NUS-HPC-AI-Lab/LARS-ImageNet-PyTorch NUS-HPC-AI-Lab/LARS-ImageNet-PyTorch

  • Stars
    star
    37
  • Rank 699,234 (Top 15 %)
  • Language
    Python
  • License
    MIT License
  • Created about 3 years ago
  • Updated almost 3 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
NUS-HPC-AI-Lab/LARS-ImageNet-PyTorch
github

NUS-HPC-AI-Lab

Reviews

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

Repository Details

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.

More Repositories

1

OpenDiT

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference
Python
1,020
star
2

Neural-Network-Diffusion

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
Python
677
star
3

InfoBatch

Lossless Training Speed Up by Unbiased Dynamic Data Pruning
Python
264
star
4

DATM

ICLR 2024, Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching
Python
55
star
5

oh-my-server

Roff
29
star
6

Dynamic-Tuning

The official implementation of "2024Arxiv Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"
Python
22
star
7

GEOM

Pytorch implementation of "Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching"
Python
12
star
8

pytorch-lamb

PyTorch implementation of LAMB for ImageNet/ResNet-50 training
Python
11
star
9

Helen

The official implementation of "Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization"
Python
9
star
10

CTRL

Pytorch implementation of "Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching"
Python
4
star