Time-Series-Library
mlops-v2
| Time-Series-Library | mlops-v2 | |
|---|---|---|
| 3 | 3 | |
| 4,492 | 457 | |
| 11.8% | 4.0% | |
| 8.7 | 3.7 | |
| 2 days ago | 26 days ago | |
| Python | Shell | |
| MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Time-Series-Library
-
[D] Doubts on the implementation of LSTMs for timeseries prediction (like including weather forecasts)
Don't use an LSTM. Get up to date with SoTA methods and read the papers in the field. LSTMs are not the way forward. Read the papers I suggested. It would be very useful to come to grips with both the Time Series Repository (https://github.com/thuml/Time-Series-Library) and Darts (https://github.com/unit8co/darts) as these are widely used for research and in industry.
- GitHub - thuml/Time-Series-Library: A Library for Advanced Deep Time Series Models.
-
Inverted Transformers Are Effective for Time Series Forecasting
Cool! I find it has been implemented in the tslib (https://github.com/thuml/Time-Series-Library), the results seem promising when I reproduce the experiments.
mlops-v2
- MLOps: Machine learning model management - Azure Machine Learning | Microsoft Learn
- Need help with Execute Python Script module in Azure ML Designer
-
Create a Managed ML Inference Endpoint and deployment using Terraform
I would create a second step or stage for deploying the endpoint. There is no benefit to try and force terraform to do something it wasn't designed for. You can run AZ CLI commands from terraform, but I don't have experience doing so. Check out this mlops accelerator - https://github.com/Azure/mlops-v2 You can see how they use multiple pipeline for setting up the infrastructure then training and deploying the model.
What are some alternatives?
autogluon - Fast and Accurate ML in 3 Lines of Code
Data-Engineering-Roadmap - Roadmap for Data Engineering
autogluon - AutoGluon: AutoML for Image, Text, Time Series, and Tabular Data [Moved to: https://github.com/autogluon/autogluon]
MachineLearningNotebooks - Python notebooks with ML and deep learning examples with Azure Machine Learning Python SDK | Microsoft
nsfw_data_scraper - Collection of scripts to aggregate image data for the purposes of training an NSFW Image Classifier
azure - Azure-related repository
darts - A python library for user-friendly forecasting and anomaly detection on time series.
clearml - ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution
vosk-build-model - How to create your own model for vosk
SynapseML - Simple and Distributed Machine Learning
neuralforecast - Scalable and user friendly neural :brain: forecasting algorithms.
computervision-recipes - Best Practices, code samples, and documentation for Computer Vision.