Comments (5)
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_size
,gradient_accumulation_steps
和learning_rate
。
from docee.
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.
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.
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.
感谢您的关注和支持~
from docee.
Related Issues (20)
- doc_lang=self.setting.doc_lang报错 HOT 3
- 这个库里面哪些代码是ptpcg这个算法用到的 HOT 29
- 新数据集的训练 HOT 18
- PTPCG 分布式训练的效率 HOT 8
- 关于trigger HOT 3
- 触发词的问题 HOT 10
- 训练 teacher prob 的问题 HOT 7
- wikievents 等英文数据集实验 HOT 23
- ner 这块的问题 HOT 7
- ner 参数设置的问题 HOT 1
- 在计算相似度时是否忽略了实体的相对位置 HOT 1
- Failed to reproduce the result with inference.py HOT 2
- Transformer相关的问题 HOT 2
- loss weight mismatch
- some doubts HOT 1
- 代码疑似错误 HOT 4
- 请问可以提供各个模型的checkpioint吗? HOT 4
- 怎么加bert模型呢 HOT 3
- Number of gold arguments for ChFinAnn HOT 11
- 请问怎么查看到中文格式的事件预测结果? HOT 6
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 docee.