Comments (3)
Keras library seems to be an excellent candidate.
Keras is a high-level neural networks library, written in Python and capable of running on top of either TensorFlow or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research.
Use Keras if you need a deep learning library that:
_Allows for easy and fast prototyping (through total modularity, minimalism, and extensibility).
Supports both convolutional networks and recurrent networks, as well as combinations of the two.
Supports arbitrary connectivity schemes (including multi-input and multi-output training).
Runs seamlessly on CPU and GPU._
Read the documentation at Keras.io.
from pyaf.
Keras also has a scikit-learn API.
from pyaf.
Experiment report:
- used keras models (Sequential, LSTM + Dense).
- tested theano and tensorflow backends
- used cpu and gpu versions of the models
Will stop the work on this feature (after 2 weeks of dev/investigations) as it is not producing significant results for time seris analysis. Will keep the code as it is in case someone is interested in continuing. All the keras models are disabled by default (neutral commit)
Conclusions
- theano is interesting, simple, fully python. implements all the steps. slow compilation though.
- tensorflow is a little bit more complex (fast when it works). Models do not serialize properly. Some issues with multiprocessing (used to speed-up PyAF).
- Model performance is not yet OK. need more investigation on this.
- keras is not yet very easy to use / mature. Does not hide properly the internals of its backends (an abstract backend is missing. should give the possibility to configure backends independently of how these are implemented).
from pyaf.
Related Issues (20)
- Projections Wrongfully Linear HOT 22
- Failure to build a multiplicative ozone model with Lag1 trend HOT 5
- Add Differentiable Variant of SMAPE Performance Measure HOT 3
- Re-run the Benchmarking process for PyAF 5.0 HOT 1
- Revisit Model Complexity Definition HOT 8
- Run some Sanity Checks for PyAF 5.0 HOT 5
- Forecast Quantiles Plots can be improved HOT 6
- Python 3.11 support HOT 1
- PyAF 5.0 Release Process HOT 8
- Use MASE by default for PyAF Model Selection HOT 9
- PyAF 5.0 Final Touch 1 : discard some non-significant components HOT 1
- PyAF 5.0 Final Touch 2: Disable alpha in ridge regressions HOT 3
- Pyaf 5.0 Final Touch 3 : report plot filenames in the logs
- Provide some UML docs for PyAF integrators HOT 7
- Pyaf 5.0 Final Touch 4 : Add More Tests
- Use MaxAbsScaler for some Multiplicative Signal Transformations HOT 1
- Pyaf 5.0 Final Touch 5 : Add more info about Exogenous Data Used in ARX Models HOT 2
- Pyaf 5.0 Final Touch 6 : Disable Timing Loggers by default HOT 1
- Pyaf 5.0 Final Touch 7 : Improve the Guess of Window Length for Moving Average Trends HOT 2
- Pyaf 5.0 Final Touch 8 : Use an Optimal Choice Rule for the Quantization Signal transform HOT 3
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 pyaf.