The current autoencoder and VAE only supports 2-d data, while there is a need to handle 3-d images. PR welcomed!
貢獻者指南
技術棧
python
領域
machine 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。
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。
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
PythonDeep learning basicsConvolutional neural networksFamiliarity with pyod library
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
The issue requests adding a CNN based autoencoder for 3D image outlier detection. Start by examining the existing autoencoder and VAE implementations in pyod (e.g., in pyod/models/autoencoder.py). Study how 2D data is handled and extend to 3D using convolutional layers (e.g., Conv2D to Conv3D). Consider using PyTorch or TensorFlow, depending on the library's current backend. Look at any related discussions in the comments. The implementation should match the library's API and include tests.
