apache/mxnet

3D Upsampling

Open

#18,493 建立於 2020年6月5日

在 GitHub 查看
 (15 留言) (3 反應) (0 負責人)C++ (20,808 star) (6,711 fork)batch import
C++Feature requestgood first issue

描述

Description

Currently MXNet does not support upsampling on 5D tensors (3D images). There is more and more work being done in the medical field where 3D images are very common. As MXNet supports 3D transposed convolutions, 3D Upsampling would be very helpful as well, since there are instances where upsampling has been shown to be as effective if not more so than a transposed convolutions.

References

PyTorch, TF both support 3D upsampling.

貢獻者指南

技術棧
cpppython
領域
machine learningai
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。
4
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。
3-5 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。
stale
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
C++Deep learning basicsMXNet internals
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。
20
研究方向
Review existing 2D upsampling operator in MXNet (likely in src/operator/nn/upsampling.cc). Study the 3D transposed convolution implementation for pattern reference. Check PyTorch's interpolate function for 3D tensors to align behavior. The main challenge is supporting 5D tensors and adding backward pass if needed.