Skip to content

Latest commit

 

History

History
25 lines (22 loc) · 600 Bytes

README.md

File metadata and controls

25 lines (22 loc) · 600 Bytes

openset-DA

Pytorch implementation of Open Set Domain Adaptation with Soft Unknown-Class Rejection.

Requirements

  • Python 3.5+
  • PyTorch 0.4
  • torchvision
  • scikit-learn

Usage

Run SVHN -> MNIST

python train_digits_osda.py --task s2m --gpu <gpu_id>

Run USPS -> MNIST

python train_digits_osda.py --task u2m --gpu <gpu_id>

Run MNIST -> USPS

python train_digits_osda.py --task m2u --gpu <gpu_id>

The results should look like below: