pytorch/vision

toy video datasets for generative models

Open

#2,676 建立於 2020年9月14日

在 GitHub 查看
 (4 留言) (0 反應) (0 負責人)Python (15,050 star) (6,858 fork)batch import
help wantedmodule: datasetsnew feature

描述

🚀 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

貢獻者指南

技術棧
python
領域
datamachine learning
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
3
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
half day
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
clear
前置要求
PyTorch Dataset APIVideo data loading
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
60
研究方向
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.