EmilienDupont/neural-processes
Pytorch implementation of Neural Processes for functions and images :fireworks:
This project helps machine learning engineers or researchers quickly experiment with Neural Processes. It takes in datasets of functions or images and allows you to train models that can then predict or fill in missing parts of new data, even with limited examples. The output is a trained Neural Process model that can be used for tasks like predicting values for unknown parts of functions or completing partial images.
235 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner looking for a PyTorch implementation of Neural Processes to perform tasks like function regression or image inpainting with varying amounts of context.
Not ideal if you are a business user looking for a no-code solution to predict values or complete images, as this requires coding knowledge and an understanding of machine learning concepts.
Stars
235
Forks
47
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 08, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/EmilienDupont/neural-processes"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MaximeVandegar/Papers-in-100-Lines-of-Code
Implementation of papers in 100 lines of code.
kk7nc/RMDL
RMDL: Random Multimodel Deep Learning for Classification
OML-Team/open-metric-learning
Metric learning and retrieval pipelines, models and zoo.
miguelvr/dropblock
Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.
PaddlePaddle/models
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models...