Pytorch Meta

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
Alternatives To Pytorch Meta
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
Text3,245341102a day ago22June 28, 2022294bsd-3-clausePython
Models, data loaders and abstractions for language processing, powered by PyTorch
Pytorch Nlp1,929982 years ago19November 04, 201916bsd-3-clausePython
Basic Utilities for PyTorch Natural Language Processing (NLP)
Pytorch Meta1,724
4 months ago28September 20, 202153mitPython
A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
9 months ago
Some tricks of pytorch... :star:
2 years ago2November 24, 201814apache-2.0Python
A medical imaging framework for Pytorch
4 months ago12Jupyter Notebook
Light-weight Single Person Pose Estimator
a year ago17mitJupyter Notebook
[NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data.
Monodepth Pytorch411
4 years ago11Python
Unofficial implementation of Unsupervised Monocular Depth Estimation neural network MonoDepth in PyTorch
Pytorch Unet357
3 years ago6mitJupyter Notebook
Simple PyTorch implementations of U-Net/FullyConvNet (FCN) for image segmentation
Ssd Pytorch335
a year ago2apache-2.0Python
SSD目标检测算法(Single Shot MultiBox Detector)(简单,明了,易用,全中文注释,单机多卡训练,视频检测)( If you train the model on a single computer and mutil GPU, this program will be your best choice , easier to use and easier to understand )
Alternatives To Pytorch Meta
Select To Compare

Alternative Project Comparisons


PyPI Build Status Documentation

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch. Torchmeta contains popular meta-learning benchmarks, fully compatible with both torchvision and PyTorch's DataLoader.


  • A unified interface for both few-shot classification and regression problems, to allow easy benchmarking on multiple problems and reproducibility.
  • Helper functions for some popular problems, with default arguments from the literature.
  • An thin extension of PyTorch's Module, called MetaModule, that simplifies the creation of certain meta-learning models (e.g. gradient based meta-learning methods). See the MAML example for an example using MetaModule.

Datasets available


You can install Torchmeta either using Python's package manager pip, or from source. To avoid any conflict with your existing Python setup, it is suggested to work in a virtual environment with virtualenv. To install virtualenv:

pip install --upgrade virtualenv
virtualenv venv
source venv/bin/activate


  • Python 3.6 or above
  • PyTorch 1.4 or above
  • Torchvision 0.5 or above

Using pip

This is the recommended way to install Torchmeta:

pip install torchmeta

From source

You can also install Torchmeta from source. This is recommended if you want to contribute to Torchmeta.

git clone
cd pytorch-meta
python install


Minimal example

This minimal example below shows how to create a dataloader for the 5-shot 5-way Omniglot dataset with Torchmeta. The dataloader loads a batch of randomly generated tasks, and all the samples are concatenated into a single tensor. For more examples, check the examples folder.

from torchmeta.datasets.helpers import omniglot
from import BatchMetaDataLoader

dataset = omniglot("data", ways=5, shots=5, test_shots=15, meta_train=True, download=True)
dataloader = BatchMetaDataLoader(dataset, batch_size=16, num_workers=4)

for batch in dataloader:
    train_inputs, train_targets = batch["train"]
    print('Train inputs shape: {0}'.format(train_inputs.shape))    # (16, 25, 1, 28, 28)
    print('Train targets shape: {0}'.format(train_targets.shape))  # (16, 25)

    test_inputs, test_targets = batch["test"]
    print('Test inputs shape: {0}'.format(test_inputs.shape))      # (16, 75, 1, 28, 28)
    print('Test targets shape: {0}'.format(test_targets.shape))    # (16, 75)

Advanced example

Helper functions are only available for some of the datasets available. However, all of them are available through the unified interface provided by Torchmeta. The variable dataset defined above is equivalent to the following

from torchmeta.datasets import Omniglot
from torchmeta.transforms import Categorical, ClassSplitter, Rotation
from torchvision.transforms import Compose, Resize, ToTensor
from import BatchMetaDataLoader

dataset = Omniglot("data",
                   # Number of ways
                   # Resize the images to 28x28 and converts them to PyTorch tensors (from Torchvision)
                   transform=Compose([Resize(28), ToTensor()]),
                   # Transform the labels to integers (e.g. ("Glagolitic/character01", "Sanskrit/character14", ...) to (0, 1, ...))
                   # Creates new virtual classes with rotated versions of the images (from Santoro et al., 2016)
                   class_augmentations=[Rotation([90, 180, 270])],
dataset = ClassSplitter(dataset, shuffle=True, num_train_per_class=5, num_test_per_class=15)
dataloader = BatchMetaDataLoader(dataset, batch_size=16, num_workers=4)

Note that the dataloader, receiving the dataset, remains the same.


Tristan Deleu, Tobias Würfl, Mandana Samiei, Joseph Paul Cohen, and Yoshua Bengio. Torchmeta: A Meta-Learning library for PyTorch, 2019 [ArXiv]

If you want to cite Torchmeta, use the following Bibtex entry:

  title={{Torchmeta: A Meta-Learning library for PyTorch}},
  author={Deleu, Tristan and W\"urfl, Tobias and Samiei, Mandana and Cohen, Joseph Paul and Bengio, Yoshua},
  note={Available at:}
Popular Pytorch Projects
Popular Dataloader Projects
Popular Machine Learning Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Meta Learning