google / bi-tempered-loss
Robust Bi-Tempered Logistic Loss Based on Bregman Divergences. https://arxiv.org/pdf/1906.03361.pdf
☆146Updated 2 years ago
Related projects: ⓘ
- Implementations of ideas from recent papers☆391Updated 3 years ago
- pytorch implement of Lookahead Optimizer☆188Updated 2 years ago
- Semi-supervised ImageNet1K models☆241Updated 4 years ago
- A simpler version of the self-attention layer from SAGAN, and some image classification results.☆210Updated 5 years ago
- lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch☆333Updated 5 years ago
- Source code for the paper "Divide and Conquer the Embedding Space for Metric Learning", CVPR 2019☆263Updated 4 years ago
- Mish Deep Learning Activation Function for PyTorch / FastAI☆160Updated 4 years ago
- Implements https://arxiv.org/abs/1711.05101 AdamW optimizer, cosine learning rate scheduler and "Cyclical Learning Rates for Training Neu…☆148Updated 5 years ago
- Experiments with Adam/AdamW/amsgrad☆194Updated 6 years ago
- Implementation and experiments for AdamW on Pytorch☆93Updated 4 years ago
- Utilities for Pytorch☆89Updated last year
- Using the CLR algorithm for training (https://arxiv.org/abs/1506.01186)☆108Updated 6 years ago
- A pytorch dataset sampler for always sampling balanced batches.☆110Updated 3 years ago
- Complementary code for the Targeted Dropout paper☆257Updated 4 years ago
- Smooth Loss Functions for Deep Top-k Classification☆246Updated 3 years ago
- Keras/TF implementation of AdamW, SGDW, NadamW, Warm Restarts, and Learning Rate multipliers☆166Updated 2 years ago
- Over9000 optimizer☆424Updated last year
- Decoupled Weight Decay Regularization (ICLR 2019)☆263Updated 5 years ago
- A New Optimization Technique for Deep Neural Networks☆532Updated 2 years ago
- Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"☆405Updated last month
- A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."☆309Updated 4 years ago
- Repo to build on / reproduce the record breaking Ranger-Mish-SelfAttention setup on FastAI ImageWoof dataset 5 epochs☆115Updated 4 years ago
- Accelerate training by storing parameters in one contiguous chunk of memory.☆291Updated 3 years ago
- Useful PyTorch functions and modules that are not implemented in PyTorch by default☆187Updated 4 months ago
- Example code showing how to use Nvidia DALI in pytorch, with fallback to torchvision. Contains a few differences to the official Nvidia …☆195Updated 4 years ago
- "Layer-wise Adaptive Rate Scaling" in PyTorch☆85Updated 3 years ago
- Unofficial PyTorch Implementation of EvoNorm☆121Updated 3 years ago
- Code for paper: "Support Vector Machines, Wasserstein's distance and gradient-penalty GANs maximize a margin"☆180Updated 4 years ago
- An implementation of shampoo☆73Updated 6 years ago
- A Re-implementation of Fixed-update Initialization☆150Updated 5 years ago