Cerebras / online-normalizationLinks
Online Normalization for Training Neural Networks (Companion Repository)
☆84Updated 4 years ago
Alternatives and similar repositories for online-normalization
Users that are interested in online-normalization are comparing it to the libraries listed below
Sorting:
- custom cuda kernel for {2, 3}d relative attention with pytorch wrapper☆43Updated 5 years ago
- PyProf2: PyTorch Profiling tool☆82Updated 5 years ago
- SelectiveBackprop accelerates training by dynamically prioritizing useful examples with high loss☆32Updated 5 years ago
- GBDT-NAS☆28Updated 3 years ago
- Make TFRecord Usable Again☆89Updated 2 years ago
- Code for paper "SWALP: Stochastic Weight Averaging forLow-Precision Training".☆62Updated 6 years ago
- Code to accompany the paper "Hierarchical Quantized Autoencoders"☆37Updated last year
- "Learning Rate Dropout" in PyTorch☆34Updated 5 years ago
- TF/Keras code for DiffStride, a pooling layer with learnable strides.☆124Updated 3 years ago
- Adaptive Gradient Clipping☆147Updated 2 years ago
- DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight …☆236Updated 2 years ago
- Structured matrices for compressing neural networks☆67Updated last year
- Continuous Augmented Positional Embeddings (CAPE) implementation for PyTorch☆42Updated 2 years ago
- Code for reproducing results in "Generative Model with Dynamic Linear Flow"☆71Updated 6 years ago
- Efficient DataLoader for PyTorch and Keras for loading datasets from web servers and object stores.☆30Updated 5 years ago
- A Re-implementation of Fixed-update Initialization☆155Updated 6 years ago
- A small demonstration of using WebDataset with ImageNet and PyTorch Lightning☆75Updated last year
- High performance pytorch modules☆18Updated 2 years ago
- Easy-to-use AdaHessian optimizer (PyTorch)☆79Updated 4 years ago
- Official code for Long Expressive Memory (ICLR 2022, Spotlight)☆70Updated 3 years ago
- ☆62Updated 5 years ago
- Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks☆18Updated 5 years ago
- Unofficial pytorch implementation of ReZero in ResNet☆24Updated 5 years ago
- ☆109Updated 4 years ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆214Updated 2 years ago
- PyTorch implementation of the paper "NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity." (NeurIPS 2020)☆66Updated 4 years ago
- ☆39Updated 5 years ago
- Implementation of "compositional attention" from MILA, a multi-head attention variant that is reframed as a two-step attention process wi…☆51Updated 3 years ago
- ☆25Updated 4 years ago
- Examples for the WebDataset PyTorch Dataset Library☆51Updated 4 years ago