ENorm logo

ENorm

Equi-normalization of Neural Networks (by Facebook)
1
8
+ 1
0

What is ENorm?

A fast and iterative method for minimizing the L2 norm of the weights of a given neural network that provably converges to a unique solution.
ENorm is a tool in the Machine Learning Tools category of a tech stack.
ENorm is an open source tool with 115 GitHub stars and 9 GitHub forks. Here’s a link to ENorm's open source repository on GitHub

Who uses ENorm?

Companies

ENorm's Features

  • Asymmetric scaling
  • Python 3.6 and latest support

ENorm Alternatives & Comparisons

What are some alternatives to ENorm?
TensorFlow
TensorFlow is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.
Keras
Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on TensorFlow or Theano. https://keras.io/
scikit-learn
scikit-learn is a Python module for machine learning built on top of SciPy and distributed under the 3-Clause BSD license.
PyTorch
PyTorch is not a Python binding into a monolothic C++ framework. It is built to be deeply integrated into Python. You can use it naturally like you would use numpy / scipy / scikit-learn etc.
CUDA
A parallel computing platform and application programming interface model,it enables developers to speed up compute-intensive applications by harnessing the power of GPUs for the parallelizable part of the computation.
See all alternatives

ENorm's Followers
8 developers follow ENorm to keep up with related blogs and decisions.