首页 Paddle框架 帖子详情
用自己处理的数据集一直报错
收藏
快速回复
Paddle框架 问答深度学习 2800 4
用自己处理的数据集一直报错
收藏
快速回复
Paddle框架 问答深度学习 2800 4

这是自己处理的数据集

关于存量客户的房贷利率是否调整,交行正在研究制定政策。而在此之前,光大和招行的房贷细则先行出炉, OOOOOOOOOOOOOOOOB-coI-coOOOOOOOOOOOOOOOB-coI-coOB-coI-coOOOOOOOOOO
约维蒂奇有望与吉拉蒂诺搭档锋线。2003-04赛季两队一同从意乙升级,之后共有8次交手, OB-naI-naI-naOOOB-naI-naI-naI-naOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO
詹俊足彩预测:俄罗斯巴西作稳胆荷兰阿根廷防平 B-naI-naOOOOOB-orI-orI-orI-orI-orOOOB-orI-orI-orI-orI-orOO
长期研究海外热钱的学者,广东省社科院教授黎友焕表示,深圳现金投放减速跟热钱流出和经济低迷有很大关系, OOOOOOOOOB-poI-poOB-goI-goI-goI-goI-goI-goB-poI-poB-naI-naI-naOOOOOOOOOOOOOOOOOOOOOOOOOOO
会直接将1000欧元转换成人民币,约合8170元;如果刷双币卡走visa通道结算, OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOB-coI-coI-coI-coOOOOO
这次我们创造出来的玩意儿绝对能够满足《红色警戒》玩家的胃口,包括百合子的地城突围战役, OOOOOOOOOOOOOOOOOOB-gaI-gaI-gaI-gaI-gaI-gaOOOOOOOOOOOOOOOOOOO
花5000钱购买一本《华胥梦天记》。 OOOOOOOOOOB-boI-boI-boI-boI-boI-boI-boO
论坛进行到现在时间已经不多了,下面我们请住房和城乡建设部科学技术委员会常务副主任、 OOOOOOOOOOOOOOOOOOOOB-goI-goI-goI-goI-goI-goI-goI-goI-goI-goI-goI-goI-goI-goI-goB-poI-poI-poI-poI-poO
CPL2011中国区选拔赛WAR3项目已产生10名晋级复赛的选手, B-orI-orI-orOOOOOOOOOOB-gaI-gaI-gaI-gaOOOOOOOOOOOOOB-poI-poO
银联上海总部人士昨日对记者表示,知道这一消息并密切关注此事。 B-coI-coI-coI-coI-coI-coOOOOOB-poI-poOOOOOOOOOOOOOOOOO
《战地:叛逆连队2》将采用DICE的下一代游戏引擎“Frostbite”, B-gaI-gaI-gaI-gaI-gaI-gaI-gaI-gaI-gaI-gaOOOB-coI-coI-coI-coOOOOOOOOOOOOOOOOOOOO
5.米德尔vs博尔顿从目前的数据收集情况分析而言,主队不败的痕迹也是较为明显的,首先, OOB-orI-orI-orOOB-orI-orI-orOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO
穿越历史的风尘:藏家12条收藏秘籍 OOOOOOOOB-poI-poOOOOOOO
这也是范冰冰续《墨攻》后第二次演绎战国时期的故事。当天记者感到范冰冰在拍摄《麦田》时心情“相当不错” OOOB-naI-naI-naOB-moI-moI-moI-moOOOOOOOOOOOOOOOOB-poI-poOOOOOOOOB-moI-moI-moI-moOOOOOOOOO
06梅塔利斯特vs奥林匹亚科斯 OOB-orI-orI-orI-orI-orOOB-orI-orI-orI-orI-orI-or
数量环比下滑了5%。这表明完美时空预计《神鬼传奇》的发布将使APA第二季度出现反弹。 OOOOOOOOOOOOOOOOOOOB-moI-moI-moI-moI-moI-moOOOOOOOOOOOOOOOOO
澳彩初盘为平半,目前以半球盘正式受注,也是对主队让球能力的看好。从赔率看,包括bet365、 OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOB-coI-coI-coI-coI-coI-coO
《模拟人生3》制作人透露游戏细节(2) B-gaI-gaI-gaI-gaI-gaI-gaI-gaB-poI-poI-poOOOOOOOOO
文华财经(编辑整理何丽丽)--据新加坡9月23日消息,亚洲燃料油跨月合约周四仍遭大单抛售, B-coI-coI-coI-coOB-poI-poOOB-naI-naI-naOOOOB-adI-adI-adOOOOOOOOOOOOOOOOOOOOOOOOOO
叶问以及苏乞儿等电影来满足意淫需求的中国人,韩国人实在硬气太多了。 B-moI-moOOB-moI-moI-moOOOOOOOOOOOOOOOOOOOOOOOOOO
难道作为一本关于游戏考察的书籍,《游戏作弊》偏离主题了吗?我并不这么认为。 OOOOOOOOOOOOOOOOB-boI-boI-boI-boI-boI-boOOOOOOOOOOOOOOO
结果在今年4月份这个奖又授予日本两位建筑师,一位是女建筑师。越到后边, OOOOOOOOOOOOOOOOOOB-poI-poI-poOOOOOOOOOOOOOO
我们把丽泽商务区不仅仅做成纯粹的面向金融产业, OOOB-scI-scI-scI-scI-scOOOOOOOOOOOOOOO
全国人大副委员长蒋正华指出,2010年,我国粗钢总产量达到6.3亿吨,钢材的总产量接近8亿吨, B-goI-goI-goI-goB-poI-poI-poI-poB-naI-naI-naOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO
根据Gameinformer的消息,这个游戏将在2011年5月3日正式上市, OOB-boI-boI-boI-boI-boI-boI-boI-boI-boI-boI-boI-boOOOOOOOOOOOOOOOOOOOOOOOO
姜山:南美区的比赛阿根廷和巴西都在本期竞猜之中。虽然阿根廷上轮主场击败乌拉圭终结连平纪录, B-naI-naOB-adI-adI-adOOOB-orI-orI-orOB-orI-orOOOOOOOOOOOOOOOOOOOOB-orI-orI-orOOOOOOO
招行和平安7家银行收取小额账户管理费。 B-coI-coOB-coI-coOOOOOOOOOOOOOO
26日央行将停发两周前重启的3年期央行票据。 OOOB-goI-goOOOOOOOOOOOOOOOOO
姜山:不来梅有希望在拜仁身上制冷吗? B-naI-naOOOOOOOOB-orI-orOOOOOO

