Giter Site home page Giter Site logo

问1:LSTMMTL、LSTMMTL2CompleteGraph区别?问2:调整readme对应参数和batchsize为16后,运行LSTMMTL,仍报out of memory,我是1块2080ti,11G,70m自己数据,需求一份论文所说9G卡可运行参数,谢谢 about docee HOT 5 CLOSED

spico197 avatar spico197 commented on June 18, 2024
问1:LSTMMTL、LSTMMTL2CompleteGraph区别?问2:调整readme对应参数和batchsize为16后,运行LSTMMTL,仍报out of memory,我是1块2080ti,11G,70m自己数据,需求一份论文所说9G卡可运行参数,谢谢

from docee.

Comments (5)

Spico197 avatar Spico197 commented on June 18, 2024

嗨,您好。

  • LSTMMTL:LSTM版的Doc2EDAG,参数量比Doc2EDAG较小,但和Doc2EDAG所需资源基本相同,至少四卡;
  • LSTMMTL2CompleteGraphModel是实验初期尝试的完全图方案,单卡可跑。

建议使用dee/models/trigger_aware.py中的TriggerAwarePrunedCompleteGraph,也是我们论文中提到的PTPCG模型,训练速度快,且相较上述两个模型的最终效果好。参数可见scripts/run_ptpcg.sh。如果是自己的数据的话,可能需要再调调参,改改train_batch_sizegradient_accumulation_stepslearning_rate

from docee.

BEILOP avatar BEILOP commented on June 18, 2024

感谢,已经在我数据集上运行完毕。速度果然是Doc2EDAG的n倍的n倍。我现在想使用CPU运行predict_one(),应该如何做?现在仍报cuda_out_of_memory,以下是我的修改:skip_train调为True,load_eval和load_test改为False,nocuda都改为True,load_inference相关改为True(看着像是推理相关参数),model_type、save_cpt_file改为TriggerAwarePrunedCompleteGraph,然后在run_dee_task里200多行Build_dee_tasking之后加上了dee_task.predict_one(我的文本)运行。

from docee.

Spico197 avatar Spico197 commented on June 18, 2024

嗨您好,load_inference是用来打比赛的时候预测线上测试集时使用,如果不需要的话也可以设置为False。如果想使用CPU预测的话,可以将CUDA_VISIBLE_DEVICES环境变量置空:CUDA_VISIBLE_DEVICES=""
另外需要在task实例化之后,将最佳模型权重导入:dee_task.resume_cpt_at(最佳轮次, resume_model=True),之后就可以调用dee_task.predict_one(字符串)方法进行推理了。

from docee.

BEILOP avatar BEILOP commented on June 18, 2024

经过测试,单事件文章效果确实实测比Doc2EDAG好,再次感谢您的开源

from docee.

Spico197 avatar Spico197 commented on June 18, 2024

感谢您的关注和支持~

from docee.

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.