Skip to content
Proyectos

kekmodel/FixMatch-pytorch

Ver en GitHub

kekmodel/FixMatch-pytorch has 800 GitHub stars and 184 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-19 17:28 UTC. Last push 2023-05-11.

Cómo se miden estas cifras

Crecimiento de estrellas medido

in 24h
0
in 7 days
Recopilando historial
in 15 days
Recopilando historial
in 1 month
Recopilando historial

Cambios netos en períodos que se solapan, no totales diarios. Los datos no disponibles se dejan en blanco. Las estrellas indican interés, no calidad.

Acerca de

Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"

Aprendizaje automático

README.md

Original

FixMatch

This is an unofficial PyTorch implementation of FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence. The official Tensorflow implementation is here.

This code is only available in FixMatch (RandAugment).

Results

CIFAR10

#Labels 40 250 4000
Paper (RA) 86.19 ± 3.37 94.93 ± 0.65 95.74 ± 0.05
This code 93.60 95.31 95.77
Acc. curve link link link

* November 2020. Retested after fixing EMA issues.

CIFAR100

#Labels 400 2500 10000
Paper (RA) 51.15 ± 1.75 71.71 ± 0.11 77.40 ± 0.12
This code 57.50 72.93 78.12
Acc. curve link link link

* Training using the following options --amp --opt_level O2 --wdecay 0.001

Usage

Train

Train the model by 4000 labeled data of CIFAR-10 dataset:

python train.py --dataset cifar10 --num-labeled 4000 --arch wideresnet --batch-size 64 --lr 0.03 --expand-labels --seed 5 --out results/[email protected]

Train the model by 10000 labeled data of CIFAR-100 dataset by using DistributedDataParallel:

python -m torch.distributed.launch --nproc_per_node 4 ./train.py --dataset cifar100 --num-labeled 10000 --arch wideresnet --batch-size 16 --lr 0.03 --wdecay 0.001 --expand-labels --seed 5 --out results/cifar100@10000

Monitoring training progress

tensorboard --logdir=<your out_dir>

Requirements

  • python 3.6+
  • torch 1.4
  • torchvision 0.5
  • tensorboard
  • numpy
  • tqdm
  • apex (optional)

My other implementations

References

Citations

@misc{jd2020fixmatch,
  author = {Jungdae Kim},
  title = {PyTorch implementation of FixMatch},
  year = {2020},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/kekmodel/FixMatch-pytorch}}
}