noahgolmant / pytorch-larsLinks
"Layer-wise Adaptive Rate Scaling" in PyTorch
☆87Updated 4 years ago
Alternatives and similar repositories for pytorch-lars
Users that are interested in pytorch-lars are comparing it to the libraries listed below
Sorting:
- Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934☆113Updated 5 years ago
- An implementation of shampoo☆77Updated 7 years ago
- A Re-implementation of Fixed-update Initialization☆155Updated 6 years ago
- Simple implementation of the LSUV initialization in PyTorch☆58Updated last year
- An official collection of code in different frameworks that reproduces experiments in "Group Normalization"☆117Updated 4 years ago
- This repository is no longer maintained. Check☆81Updated 5 years ago
- ☆62Updated 5 years ago
- Code to reproduce some of the figures in the paper "On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima"☆145Updated 8 years ago
- homura is a library for fast prototyping DL research☆106Updated 3 years ago
- PyTorch implementation of shake-drop regularization☆55Updated 5 years ago
- Implementation of the reversible residual network in pytorch☆105Updated 3 years ago
- [NeurIPS'20] GradAug: A New Regularization Method for Deep Neural Networks☆94Updated 4 years ago
- On Network Design Spaces for Visual Recognition☆96Updated 5 years ago
- ☆165Updated 6 years ago
- Code for paper "SWALP: Stochastic Weight Averaging forLow-Precision Training".☆62Updated 6 years ago
- Implements pytorch code for the Accelerated SGD algorithm.☆215Updated 7 years ago
- Unofficial PyTorch Implementation of EvoNorm☆122Updated 3 years ago
- Simple experiment of Apex (A PyTorch Extension)☆47Updated 5 years ago
- A PyTorch implementation of shake-shake☆111Updated 5 years ago
- Utilities for Pytorch☆88Updated 2 years ago
- Implementation of soft parameter sharing for neural networks☆69Updated 4 years ago
- Filter Response Normalization tested on better ImageNet baselines.☆35Updated 5 years ago
- [NeurIPS 2020 Oral] Is normalization indispensable for training deep neural networks?☆34Updated 3 years ago
- [NeurIPS '18] "Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?" Official Implementation.☆129Updated 3 years ago
- pytorch implementation of basic kmeans algorithm(lloyd method with forgy initialization) with gpu support☆93Updated 7 years ago
- ☆23Updated 6 years ago
- Delta Orthogonal Initialization for PyTorch☆18Updated 7 years ago
- Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training o…☆149Updated 8 years ago
- Code for https://arxiv.org/abs/1810.04622☆141Updated 5 years ago
- Discovering Neural Wirings (https://arxiv.org/abs/1906.00586)☆137Updated 5 years ago