pyg-team/pytorch_geometric

[Dataset] add MedShapeNet to datasets

Open

#8,719 建立於 2024年1月4日

在 GitHub 查看
 (2 留言) (3 反應) (1 負責人)Python (19,985 star) (3,514 fork)batch import
datasetfeaturegood first issue

描述

🚀 The feature, motivation and pitch

https://medshapenet.ikim.nrw/ Adding this dataset to PyG w/ an example of training a simple GNN that would enable exploration at scale across the community for allowing AI to understand the plethora of complex medical shapes that exist

I will guide @jdhenaos, @loupl, and @ericauld in completing this task (cannot assign them as assignees unfortunately)

Alternatives

No response

Additional context

No response

貢獻者指南

技術棧
pythonpytorch
領域
machine learningdata
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。
1-2 days
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。
active
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
PythonPyTorchPyG dataset APIbasic GNN knowledge
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。
65
研究方向
Study existing dataset implementations in the PyG datasets directory (e.g., 'torch geometric/datasets/'). Create a new dataset class for MedShapeNet that downloads and processes the data. Ensure compatibility with the existing dataset interface. Also, implement a simple GNN training example in an example script. Refer to the PyG documentation for dataset contributions.