randaugment 开源项目推荐（21 个）

huggingface /pytorch-image-models

最大的 PyTorch 图像编码器/骨干网络集合。包括训练、评估、推理、导出脚本和预训练权重——ResNet、ResNeXT、EfficientNet、NFNet、Vision Transformer (ViT)、MobileNetV4、MobileNet-V3 & V2、RegNet、DPN、CSPNet、Swin Transformer、MaxViT、CoAtNet、ConvNeXt 等

PaddlePaddle /PaddleClas

A treasure chest for visual classification and recognition powered by PaddlePaddle

kekmodel /FixMatch-pytorch

非官方的PyTorch实现的“FixMatch：以一致性和信心简化半监督学习”

cavalleria /cavaface

人脸识别训练项目（pytorch）

affjljoo3581 /Differentiable-RandAugment

使用可微操作优化 RandAugment

seungjunlee96 /PointNet2_RandAugment

Applying RandAugment on PointNet++

shjo-april /Tensorflow_FixMatch

[Re-implementation] FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

wangermeng2021 /FastClassification

FastClassification 是一个用于类别分类的 tensorflow 工具箱。它提供包含多种骨干网络和训练技巧的训练模块，以实现最先进的类别分类。

tgilewicz /uniformaugment

UniformAugment 的非官方 PyTorch 复现。

sayakpaul /Keras-Examples-RandAugment

Full experimentation notebook for my Keras Example on using RandAugment.

manhph2211 /CLS-Template

A simple template for classifying things

chjort /chambers

深度学习模块集合

reshalfahsi /image-classification-augmentation

使用 Swin Transformer 结合 RandAugment、CutMix 和 MixUp 进行图像分类

aybarburak /MICCAI_ISIC

EfficientNet with Robust Training: MICCAI Skin Cancer Analysis Challenge

revidee /CoMER

SSL Methods integrated into the official implementation of the ECCV"22 Paper "CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognition"

ngocphucck /Sleeping-posture-classification

This project includes multiple models, loss functions, optimizers and image augmentations for image classification task

A-Telfer /AugKey

RandAugment with Keypoints Annotation Support.

zakaria-aabbou /UDA_mnist

Prediction of MNIST data with only 100 labels

RubenHaisma /rl-augment

Learn an image-augmentation policy with RL (group-relative policy gradient — the GRPO trick) and honestly prove whether it beats RandAugment/TrivialAugment. Agent-drivable --json CLI; verifiable reward = held-out accuracy. RL × computer-vision.

NamanMakkar /UoE-INFR11031-Advanced-Vision-CW-21-22

This repository contains the code and the report for the coursework of INFR11031 Advanced Vision, a postgraduate course offered at The University of Edinburgh. The task was to train on limited and improve the accuracy of the ResNet-50 classifier on a small subset of the ImageNet dataset containing 50K training images and 50K test images. Achieve…