Comments (2)
It seems that the errors you have mentioned are caused by loading a wrong saved model. Note that the TEN model is initialized by a TEN-X model, so when you change to another dataset, you should not only change the args['data_dir'] argument, but also the args['resume'] argument which indicates the directory where the TEN-X model is saved. Maybe you have loaded a TEN-X model on the DSTC2 dataset when you train a TEN model on the WOZ dataset, which leads to the mismatching of parameter dimensions in your created model and loaded model.
from ten_emnlp2020.
Actually, i am just training TEN-X model, i did not went to TEN. By default in config file the args['resume'] is none for Ten-X. you are right that when i changed dataset then it was loading the last saved model from directory which might be causing to lead mismatching dimensions parameters. now i have just changed the directory from TEN-X to TEN-X/woz for woz dataset in root experimental folder i.e. args ['dexp']. its now training and working. thank you.
from ten_emnlp2020.
Related Issues (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 ten_emnlp2020.