Discover NUS-HPC-AI-Lab/Neural-Network-Diffusion Open Source project

Stars
677
Rank 64,449 (Top 2 %)
Language
Python
Created 7 months ago
Updated 3 months ago

NUS-HPC-AI-Lab

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

We introduce a novel approach for parameter generation, named neural network diffusion (\textbf{p-diff}, p stands for parameter), which employs a standard latent diffusion model to synthesize a new set of parameters

OpenDiT

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference

Python

1,020

InfoBatch

Lossless Training Speed Up by Unbiased Dynamic Data Pruning

Python

264

DATM

ICLR 2024, Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching

Python

LARS-ImageNet-PyTorch

Accuracy 77%. Large batch deep learning optimizer LARS for ImageNet with PyTorch and ResNet, using Horovod for distribution. Optional accumulated gradient and NVIDIA DALI dataloader.

Python

oh-my-server

Roff

Dynamic-Tuning

The official implementation of "2024Arxiv Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"

Python

GEOM

Pytorch implementation of "Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching"

Python

pytorch-lamb

PyTorch implementation of LAMB for ImageNet/ResNet-50 training

Python

Helen

The official implementation of "Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization"

Python

CTRL

Pytorch implementation of "Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching"

Python

NUS-HPC-AI-Lab/Neural-Network-Diffusion

NUS-HPC-AI-Lab

Reviews

Repository Details

More Repositories