sseung0703 / Lightweighting_CookbookLinks
This project attempts to build neural network training and lightweighting cookbook including three kinds of lightweighting solutions, i.e., knowledge distillation, filter pruning, and quantization.
☆22Updated 3 years ago
Alternatives and similar repositories for Lightweighting_Cookbook
Users that are interested in Lightweighting_Cookbook are comparing it to the libraries listed below
Sorting:
- Tensorflow2 training code with jit compiling on multi-GPU.☆17Updated 4 years ago
- Reproduction of Vision Transformer in Tensorflow2. Train from scratch and Finetune.☆48Updated 3 years ago
- Learning Features with Parameter-Free Layers, ICLR 2022☆84Updated 2 years ago
- ☆26Updated 7 months ago
- Official repository for Automated Learning Rate Scheduler for Large-Batch Training (8th ICML Workshop on AutoML)☆40Updated 3 years ago
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆205Updated 2 years ago
- Official Pytorch implementation of C3-GAN (Spotlight at ICLR 2022)☆127Updated 3 years ago
- Unofficial JAX implementations of deep learning research papers☆156Updated 3 years ago
- A minimal implementation of Gaussian process regression in PyTorch☆64Updated 2 years ago
- Automatic Mixed Precision Tutorials using pytorch. Based on PyTorch 1.6 Official Features, implement classification codebase using custo…☆89Updated 5 years ago
- Jax/Flax implementation of DeiT and DeiT-III (ViT)☆18Updated 8 months ago
- Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch☆184Updated 2 years ago
- EfficientNet, MobileNetV3, MobileNetV2, MixNet, etc in JAX w/ Flax Linen and Objax☆128Updated last year
- Tensorflow Implementation of "Slowing Down the Weight Norm Increase in Momentum-based Optimizers"☆47Updated 4 years ago
- A GPT, made only of MLPs, in Jax☆58Updated 4 years ago
- AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (ICLR 2021)☆415Updated 4 years ago
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆85Updated last year
- Code release for "Dropout Reduces Underfitting"☆314Updated 2 years ago
- OSLO: Open Source framework for Large-scale model Optimization☆309Updated 3 years ago
- ☆75Updated 2 years ago
- PyTorch Model Compression☆234Updated 2 years ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆215Updated 2 years ago
- ☆55Updated last year
- Making a PyTorch model easier than ever!☆79Updated 3 years ago
- OSLO: Open Source for Large-scale Optimization☆175Updated last year
- ☆66Updated 5 months ago
- The OTHER pytorch boilerplate☆45Updated 5 months ago
- A performance library for machine learning applications.☆184Updated last year
- read 1 paper everyday (only weekday)☆56Updated 3 years ago
- FID computation in Jax/Flax.☆28Updated last year