microsoft/InnerEye-DeepLearning

Patch visualization: Highlight that areas that are never sampled

Open

#301 建立於 2020年10月28日

在 GitHub 查看
 (0 留言) (0 反應) (0 負責人)Python (519 star) (138 fork)batch import
good first issuenot urgentreporting and diagnostics

描述

From the present thumbnails, it is not clear which pixels will never be included in training. Can we highlight those in a different color?

AB#3939

貢獻者指南

技術棧
python
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。
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。
fresh
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
Understanding of patch sampling in medical imagingFamiliarity with visualization code in the repository
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 the existing thumbnail generation code in the repository (likely in the visualization module) to understand how patches are currently displayed. Identify the logic that determines which pixels are sampled for training. Modify the visualization to color unsampled pixels differently, e.g., by adding a semi transparent overlay. Review any related documentation or comments about sampling strategies to ensure accuracy.