OpenSSC

This repository contains the implementation of our MICCAI 2024 paper "Open-Set Semi-Supervised Classification with Learnable Prototypes and Outlier Filter"

Requirements

python 3.6

numpy 1.16.4

Pytorch 1.8.1

pillow 7.0.0

opencv-python 4.1.0

Usage

1. Clone the repository, and download the pre-trained ImaenNet model, put them into ./ folder. The details of the training are in train_open.py file.

2. And then run the code：python train_open.py Note that the parameters and paths should be set beforehand

LICENSE

Code can only be used for ACADEMIC PURPOSES. NO COMERCIAL USE is allowed. Copyright © College of Computer Science, Nankai University. All rights reserved.