 

这是报错代码

 

) in
----> 1 run_states=seq_label_task.finetune_and_eval()
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlehub/finetune/task/base_task.py in finetune_and_eval(self)
    943
    944     def finetune_and_eval(self):
--> 945         return self.finetune(do_eval=True)
    946
    947     def finetune(self, do_eval=False):
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlehub/finetune/task/base_task.py in finetune(self, do_eval)
    964                 while self.current_epoch <= self.config.num_epoch:
    965                     self.config.strategy.step()
--> 966                     run_states = self._run(do_eval=do_eval)
    967                     self.env.current_epoch += 1
    968
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlehub/finetune/task/base_task.py in _run(self, do_eval)
   1197             global_run_states = []
   1198             period_run_states = []
-> 1199             for batch in data_reader():
   1200                 step_run_state = RunState(len(self.fetch_list))
   1201                 step_run_state.run_step = 1
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/reader.py in __next__(self)
   1146                 return self._reader.read_next_list()
   1147             else:
-> 1148                 return self._reader.read_next()
   1149         except StopIteration:
   1150             self._queue.close()
EnforceNotMet:
----------------------
Error Message Summary:
----------------------
FatalError: Blocking queue is killed because the data reader raises an exception.
  [Hint: Expected killed_ != true, but received killed_:1 == true:1.] (at /paddle/paddle/fluid/operators/reader/blocking_queue.h:154)) in
----> 1 run_states=seq_label_task.finetune_and_eval()
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlehub/finetune/task/base_task.py in finetune_and_eval(self)
    943
    944     def finetune_and_eval(self):
--> 945         return self.finetune(do_eval=True)
    946
    947     def finetune(self, do_eval=False):
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlehub/finetune/task/base_task.py in finetune(self, do_eval)
    964                 while self.current_epoch <= self.config.num_epoch:
    965                     self.config.strategy.step()
--> 966                     run_states = self._run(do_eval=do_eval)
    967                     self.env.current_epoch += 1
    968
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlehub/finetune/task/base_task.py in _run(self, do_eval)
   1197             global_run_states = []
   1198             period_run_states = []
-> 1199             for batch in data_reader():
   1200                 step_run_state = RunState(len(self.fetch_list))
   1201                 step_run_state.run_step = 1
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/reader.py in __next__(self)
   1146                 return self._reader.read_next_list()
   1147             else:
-> 1148                 return self._reader.read_next()
   1149         except StopIteration:
   1150             self._queue.close()
EnforceNotMet:
----------------------
Error Message Summary:
----------------------
FatalError: Blocking queue is killed because the data reader raises an exception.
  [Hint: Expected killed_ != true, but received killed_:1 == true:1.] (at /paddle/paddle/fluid/operators/reader/blocking_queue.h:154)

