Comments (5)
你好,我跑的结果比你还低1-2个点。请问你有用with_error参数吗,然后epochs是采用论文里的6次,还是用的run_spellgcn.sh里面的10次epochs.
from spellgcn.
你好,我跑的结果比你还低1-2个点。请问你有用with_error参数吗,然后epochs是采用论文里的6次,还是用的run_spellgcn.sh里面的10次epochs.
我全都是按默认的setting跑的,with_error=False,epoch=10,直接测试最后一个ckpt的performance。唯一有一点不同,是因为显存限制我把训练的batch_size从32改成了20。
from spellgcn.
各位大佬有用bert复现结果的吗?我用spellgcn、bert做这个问题,出现的情况就是完全相同的训练超参,固定一个随机种子,spellgcn指标高于bert,换一个随机种子,bert指标反过来高于spellgcn了,有点晕。
from spellgcn.
@drzqb 你是怎么用的bert,直接把gcn层去掉了么,我用pytorch复现发现比他的tensorflow复现的结果差好多
from spellgcn.
您好,我把Wang2018的伪数据也加到训练集中训练,在SIGHAN15和SIGHAN14上得到结果比paper上写的低1个点左右。
Sentce Level,Detection F1 SIGHAN15: paper上写的77.7,复现结果:76.46;SIGHAN14: paper上写的67.2,复现结果65.43。
我跑了多次,结果有高有低,但都没有达到paper上报但值。paper上说报的结果是跑5次平均之后的结果,理论上跑多次得到的值应该在paper得到的值上下才对。
请问可以给一个可以完全复现paper上结果的代码setting吗,比如随机种子的值或其他细节之处?
你好,想问下你的27.1k的训练数据是处理的和TrainingTruthAll.txt和TrainingInputAll.txt格式一样然后直接加到这两个文件里嘛,我也是用的源代码的参数,但是训练结果的recall和文章里差10个点左右,呜呜
from spellgcn.
Related Issues (20)
- 为什么relation_vocab.txt中的关系只有三种? HOT 4
- 代码如何实现多卡训练 HOT 7
- 训练方式疑问
- 训练数据集 HOT 2
- 关于模糊音的数据问题
- 多字少字问题 HOT 1
- 无法复现结果 HOT 9
- 论文中LMC baseline模型的Character-level指标,在SIGHAN15 上的结果可能写成了在SIGHAN14上的结果 HOT 2
- 测评方法 HOT 5
- ValueError: Shape must be rank 2 but is rank 3 for 'gcn/GCN-0/relation_prototype_scope/MatMul' (op: 'MatMul') with input shapes: [2,4755,768], [768,1]. HOT 3
- 关于检测效率的疑问
- 请教各位大佬关于推理速度的问题 HOT 1
- 代码调用GPU的效率是不是很拉跨啊 HOT 4
- 请问可否开源出你们训练出的最优模型? HOT 1
- 请问模型如何高效部署?
- error HOT 2
- OOM问题
- OOM问题
- 验证集
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 spellgcn.