APPN: an Attention-based Pseudo-label Propagation Network for few-shot learning with noisy labels

The aim for this repository is to contain clean, readable and tested code to produce APPN.

This project is written in python 3.6 and Pytorch and assumes you have a GPU.

our model in the file model.py

Getting started

CIFAR-FS

• Change directory to ./filelists/cifar
• Download CIFAR-FS
• run python make.py in the terminal

FC100

• Change directory to ./filelists/fc100
• Download FC100
• run python make.py in the terminal

miniImagenet

• Change directory to ./filelists/miniImagenet
• Download miniImagenet
• run python make.py in the terminal

tieredImagenet

• Change directory to ./filelists/tieredImagenet
• Download tieredImagenet
• run python make.py in the terminal

Running the scripts

To train the APPN network in the terminal, use:

$ python experiment.sh