Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings
NotificationsYou must be signed in to change notification settings

Ascend-Research/Reparameterization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Official implementation of "Reparameterization through Spatial Gradient Scaling".

alt text

CIFAR-100

VGG-11

CUDA_VISIBLE_DEVICES=0 python tools/train.py -c configs/strategies/SGS/wei_cifar.yaml --model wei_vgg11_bn --dataset cifar100 --experiment cifar100_wei_vgg11_bn_nmi5 --sgs --data-path ~/datasets/CIFAR --dist-port 29500
ModelBaselinePaperThis Repo
VGG-1170.8±0.173.2±0.173.4±0.1
VGG-1674.9±0.176.2±0.176.7±0.1
ResNet-1877.8±0.178.8±0.178.6±0.1
ModelBaseline (GPUs hours)Ours (GPUs hours)
VGG-110.620.65
VGG-160.830.89
ResNet-181.021.15

ImageNet

bash tools/dist_train.sh 8 configs/strategies/SGS/resnet.yaml resnet18 --experiment imagenet_res18_sgs --sgs --data-path ~/datasets/ImageNet --dist-port 29500
ModelBaselinePaperThis Repo
ResNet-1871.13±0.0471.65±0.0571.62

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors3

  •  
  •  
  •  
[8]ページ先頭
©2009-2025 Movatter.jp