Skip to content

Latest commit

 

History

History
37 lines (25 loc) · 971 Bytes

README.md

File metadata and controls

37 lines (25 loc) · 971 Bytes

Pseudo-Label The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks

The repository implement a semi-supervised method for Deep Neural Networks, the Pseudo Label. More details for the method please refer to Pseudo-Label The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks.

The environment:

  • Python 3.6.5 :: Anaconda
  • PyTorch 0.4.0
  • torchvision 0.2.1
  • tensorboardX (for log)
  • tensorflow (for visualization)

To prepare the data:

bash data-local/bin/prepare_cifar10.sh

To run the code:

python -m experiments.cifar10_test

Visualization:

Make sure you have installed the tensorflow for tensorboard

tensorboard --logdir runs

Code Reference

pytorch-cifar@kuangliu

mean-teacher@CuriousAI

senet.pytorch@moskomule