pyro
diffmimic
pyro | diffmimic | |
---|---|---|
9 | 1 | |
8,364 | 258 | |
0.5% | - | |
8.4 | 4.1 | |
10 days ago | 7 months ago | |
Python | Python | |
Apache License 2.0 | GNU General Public License v3.0 or later |
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.
pyro
-
Show HN: Designing Bridges with PyTorch
Mostly I use pytorch for statistical modeling https://pyro.ai . Under the hood that package uses a lot of Monte Carlo integration and variational methods (i.e. integration by optimization). It does support neural nets, but probably >80% of pyro users stick to simpler hierarchical Bayesian models.
- Pyro: The Universal, Probablistic Programming Language
- The Jupyter+Git problem is now solved
- Pyro: Deep universal probabilistic programming with Python and PyTorch
-
Computational Bayesian Inference Techniques
Amortized Variational Inference (Like done in pyro.ai with neural networks)
-
[P] torchegranate: a PyTorch rewrite of the pomegranate library for probabilistic modeling
Can you compare this to Pyro, which is also built on top of PyTorch?
- [Q] Updated book or review paper on MCMC methods
- Is anyone here working in uncertainty estimation in neural networks?
-
[D] Do you train and deploy models using just one framework or multiple frameworks at work?
Using pyod, statmodels, scikit-learn, Tensorflow and pyro.ai (that is using PyTorch as backend). I always use the same framework for training and for production.
diffmimic
-
Show HN: Designing Bridges with PyTorch
Ehh, there’s a lot that goes into it. Just because a physics engine is differentiable doesn’t mean that its gradients going to be useful. For example, if you look at Brax/Mujoco in JAX, the gradients generated by Mujoco are absolute garbage if you’re trying to train a robotics controller, but the more video-game like engines give pretty good results (see https://github.com/jiawei-ren/diffmimic).
What are some alternatives?
PyMC - Bayesian Modeling and Probabilistic Programming in Python
MoCapAct - A Multi-Task Dataset for Simulated Humanoid Control
scikit-learn - scikit-learn: machine learning in Python
Prophet - Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
trueskill - An implementation of the TrueSkill rating system for Python
probability - Probabilistic reasoning and statistical analysis in TensorFlow
Keras - Deep Learning for humans
tensorflow - An Open Source Machine Learning Framework for Everyone
MLflow - Open source platform for the machine learning lifecycle
Sacred - Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
xgboost - Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
PaddlePaddle - PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice (『飞桨』核心框架,深度学习&机器学习高性能单机、分布式训练和跨平台部署)