eladhoffer / bigBatchLinks
Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training of neural networks"
☆149Updated 8 years ago
Alternatives and similar repositories for bigBatch
Users that are interested in bigBatch are comparing it to the libraries listed below
Sorting:
- Implementation of "Learning with Random Learning Rates" in PyTorch.☆102Updated 5 years ago
- Implements pytorch code for the Accelerated SGD algorithm.☆215Updated 7 years ago
- Second-order optimiser for deep networks☆76Updated 6 years ago
- Code to reproduce some of the figures in the paper "On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima"☆144Updated 8 years ago
- DeepArchitect: Automatically Designing and Training Deep Architectures☆147Updated 5 years ago
- Files to create the figures in the paper "Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates"☆191Updated 7 years ago
- TensorFlow implementation of (Momentum) Stochastic Variance-Adapted Gradient.☆44Updated 7 years ago
- ☆44Updated 7 years ago
- An implementation of shampoo☆77Updated 7 years ago
- Visualizing Deep Neural Network Decisions: Prediction Difference Analysis☆118Updated 7 years ago
- A tutorial on 'Soft weight-sharing for Neural Network compression' published at ICLR2017☆145Updated 8 years ago
- Accelerate Neural Net Training by Progressively Freezing Layers☆211Updated 7 years ago
- repo that holds code for improving on dropout using Stochastic Delta Rule☆142Updated 6 years ago
- ☆79Updated 7 years ago
- Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934☆113Updated 5 years ago
- A pytorch implementation of "Self-Normalizing Neural Networks" by Klambauer et al. (still beta)☆60Updated 8 years ago
- ☆219Updated 7 years ago
- Weight initialization schemes for PyTorch nn.Modules☆70Updated 8 years ago
- Wide-residual network implementations. Best result for cifar10(97.12%), cifar100(84.12%), and other kaggle challenges☆37Updated 8 years ago
- Tensorflow implementation of Magnet Loss from "Metric Learning for Adaptive Density Discrimination"☆95Updated 7 years ago
- PyTorch implementation of PathNet: Evolution Channels Gradient Descent in Super Neural Networks☆80Updated 7 years ago
- 2.86% and 15.85% on CIFAR-10 and CIFAR-100☆295Updated 6 years ago
- Code for paper "Convergent Learning: Do different neural networks learn the same representations?"☆86Updated 9 years ago
- ☆29Updated 8 years ago
- Odds and Ends and Things I've implemented.☆78Updated 6 years ago
- ☆138Updated 8 years ago
- Snapshot Ensembles in Torch (Snapshot Ensembles: Train 1, Get M for Free)☆189Updated 8 years ago
- Lasagne code for weight normalization☆88Updated 9 years ago
- ☆69Updated 8 years ago
- ☆253Updated 8 years ago