Smooth Neighbors on Teacher Graphs for Semi-supervised Learning (CVPR 2018 spotlight)

This is an implementation of SNTG reproducing the results in Smooth Neighbors on Teacher Graphs for Semi-supervised Learning.

By Yucen Luo, Jun Zhu, Mengxi Li, Yong Ren, Bo Zhang.

Most code is adapted from Temporal Ensembling

Quick start

Reproducing the results on MNIST, SVHN and CIFAR10.

Modify the hyperparameters in config.py and then python train_emb.py

Requirements

Theano 0.9.0.dev4
Lasagne 0.2.dev1
CUDA toolkit 8.0, CUDNN 5105