Skip to content

zhunzhong07/pytorch-cifar

This branch is 47 commits behind kuangliu/pytorch-cifar:master.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

author
kuangliu
Jun 7, 2017
e68081e · Jun 7, 2017

History

31 Commits
Jun 7, 2017
Jun 6, 2017
May 27, 2017
May 9, 2017

Repository files navigation

Train CIFAR10 with PyTorch

I'm playing with PyTorch on the CIFAR10 dataset.

Pros & cons

Pros:

  • Built-in data loading and augmentation, very nice!
  • Training is fast, maybe even a little bit faster.
  • Very memory efficient!

Cons:

  • No progress bar, sad :(
  • No built-in log.

Accuracy

Model Acc.
VGG16 92.64%
ResNet18 93.02%
ResNet50 93.62%
ResNet101 93.75%
ResNeXt29(32x4d) 94.73%
ResNeXt29(2x64d) 94.82%
DenseNet121 95.04%
ResNet18(pre-act) 94.75%

Learning rate adjustment

I manually change the lr during training:

  • 0.1 for epoch [0,150)
  • 0.01 for epoch [150,250)
  • 0.001 for epoch [250,350)

Resume the training with python main.py --resume --lr=0.01

About

95.04% on CIFAR10 with PyTorch

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%