0
收藏
回复
全部评论(4)
时间顺序
阿超
#2 回复于2020-11

求大神帮忙 可有偿

0
回复
AIStudio810258
#3 回复于2020-11

如果不是读第一条数据就报错,检查下数据集格式吧

0
回复
Michael阿明
#4 回复于2021-09

SystemError: (Fatal) Blocking queue is killed because the data reader raises an exception.
[Hint: Expected killed_ != true, but received killed_:1 == true:1.] (at /paddle/paddle/fluid/operators/reader/blocking_queue.h:166)

 

做 nlp 也遇到这个问题。。

epoch:179 - step:2698 - loss: 0.000071, best f1 score: 0.910891 on epoch 48
epoch:179 - step:2699 - loss: 0.000531, best f1 score: 0.910891 on epoch 48
epoch:179 - step:2700 - loss: 0.000017, best f1 score: 0.910891 on epoch 48
eval precision: 0.897959 - recall: 0.897959 - f1: 0.897959
[2021-09-18 15:17:50,866] [ INFO] - Already cached /home/web/.paddlenlp/models/ernie-gram-zh/vocab.txt
[2021-09-18 15:17:50,874] [ INFO] - Already cached /home/web/.paddlenlp/models/ernie-gram-zh/ernie_gram_zh.pdparams
----train with ./data/origin_train1.txt train PRF------
WARNING:root:DataLoader reader thread raised an exception.
Exception in thread Traceback (most recent call last):
Thread-361 File "method_compare.py", line 144, in
:
Traceback (most recent call last):
caltrainPRF(model, tokenizer, "./data/origin_dev.txt", label_vocab, trans_func) File "/opt/bdp/data01/anaconda3/envs/pp21/lib/python3.8/threading.py", line 932, in _bootstrap_inner

File "/opt/bdp/data01/***/ner_utils.py", line 178, in caltrainPRF
self.run()
File "/opt/bdp/data01/anaconda3/envs/pp21/lib/python3.8/threading.py", line 870, in run
res = predict_batchText(model, tokenizer, texts, label_vocab, trans_func)self._target(*self._args, **self._kwargs)

File "/opt/bdp/data01/***/ner_utils.py", line 125, in predict_batchText
File "/opt/bdp/data01/anaconda3/envs/pp21/lib/python3.8/site-packages/paddle/fluid/dataloader/dataloader_iter.py", line 192, in _thread_loop
return predict(model, data_loader, pred_data, label_vocab, pred=True, predSingleText=2)six.reraise(*sys.exc_info())

File "/opt/bdp/data01/***/ner_utils.py", line 86, in predict
File "/opt/bdp/data01/anaconda3/envs/pp21/lib/python3.8/site-packages/six.py", line 719, in reraise
raise valuefor input_ids, token_type_ids, lengths in data_loader:

File "/opt/bdp/data01/anaconda3/envs/pp21/lib/python3.8/site-packages/paddle/fluid/dataloader/dataloader_iter.py", line 160, in _thread_loop
File "/opt/bdp/data01/anaconda3/envs/pp21/lib/python3.8/site-packages/paddle/fluid/dataloader/dataloader_iter.py", line 197, in __next__
data = self._reader.read_next_var_list()
batch = self._dataset_fetcher.fetch(indices)SystemError:
(Fatal) Blocking queue is killed because the data reader raises an exception.
[Hint: Expected killed_ != true, but received killed_:1 == true:1.] (at /paddle/paddle/fluid/operators/reader/blocking_queue.h:166)
File "/opt/bdp/data01/anaconda3/envs/pp21/lib/python3.8/site-packages/paddle/fluid/dataloader/fetcher.py", line 106, in fetch

0
回复
FutureSI
#5 回复于2021-09

清洗下数据,不行删了那条试试

0
回复
需求/bug反馈?一键提issue告诉我们
发现bug?如果您知道修复办法,欢迎提pr直接参与建设飞桨~
在@后输入用户全名并按空格结束,可艾特全站任一用户