implementation of the paper "MarginGAN: Adversarial Training in Semi-Supervised Learning"

Last update: Dec 23, 2022

Related tags

Overview

MarginGAN

This repository is the implementation of the paper "MarginGAN: Adversarial Training in Semi-Supervised Learning".

1."preliminary" is the implementation of Preliminary Experiment on MNIST of the paper. Thank the authors of pytorch-generative-model-collections and examples of pytorch, our code is widely adapted from their repositories.

To train the network, an example is as follows:

python main.py \
  --gan_type MarginGAN \
  --num_labels 600 \
  --lrC 0.1 \
  --epoch 50

2."ablation" is the implementation of Ablation Study on MNIST of the paper. To train the network, an example is as follows:

python main.py \
--gan_type MarginGAN_UG \
--num_labels 600 \
--lrC 0.01 \
--epoch 50

3."further" is the implementation of Experiment on SVHN and CIFAR-10 of the paper. Thank the authors of mean teacher, our code is widely adapted from their repositories.

To train the network, an example is as follows:

python MarginGAN_main.py \
    --dataset cifar10 \
    --train-subdir train+val \
    --eval-subdir test \
    --batch-size 128 \
    --labeled-batch-size 31 \
    --arch cifar_shakeshake26 \
    --consistency-type mse \
    --consistency-rampup 5 \
    --consistency 100.0 \
    --logit-distance-cost 0.01 \
    --weight-decay 2e-4 \
    --lr-rampup 0 \
    --lr 0.05 \
    --nesterov True \
    --labels data-local/labels/cifar10/1000_balanced_labels/00.txt  \
    --epochs 180 \
    --lr-rampdown-epochs 210 \
    --ema-decay 0.97 \
    --generated-batch-size 32

implementation of the paper "MarginGAN: Adversarial Training in Semi-Supervised Learning"

Related tags

Overview

MarginGAN

Owner

Van

Best Practices on Recommendation Systems

Software associated to AAAI paper "Planning with Biological Neurons and Synapses"

WRENCH: Weak supeRvision bENCHmark

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

Pytorch Implementation for Dilated Continuous Random Field

Improving Convolutional Networks via Attention Transfer (ICLR 2017)

A framework that constructs deep neural networks, autoencoders, logistic regressors, and linear networks

PyTorch implementation of paper "Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes", CVPR 2021

Hand tracking demo for DIY Smart Glasses with a remote computer doing the work

Circuit Training: An open-source framework for generating chip floor plans with distributed deep reinforcement learning

Pytorch implementation of face attention network

Indices Matter: Learning to Index for Deep Image Matting

[NeurIPS 2021] Source code for the paper "Qu-ANTI-zation: Exploiting Neural Network Quantization for Achieving Adversarial Outcomes"

A Simulated Optimal Intrusion Response Game

Global Filter Networks for Image Classification

Code release for "Conditional Adversarial Domain Adaptation" (NIPS 2018)

DI-HPC is an acceleration operator component for general algorithm modules in reinforcement learning algorithms

MASS (Mueen's Algorithm for Similarity Search) - a python 2 and 3 compatible library used for searching time series sub-sequences under z-normalized Euclidean distance for similarity.

For AILAB: Cross Lingual Retrieval on Yelp Search Engine

The official implementation of the Interspeech 2021 paper WSRGlow: A Glow-based Waveform Generative Model for Audio Super-Resolution.