Skip to content
/ FSL Public

这个仓库里面包含小样本学习的经典代码,包括网上整理,以及论文复现,是您入门的不二选择

Notifications You must be signed in to change notification settings

AIYAU/FSL

Repository files navigation

File Descriptor

FSL中的数据加载与标准分类略有不同,因为我们以少量分类任务的形式采样批量实例。

  • TaskSampler: 标准PyTorch Sampler对象的扩展,以少量分类任务的形式对批次进行采样
  • FewShotDataset: 一个抽象类,用于标准化您想要使用的任何数据集的接口
  • EasySet: 一个随时可用的FewShotDataset对象,用于处理具有类分类的目录分割的图像数据集
  • WrapFewShotDataset: 将任何数据集转换为一个FewShotDataset对象的包装器
  • FeaturesDataset: 处理预提取特征的数据集
  • SupportSetFolder: 用于处理存储在目录中的支持集的数据集

Datasets to test your model

CU-Birds

from easyfsl.datasets import CUB

train_set = CUB(split="train", training=True)
test_set = CUB(split="test", training=False)

tieredImageNet

from easyfsl.datasets import TieredImageNet

train_set = TieredImageNet(split="train", training=True)
test_set = TieredImageNet(split="test", training=False)

miniImageNet

from easyfsl.datasets import MiniImageNet

train_set = MiniImageNet(root="where/imagenet/is", split="train", training=True)
test_set = MiniImageNet(root="where/imagenet/is", split="test", training=False)

Danish Fungi

from easyfsl.datasets import DanishFungi

dataset = DanishFungi(root="where/fungi/is")

QuickStart

  1. Install the package: pip install easyfsl or simply fork the repository.

  2. Download your data.

  3. Design your training and evaluation scripts. You can use our example notebooks for episodic training or classical training.

学习课程推荐

· 待补充

Acknowledgement

easyfsl FSL-Mate

About

这个仓库里面包含小样本学习的经典代码,包括网上整理,以及论文复现,是您入门的不二选择

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published