zhuchen03 / gradinit
Learning to Initialize Neural Networks for Stable and Efficient Training
☆138Updated 2 years ago
Alternatives and similar repositories for gradinit:
Users that are interested in gradinit are comparing it to the libraries listed below
- Compression schema for gradients of activations in backward pass☆44Updated last year
- ☆14Updated last year
- ☆47Updated 4 years ago
- Unofficial implementation of Perceiver IO☆120Updated 2 years ago
- A small library with distillation, quantization and pruning pipelines☆26Updated 3 years ago
- Code for the paper "PALBERT: Teaching ALBERT to Ponder", NeurIPS 2022 Spotlight☆37Updated last year
- A simple library that implements CLIP guided loss in PyTorch.☆77Updated 3 years ago
- Code for MSID, a Multi-Scale Intrinsic Distance for comparing generative models, studying neural networks, and more!☆51Updated 5 years ago
- Simple but high-performing method for learning a policy of test-time augmentation☆38Updated last year
- Pytorch implementation of Variational Dropout Sparsifies Deep Neural Networks☆84Updated 3 years ago
- GPT, but made only out of MLPs☆88Updated 3 years ago
- ☆26Updated 3 years ago
- Lightweight knowledge distillation pipeline☆28Updated 3 years ago
- A library helping to gather stats and run checks during training deep learning models with Pytorch☆36Updated 2 years ago
- Distillation of BERT model with catalyst framework☆76Updated last year
- Implementation of Online Label Smoothing in PyTorch☆94Updated 2 years ago
- A GPT, made only of MLPs, in Jax☆57Updated 3 years ago
- Theoretical Deep Learning: generalization ability☆46Updated 5 years ago
- Easy-to-use AdaHessian optimizer (PyTorch)☆77Updated 4 years ago
- Very simple and short implementation of gradient boosting in 18 lines of code☆9Updated 4 years ago
- ☆199Updated 2 years ago
- Implementation of Feedback Transformer in Pytorch☆105Updated 3 years ago
- Pytorch based library to rank predicted bounding boxes using text/image user's prompts.☆51Updated 3 years ago
- Implementations of quasi-hyperbolic optimization algorithms.☆102Updated 4 years ago
- RUDOLPH: One Hyper-Tasking Transformer can be creative as DALL-E and GPT-3 and smart as CLIP☆254Updated 2 years ago
- Greedy Bayesian Posterior Approximation with Deep Ensembles. A. Tiulpin and M. B. Blaschko. (2021)☆11Updated 2 years ago
- a lightweight transformer library for PyTorch☆71Updated 3 years ago
- Tensorboard parser☆22Updated 3 months ago
- Comparing PyTorch Catalyst, Ignite, Lightning by sample code☆20Updated 2 years ago
- A collection of code snippets for my PyTorch Lightning projects☆107Updated 4 years ago