tbachlechner / ReZero-examples
PyTorch Examples repo for "ReZero is All You Need: Fast Convergence at Large Depth"
☆62Updated 6 months ago
Alternatives and similar repositories for ReZero-examples:
Users that are interested in ReZero-examples are comparing it to the libraries listed below
- MTAdam: Automatic Balancing of Multiple Training Loss Terms☆36Updated 4 years ago
- An implementation of shampoo☆74Updated 6 years ago
- Pytorch implementation of the hamburger module from the ICLR 2021 paper "Is Attention Better Than Matrix Decomposition"☆98Updated 4 years ago
- ☆47Updated 4 years ago
- ☆32Updated 5 years ago
- "Learning Rate Dropout" in PyTorch☆34Updated 5 years ago
- custom cuda kernel for {2, 3}d relative attention with pytorch wrapper☆43Updated 4 years ago
- A pytorch implementation for the LSTM experiments in the paper: Why Gradient Clipping Accelerates Training: A Theoretical Justification f…☆44Updated 5 years ago
- ☆14Updated 5 years ago
- [NeurIPS'19] [PyTorch] Adaptive Regularization in NN☆67Updated 5 years ago
- Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation pr…☆45Updated 5 years ago
- Code base for SRSGD.☆28Updated 4 years ago
- [ICML 2020] code for "PowerNorm: Rethinking Batch Normalization in Transformers" https://arxiv.org/abs/2003.07845☆119Updated 3 years ago
- Partially Adaptive Momentum Estimation method in the paper "Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep …☆39Updated last year
- Implementation of soft parameter sharing for neural networks☆69Updated 4 years ago
- Unsupervised Data Augmentation experiments in PyTorch☆59Updated 5 years ago
- Delta Orthogonal Initialization for PyTorch☆18Updated 6 years ago
- A simple Transformer where the softmax has been replaced with normalization☆19Updated 4 years ago
- The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) p…☆40Updated 4 years ago
- Notes from NeurIPS 2019☆29Updated 5 years ago
- ☆34Updated 6 years ago
- "Layer-wise Adaptive Rate Scaling" in PyTorch☆86Updated 4 years ago
- Implementation of the reversible residual network in pytorch☆103Updated 3 years ago
- This repository is no longer maintained. Check☆81Updated 4 years ago
- PyTorch implementation of HashedNets☆36Updated last year
- Code for the ICML'20 paper "Improving Transformer Optimization Through Better Initialization"☆89Updated 4 years ago
- Improving generalization by controlling label-noise information in neural network weights.☆40Updated 4 years ago
- SSL using PyTorch☆49Updated 5 years ago
- diffGrad: An Optimization Method for Convolutional Neural Networks☆55Updated 2 years ago
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆102Updated 3 years ago