Skip to content

ma-xu/Open-Set-Recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Open Set Recognition Project

Ongoing Open Set Recognition project using PyTorch.

For any issue and question, please email ma.xu1@northeastern.edu

Attention: need to be re-constrcuted due to my experimental implementations (especially my methods).

Requirements

For different Algorithms and different datasets, the requirements varies. In general, the basic and must requirements are:

# pytorch 1.4+, torchvision 0.7.0 +
pip3 install torch torchvision
# sklearn
pip3 install -U scikit-learn
# numpy
pip3 install numpy
# scikit-learn-0.23.2
pip3 install -U sklearn

For OpenMax:

pip3 install libmr

For plotting MNIST:

pip3 install imageio
pip3 install tqdm

Supporting

Have a try

Click go link to the related method/dataset and have a try.

CIFAR-100 CIFAR-10 MNIST ImageNet
OpenMax [ReadME] go
OLTR [ReadME] go
CenterLoss [ReadME] go