pytorch/vision

toy video datasets for generative models

Open

#2,676 opened on Sep 14, 2020

View on GitHub
 (4 comments) (0 reactions) (0 assignees)Python (15,050 stars) (6,858 forks)batch import
help wantedmodule: datasetsnew feature

Description

🚀 Feature

Adding toy video datasets for generative models such as Moving MNIST and Robonet

Motivation

The currently available video datasets are suitable for recognition and not synthesis. It would be nice if you add simple toy video datasets such as Moving MNIST.

cc @pmeier

Contributor guide

Tech stack
python
Domain
datamachine learning
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.
half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
PyTorch Dataset APIVideo data loading
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60
Research direction
Examine existing dataset implementations in torchvision/datasets/, especially the MNIST class. Implement a MovingMNIST class that generates synthetic videos of moving digits with random trajectories. Follow the pattern of other datasets, including proper registration in init .py and adding unit tests. For Robonet, explore the original dataset format and adapt it similarly. Consider reaching out to maintainers (cc @pmeier) for guidance on integration.