YannDubs/Neural-Process-Family

Code for the Neural Processes website and replication of 4 papers on NPs. Pytorch implementation.

48
/ 100
Emerging

This project helps machine learning researchers explore and replicate experiments with Neural Processes (NPs). It provides PyTorch code and pretrained models for various NP architectures, allowing users to input image or 1D synthetic datasets and observe the models' predictive distributions, such as image super-resolution. This is ideal for academics and researchers focusing on probabilistic modeling and meta-learning.

231 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or student who wants to understand, experiment with, or replicate results from the Neural Process family of models.

Not ideal if you are looking for a ready-to-use application or a production-grade library for non-research purposes, as this is primarily an experimental and research-focused codebase.

machine-learning-research probabilistic-modeling meta-learning image-super-resolution academic-replication
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

231

Forks

53

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YannDubs/Neural-Process-Family"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.