Comments (11)
Can you share what command you ran, and a screenshot of whatever you saw when you ran the command?
from embedkgqa.
I ran the following code successfully
python3 main.py --mode train --relation_dim 200 --hidden_dim 256 \ --gpu 3 --freeze 0 --batch_size 128 --validate_every 5 --hops 2 --lr 0.0005 --entdrop 0.1 --reldrop 0.2 --scoredrop 0.2 \ --decay 1.0 --model ComplEx --patience 5 --ls 0.0 --kg_type full
But when I wanna get the test score and ran the following code:
python3 main.py --mode eval --relation_dim 200 --hidden_dim 256 \ --gpu 3 --freeze 0 --batch_size 128 --validate_every 5 --hops 2 --lr 0.0005 --entdrop 0.1 --reldrop 0.2 --scoredrop 0.2 \ --decay 1.0 --model ComplEx --patience 5 --ls 0.0 --kg_type full
It didin't work, and the error message was as follows:
Traceback (most recent call last): File "main.py", line 361, in <module> embedding_dim=args.embedding_dim) TypeError: eval() takes no keyword arguments
which I think is because there's no eval function in main.py, is there?
from embedkgqa.
Yes, eval function isn't there, but eval happens when running the train command. What output did you get when you ran the train command?
from embedkgqa.
Model has exceed patience. Saving best model and exiting.
And there isn't any score message
from embedkgqa.
There IS validation accuracy, but no test accuracy
from embedkgqa.
Please see issue #14. Whenever validation accuracy increases it finds and prints the test accuracy. If this still doesn't work, please let me know.
from embedkgqa.
Thank you for your reply, I've understood. When I train on KG-50, it can be shown normally. When I train on KG-Full, the best test score appears at the first epoch, therefore no test score is shown. For convenience, will you give the eval function and online QA code in the future?
from embedkgqa.
Yes, I'll create a new issue about having separate eval function. What do you mean by online QA code?
from embedkgqa.
It means when inputing a question, output an answer, which realizes a question answering process.
from embedkgqa.
Got it. Can you please create a new issue with relevant title for this? I will close this one. It will be easier to resolve that way. Thanks.
from embedkgqa.
All right
from embedkgqa.
Related Issues (20)
- [MetaQA] Training data contains knowledge base triplets as questions HOT 2
- relation in fbwq_full
- relation matching
- MetaQA relation match HOT 1
- About ComplEx score calculation HOT 1
- The MetaQA dataset HOT 2
- Question with "half KG" protocol HOT 2
- How to build your own pruning_ train.txt
- Hello I have some questiones about the code such as what is the meaning of "best_valid" HOT 1
- Do you use the folder "train_embeddings"?
- I have some question in the relation matching
- When I run RoBERTa / main.py, running to ' creating model ' GPU takes up 0 and takes several hours to create the model.
- Is it possible to share the pdf version or ppt version slides
- How to use eval? How can I use pre trained model for QA? HOT 1
- RoBERTa used for question embedding
- Pretrained models missing HOT 1
- How to set up fbwq_full?
- miss files HOT 2
- About dataset
- pretrained_models.zip HOT 1
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 embedkgqa.