pytorch/vision

Mini imagenet, tiered imagenet

Open

#1,028 opened on Jun 16, 2019

View on GitHub
 (4 comments) (3 reactions) (0 assignees)Python (6,858 forks)batch import
enhancementhelp wantedmodule: datasets

Repository metrics

Stars
 (15,050 stars)
PR merge metrics
 (Avg merge 12d 8h) (14 merged PRs in 30d)

Description

Hello,

Is it possible to add omniglot, mini imagenet and tiered imagenet datasets to torchvision.

And is it possible to upload these datasets to google drive, and share that link, so that people using google colab do not need to download these datasets. they access them directly by adding the dataset to their drives.

This would reduce the time taken to download datasets, as they would be directly available through google drive in untarred manner, making life easy.

Thanks

Contributor guide

Research direction
Study existing dataset implementations in torchvision (e.g., ImageFolder, CIFAR10) to understand the required structure. Then implement a new dataset class for Mini ImageNet and Tiered ImageNet, following the pattern of existing datasets. Consider using torch.utils.data.Dataset and providing download functionalities.
Tech stack
pythonpytorch
Domain
machine learningdata
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65