Comments (7)
My initial try with just requiring gluton-ts did not work out so well as the pydantic decorators call mxnet etc.
I think the tight coupling with mxnet is something we should work on. Ideally, the basic parts are generic and don't assume any ml library.
from pytorch-ts.
Thanks david, yes no ill intent here. Ideally I would love to just depend on gluonts (and there is an issue about that on the gluonts side) and in the mean time i have tried my best to keep the license files in the headers and also included the gluonts license in here as well.
I can certainly go over it again now that the paper deadlines are over and see what I missed and would like to acknowledge any attribution. Would love your input on how best to do that?
Also note that any fixes or features I add here I try to push it to gluonts as well: https://github.com/awslabs/gluon-ts/commits?author=kashif
from pytorch-ts.
Thanks for your answer, I should have sayed also that it is really cool to have an option to use pytorch for TS forecasting!
I did not look at all files, it is true that some have the copyright header but a lot of them are missing it (it should be easy to fix). For the contribution, perhaps you could say something in the README that the repository is a fork of gluon-ts with some new models and the functionality to run on pytorch?
As you said, it would be great to just depend on gluon-ts for common functionalities (maybe this is possible already for i/o stuff such as datasets and evaluation?). I know about your contributions in gluon-ts are they are very much appreciated! (also read your multivariate paper, cool stuff!).
from pytorch-ts.
thanks! I'll get the headers sorted ASAP and change the readme as per your request as well.
My initial try with just requiring gluton-ts did not work out so well as the pydantic
decorators call mxnet etc.
from pytorch-ts.
Thanks a lot for doing this, hope that the backends of gluon-ts will be able to support pytorch soon!
from pytorch-ts.
I completely agree with Jasper. Basically, almost everything thats not in the pts/model folder can be shared code between gluon-ts and pts.
Maybe a good structure is one package that contains all the sharable code (say core-ts
) and separate packages containing mxnet/pytorch models and having core-ts
as their dependency.
from pytorch-ts.
@geoalgo can you kindly have a look now? Thanks!
from pytorch-ts.
Related Issues (20)
- Timegrad example notebook has an error. HOT 1
- Hyperparameter settings (TemporalFlow) HOT 1
- Can not replicate the experiment results in the paper HOT 8
- delete 1 hour data in training dataset can lead to much better results HOT 1
- Validation Samplers
- Exception: Reached maximum number of idle transformation calls. HOT 11
- Branch: 0.7.0 - RuntimeError: Cannot serialize type diffusers.schedulers
- Run out of memory when I tried to run "Time-Grad-Electricity.ipynb" HOT 2
- Missing Trainer in version-0.7.0 HOT 1
- Enhancing Covariate Conditioning in TimeGrad HOT 1
- Multivariate-Flow-Solar:an error is reported when flow_type='MAF' HOT 1
- Reproducibility issue in TimeGrad with ver-0.7.0 HOT 8
- Inquiry about implementation of mean_wQuantileLoss and m_sum_mean_wQuantileLoss
- A question about the hyperparameter Settings of the model Time-Grad on both of Solar and Wikipedia datasets.
- Issue while runing the Readme
- can't generate dataset "pts_m5" HOT 5
- TypeError: `model` must be a `LightningModule` or `torch._dynamo.OptimizedModule`, got `TimeGradLightningModule`
- ValidationError: 1 validation error for PyTorchPredictorModel
- TypeError: PyTorchPredictor.__init__() got an unexpected keyword argument 'freq' HOT 14
- too many indices for array: array is 1-dimensional, but 2 were indexed
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 pytorch-ts.