fbadine / lstnet Goto Github PK
View Code? Open in Web Editor NEWA Tensorflow / Keras implementation of "Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks" paper
A Tensorflow / Keras implementation of "Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks" paper
Is there Attention layer in the code?
Paralleled with SkipGRU module.
When I tried run the implementation on exchange rate, I got the error below. Where are these missings functions?
Traceback (most recent call last):
File "main.py", line 13, in
from util.model_util import LoadModel, SaveModel, SaveResults, SaveHistory
ModuleNotFoundError: No module named 'util'
The idea of predicting new data considers that they are not normalized, however, the file script normalizes them in the prediction of unknown samples.
In main.py, the following imports are done.
from util.model_util import LoadModel, SaveModel, SaveResults, SaveHistory
from util.Msglog import LogInit
However this util module seems to be missing. Where can I find these?
Thanks
Hello, Thanks for your code. I was trying PyTorch implementation and it gave me way better results than this Tensorflow implementation, even though I am using the same hyperparameters, optimizer. What other differences do you think I should look at?
Why the default of '--series-to-plot' is 0 and what does it mean?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.