Comments (8)
我也遇到这个错误了,请问解决了吗
已经解决了,解决方法:
在windows下面操作,需要修改以下几个地方:
- flat_main.py 中,第306行,cache_name中的冒号(:)都替换成井号(#)
cache_name = os.path.join('cache',(args.dataset+'_lattice'+'_only_train#{}'+
'_trainClip#{}'+'_norm_num#{}'
+'char_min_freq{}'+'bigram_min_freq{}'+'word_min_freq{}'+'only_train_min_freq{}'
+'number_norm{}'+'lexicon_{}'+'load_dataset_seed{}')
- 如果没有GPU,则修改utils.py 第220行添加一行:
device = None
from flat-lattice-transformer.
可以试试先在当前目录下新建一个cache文件夹
from flat-lattice-transformer.
可以试试先在当前目录下新建一个cache文件夹
尝试了,就是在../V0/ 文件夹下,新建了一个cache的文件夹,然后运行代码,还是报错,同样的错误,
cache文件夹下生成的文件:
from flat-lattice-transformer.
我也遇到这个错误了,请问解决了吗
from flat-lattice-transformer.
from flat-lattice-transformer.
感谢感谢,解决了。另外还有两个问题不太确定。 1.你生成的yj文件也是这个样子吗? 2.还有运行的时候Found 698668 out of 698670 words in the pre-training embedding.这个正常吗
…
------------------ 原始邮件 ------------------ 发件人: "LeeSureman/Flat-Lattice-Transformer" <[email protected]>; 发送时间: 2020年11月10日(星期二) 下午3:38 收件人: "LeeSureman/Flat-Lattice-Transformer"<[email protected]>; 抄送: "Jam Don"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [LeeSureman/Flat-Lattice-Transformer] 运行weibo数据集报错 (#42) 我也遇到这个错误了,请问解决了吗 已经解决了,解决方法: 在windows下面操作,需要修改以下几个地方: flat_main.py 中,第306行,cache_name中的冒号(:)都替换成井号(#) cache_name = os.path.join('cache',(args.dataset+'_lattice'+'_only_train#{}'+ '_trainClip#{}'+'norm_num#{}' +'char_min_freq{}'+'bigram_min_freq{}'+'word_min_freq{}'+'only_train_min_freq{}' +'number_norm{}'+'lexicon{}'+'load_dataset_seed{}') 如果没有GPU,则修改utils.py 第220行添加一行: device = None — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
- 就是我没看到你发的图,我看了看我的,如果用文本软件打开确实是乱码,应该是二进制文件;
- 这个我也不太清楚是否正常,训练的时候我也是这么显示的。
from flat-lattice-transformer.
from flat-lattice-transformer.
我也遇到这个错误了,请问解决了吗
已经解决了,解决方法: 在windows下面操作,需要修改以下几个地方:
- flat_main.py 中,第306行,cache_name中的冒号(:)都替换成井号(#)
cache_name = os.path.join('cache',(args.dataset+'_lattice'+'_only_train#{}'+ '_trainClip#{}'+'_norm_num#{}' +'char_min_freq{}'+'bigram_min_freq{}'+'word_min_freq{}'+'only_train_min_freq{}' +'number_norm{}'+'lexicon_{}'+'load_dataset_seed{}')
- 如果没有GPU,则修改utils.py 第220行添加一行:
device = None
则修改utils.py 第220行添加一行:
device = None我修改了这个,但是出现了这样的报错怎么解决
from flat-lattice-transformer.
Related Issues (20)
- 使用自定义数据集,训练过程SpanFPreRecMetric各项指标值均为0该如何解决 HOT 2
- report的实验结果是best result还是average? HOT 2
- 读取vocab文件时编码问题
- 载入数据问题:load_msra_ner_without_dev HOT 3
- 官方提供的数据集是不是不全呀? HOT 3
- flat_main.py为什么把测试集直接赋值给了验证集了呢 HOT 1
- 请问该模型能用于生产嘛?感觉模型太大,无法部署
- `LSTM_SeqLabel_True( )`从头到尾没见定义过,咋用?????????????
- 请问参数pos_norm的含义是什么呀?
- 在自己的数据上出现错误
- 吐了
- FileNotFoundError: [Errno 2] No such file or directory: HOT 4
- 数据集提问 HOT 1
- yangjie_word_char_mix.txt 文件 HOT 1
- 你好大佬,跑V1时 NameError: name '_WordBertModel' is not defined这个怎么解决?谢谢 HOT 3
- 大佬你好,请问对应数据集的lexicon是怎么生成的呢
- 复现精度问题 HOT 2
- 代码报错
- key error bigram
- pos_s 和 pos_e 怎么求的
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from flat-lattice-transformer.