，请帮助我们。谢谢。
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/62300836
复制相关文章
相似问题
腾讯云开发者
