Comments (2)
The question is just out of curiosity.
The random seeds in deep learning would bring fluctuations to the model results. So I'd like to ask how your model behaves under other seeds?
from kdd2018_mpcn.
Hey there,
1337 is just an artifact and default value of all my codebases. I don't remember how 1337 came about but i probably started using some other person's codebase with 1337 seed initially. that's all the number stuck everywhere. also some of my codebases come from the same private repo which i extracted a slice to release on github.
In general, I don't really pay attention to the seed actually. I believe this seed only controls python's random number generator and not TF or the deep learning framework as I still observe different values for different runs (not very sure about this...).
from kdd2018_mpcn.
Related Issues (13)
- get_rec_config not defined HOT 1
- Some experimental details about parameter setting HOT 1
- Does a sample of (user reviews, item reviews, rating) contains the review wrote by user for item? HOT 2
- What is the user_negative mean in file prep/prep_amazon2.py?
- Can you share running instructions and code for data prep? HOT 5
- Can you share the data prep of the Amazon HOT 2
- About hierarchical inputs HOT 1
- About some bug in prep_amazon2.py HOT 6
- Some issues about prep_amazon2.py and train.py HOT 5
- other project HOT 2
- Some problems in train.py HOT 3
- Can you share running instruction of yelp?
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 kdd2018_mpcn.