Code Monkey home page Code Monkey logo

Comments (7)

976985088 avatar 976985088 commented on August 16, 2024 1

训练doupo没有改任何参数,推断出现同样的问题

from transformer-xl-chinese.

lk1983823 avatar lk1983823 commented on August 16, 2024

我在训练doupo的时候,也是出现了同样的问题.

from transformer-xl-chinese.

Yuanchenbo avatar Yuanchenbo commented on August 16, 2024

楼上的两位,请问问题解决了没

from transformer-xl-chinese.

ZJiaBin avatar ZJiaBin commented on August 16, 2024

我遇到了类似的问题发现是因为词表不一致的问题,可以看一下 train_gpu.py 文件中,inference函数的dataset_name与train函数是否一致?

from transformer-xl-chinese.

scorpio2017 avatar scorpio2017 commented on August 16, 2024

我遇到了类似的问题发现是因为词表不一致的问题,可以看一下 train_gpu.py 文件中,inference函数的dataset_name与train函数是否一致?

什么意思?与train函数的什么是否一致?

from transformer-xl-chinese.

GaoPeng97 avatar GaoPeng97 commented on August 16, 2024

抱歉各位,回复的比较晚,大家看下readme 中”注意在inference的时候记得修改train_gpu.py中第504行,改成你想inference的数据集名字“ 有没有注意到

from transformer-xl-chinese.

GaoPeng97 avatar GaoPeng97 commented on August 16, 2024

各位 不知道你们还在不在这个repo上跟进,回复各位较晚了 非常抱歉,问题已经修复,感谢你们的反馈, 问题来源于之前在data/doupo/ 下有一个记录corpus 的信息的json,和一个cache.pkl, 这样在运行bash base_doupo_gpu.sh train_data 时,如果识别到cache.pkl, 就不会重新生成训练数据,会直接使用原来的有问题的那个,所以简单的解决办法就是把除*.txt 以外的都直接删掉即可。

from transformer-xl-chinese.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.