aliutkus/groupmap
GroupMap: beyond mean and variance matching for deep learning
This project offers an alternative to traditional normalization methods in deep learning, transforming input data so it precisely matches a user-defined distribution like uniform, Gaussian, or Cauchy. Instead of just adjusting the mean and variance, it remaps the entire data distribution. This is intended for deep learning researchers and practitioners who need fine-grained control over the statistical properties of their model's internal representations.
No commits in the last 6 months.
Use this if you need to enforce a specific arbitrary statistical distribution on your deep learning model's activations or input features, rather than just normalizing their mean and variance.
Not ideal if you require your model to track and apply statistics learned over an entire training dataset during inference, as this implementation always computes statistics from the current batch.
Stars
11
Forks
—
Language
Python
License
MIT
Category
Last pushed
Sep 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aliutkus/groupmap"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/rectified-flow-pytorch
Implementation of rectified flow and some of its followup research / improvements in Pytorch
probabilists/zuko
Normalizing flows in PyTorch
davidnabergoj/torchflows
Modern normalizing flows in Python. Simple to use and easily extensible.
keishihara/flow-matching
Flow Matching implemented in PyTorch
LukasRinder/normalizing-flows
Implementation of normalizing flows in TensorFlow 2 including a small tutorial.