不用CUDA时出现的问题

[ZhiliWang]

按照指示搭建环境，下载各种文件后直接跑和readme里一样的例子，唯一改变的是把use_cuda = True 改成False。尝试了很多改变都会回到这个key error错误信息：

代码：

预测中文句子级情感分类任务

my_senta.init_model(model_class="ernie_1.0_skep_large_ch", task="sentiment_classify", use_cuda=use_cuda)
texts = ["中山大学是岭南第一学府"]
result = my_senta.predict(texts)
print(result)

预测中文评价对象级的情感分类任务

my_senta.init_model(model_class="ernie_1.0_skep_large_ch", task="aspect_sentiment_classify", use_cuda=use_cuda)
texts = ["百度是一家高科技公司"]
aspects = ["百度"]
result = my_senta.predict(texts, aspects)
print(result)

预测中文观点抽取任务

my_senta.init_model(model_class="ernie_1.0_skep_large_ch", task="extraction", use_cuda=use_cuda)
texts = ["唐 家 三 少 ， 本 名 张 威 。"]
result = my_senta.predict(texts, aspects)
print(result)

---

KeyError Traceback (most recent call last)
in
10 # 预测中文句子级情感分类任务
11
---> 12 my_senta.init_model(model_class="ernie_1.0_skep_large_ch", task="sentiment_classify", use_cuda=use_cuda)
13 texts = ["中山大学是岭南第一学府"]
14 result = my_senta.predict(texts)

/opt/anaconda3/envs/hsbc/lib/python3.7/site-packages/senta/train.py in init_model(self, model_class, task, use_cuda)
222 tokenizer_params["bpe_json_file"] = _get_abs_path(bpe_j_file)
223
--> 224 tokenizer_class = RegisterSet.tokenizer.getitem(tokenizer_name)
225 self.tokenizer = tokenizer_class(vocab_file=tokenizer_vocab_path,
226 split_char=" ",

/opt/anaconda3/envs/hsbc/lib/python3.7/site-packages/senta/common/register.py in getitem(self, key)
45 except Exception as e:
46 logging.error("module {key} not found: {e}")
---> 47 raise e
48
49 def contains(self, key):

/opt/anaconda3/envs/hsbc/lib/python3.7/site-packages/senta/common/register.py in getitem(self, key)
42 def getitem(self, key):
43 try:
---> 44 return self._dict[key]
45 except Exception as e:
46 logging.error("module {key} not found: {e}")

KeyError: 'FullTokenizer'

请问是哪里出错了呢？

[ZhiliWang]

想出来了，不好意思

[yingxiayin]

请问这里的问题应该怎么办呢

[LinZY6]

想出来了，不好意思

请问您怎样解决的