Comments (4)
No. This is intend to make sure the order of calculation is correct.
See Use more memory to avoid ordering issue
from keras-transformer-xl.
I am not following why the nested function needs to be executed 10x. Given that you are calling Memory inside the for loop, it reinitializes the state, such that the output will always be the same.
My comment is regarding why
for _ in range(10):
exists
from keras-transformer-xl.
Because before that commit, the memory block produces wrong output with a random probability. I have to make sure it always produces the expected output.
from keras-transformer-xl.
Thanks for clarifying. I appreciate your work!
from keras-transformer-xl.
Related Issues (8)
- Visualization HOT 3
- Make documentation clearer about the MemorySequence class and the expected inputs and outputs passed. HOT 3
- Transformer-Xl for a Classification Task HOT 1
- Transformer-Xl for a Classification Task HOT 1
- can you reproduce the sota transformer-xl results on wikitext-103
- can you reproduce the sota transformer-xl results on wt103? HOT 1
- I find the structure has a little difference to official model. 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 keras-transformer-xl.