XuezheMax / apollo

Related projects ⓘ

Alternatives and complementary repositories for apollo

• majumderb / rezero
  Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"
  ☆407Updated 3 months ago
• alphadl / lookahead.pytorch
  lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch
  ☆334Updated 5 years ago
• lonePatient / lookahead_pytorch
  pytorch implement of Lookahead Optimizer
  ☆188Updated 2 years ago
• egg-west / AdamW-pytorch
  Implementation and experiments for AdamW on Pytorch
  ☆93Updated 4 years ago
• KrisKorrel / sparsemax-pytorch
  Implementation of Sparsemax activation in Pytorch
  ☆156Updated 4 years ago
• lucidrains / hamburger-pytorch
  Pytorch implementation of the hamburger module from the ICLR 2021 paper "Is Attention Better Than Matrix Decomposition"
  ☆98Updated 3 years ago
• twistedcubic / attention-rank-collapse
  [ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.
  ☆162Updated 3 years ago
• lorenmt / maxl
  The implementation of "Self-Supervised Generalisation with Meta Auxiliary Learning" [NeurIPS 2019].
  ☆170Updated 2 years ago
• lucidrains / sinkhorn-transformer
  Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention
  ☆253Updated 3 years ago
• thegregyang / LossUpAccUp
  Loss and accuracy go opposite ways...right?
  ☆90Updated 4 years ago
• PhilJd / contiguous_pytorch_params
  Accelerate training by storing parameters in one contiguous chunk of memory.
  ☆291Updated 4 years ago
• zhuohan123 / macaron-net
  Codes for "Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View"
  ☆145Updated 5 years ago
• cybertronai / pytorch-lamb
  Implementation of https://arxiv.org/abs/1904.00962
  ☆369Updated 3 years ago
• AMLab-Amsterdam / L0_regularization
  Learning Sparse Neural Networks through L0 regularization
  ☆239Updated 4 years ago
• ryanchankh / redunet_demo
  ☆80Updated 3 years ago
• tczhangzhi / awesome-normalization-techniques
  Papers for normalization techniques, released codes collections.
  ☆225Updated 4 years ago
• layer6ai-labs / T-Fixup
  Code for the ICML'20 paper "Improving Transformer Optimization Through Better Initialization"
  ☆89Updated 3 years ago
• Yonghongwei / Gradient-Centralization
  A New Optimization Technique for Deep Neural Networks
  ☆533Updated 2 years ago
• tbachlechner / ReZero-examples
  PyTorch Examples repo for "ReZero is All You Need: Fast Convergence at Large Depth"
  ☆62Updated 3 months ago
• LiyuanLucasLiu / Transformer-Clinic
  Understanding the Difficulty of Training Transformers
  ☆328Updated 2 years ago
• epfml / collaborative-attention
  Code for Multi-Head Attention: Collaborate Instead of Concatenate
  ☆150Updated last year
• hongyi-zhang / Fixup
  A Re-implementation of Fixed-update Initialization
  ☆151Updated 5 years ago
• guolinke / TUPE
  Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve exis…
  ☆250Updated 3 years ago
• sacmehta / delight
  DeLighT: Very Deep and Light-Weight Transformers
  ☆467Updated 4 years ago
• hosseinshn / GradNorm
  This in my Demo of Chen et al. "GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks" ICML 2018
  ☆169Updated 3 years ago
• megvii-model / MABN
  ☆182Updated last year
• takashiishida / flooding
  [ICML 2020] code for the flooding regularizer proposed in "Do We Need Zero Training Loss After Achieving Zero Training Error?"
  ☆92Updated last year
• HaozhiQi / ISONet
  Deep Isometric Learning for Visual Recognition (ICML 2020)
  ☆143Updated 2 years ago
• mpyrozhok / adamwr
  Implements https://arxiv.org/abs/1711.05101 AdamW optimizer, cosine learning rate scheduler and "Cyclical Learning Rates for Training Neu…
  ☆150Updated 5 years ago
• csrhddlam / pytorch-checkpoint
  ☆165Updated 5 years ago