Comments (17)
i dont know
from kgcn-pytorch.
You can share the metrics code that you wrote?thank you very much。
from kgcn-pytorch.
可以分享一下你写的实验结果评价标准代码?非常感谢。
from kgcn-pytorch.
可以分享一下你写的实验结果评价标准代码?非常感谢。
I used his code without any modifications.
论文里面的评价指标是AUC和F1,他的代码实验结果评价指标只有 损失值和roc_auc_score,是怎么看出来比论文里面的结果好10%呀?
from kgcn-pytorch.
May I ask why the test results of last.fm data set are about 10% higher than those in the paper
可以分享一下你写的实验结果评价标准代码?非常感谢。
from kgcn-pytorch.
我也没改,按照源代码跑的结果,具体明天我看一下
from kgcn-pytorch.
好的,感谢感谢
from kgcn-pytorch.
from kgcn-pytorch.
roc_auc_score算出来的结果就是Auc的值,我跑出来的结果roc_auc_score=0.89568,F1=0.80918
…
---Original--- From: @.> Date: Tue, Aug 2, 2022 22:19 PM To: @.>; Cc: @.>;"State @.>; Subject: Re: [zzaebok/KGCN-pytorch] May I ask why the test results of last.fmdata set are about 10% higher than those in the paper (Issue #5) 好的,感谢感谢 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you modified the open/close state.Message ID: @.***>
嗯嗯,感谢感谢,可以分享一下F1是怎么写的吗
from kgcn-pytorch.
from kgcn-pytorch.
from sklearn.metrics import roc_auc_score,f1_score这两个函数,你跑出来结果怎么样呢,可以告诉我一下吗
…
---Original--- From: @.> Date: Wed, Aug 3, 2022 16:58 PM To: @.>; Cc: @.>;"State @.>; Subject: Re: [zzaebok/KGCN-pytorch] May I ask why the test results of last.fmdata set are about 10% higher than those in the paper (Issue #5) roc_auc_score算出来的结果就是Auc的值,我跑出来的结果roc_auc_score=0.89568,F1=0.80918 … ---Original--- From: @.> Date: Tue, Aug 2, 2022 22:19 PM To: @.>; Cc: @.>;"State @.>; Subject: Re: [zzaebok/KGCN-pytorch] May I ask why the test results of last.fmdata set are about 10% higher than those in the paper (Issue #5) 好的,感谢感谢 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you modified the open/close state.Message ID: @.> 嗯嗯,感谢感谢,可以分享一下F1是怎么写的吗 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you modified the open/close state.Message ID: @.>
Auc好像是0.86左右,f1没有跑,每天加上f1再跑一边,给你具体结果
from kgcn-pytorch.
Auc是0.85610,f1是0.779465
from kgcn-pytorch.
from kgcn-pytorch.
我也不知道
from kgcn-pytorch.
请问您能分享一下加入了AUC,F1score的文件或者代码吗?我加入了评价指标的代码,但是跑出来超级低,我不知道哪里出了问题。能否看一下您的代码?非常感谢
from kgcn-pytorch.
请问您能分享一下加入了AUC,F1score的文件或者代码吗?我加入了评价指标的代码,但是跑出来超级低,我不知道哪里出了问题。能否看一下您的代码?非常感谢
暂时不用了,我知道了,我按照论文设置的batchsize跑出来很低auc0.5,按照本复现代码的作者设置的batchsize跑出来很好。
from kgcn-pytorch.
outputs_predict = [int(item > 0.5) for item in outputs.cpu().detach().numpy()]
total_f1 += f1_score(labels.cpu().detach().numpy(), outputs_predict)
print('[Epoch {}]test_f1: '.format(epoch + 1), total_f1 / len(test_loader))
这是我加的f1
from kgcn-pytorch.
Related Issues (9)
- adj numpy to torch tensor
- Why is the result so much better than the original? HOT 2
- Questions about LabelEncoder
- typo
- enviroment requirement HOT 2
- When training the Movielens data set, the training process becomes very slow HOT 1
- RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (CPU) HOT 2
- Request to use your code HOT 2
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 kgcn-pytorch.