davisking/dlib

3D convolution and pooling

Open

#989 创建于 2017年11月30日

在 GitHub 查看
 (7 评论) (1 反应) (0 负责人)C++ (12,570 star) (3,314 fork)batch import
help wanted

描述

I am currently looking for CNN training tools for windows with c++. dlib seems to be a good choice as the example clearly illustrate how ResNet is implemented.

However, I am looking for applications for 3D image segmentation which requires 3D pooling and convolution (somehow it is called 4D convolution in this link

This function is supported in caffe2, tensorflow and pytorch. Any plan to implement for a higher dimension CNN operations?

贡献者指南

技术栈
cpp
领域
machine learning
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
5
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
over 1 week
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
C++dlib CNN API3D convolution concepts
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
15
研究方向
This issue requests adding 3D convolution and pooling operations to dlib's deep learning module. The discussion indicates a need for higher dimensional CNN support for tasks like 3D image segmentation. To implement, study dlib's existing convolution and pooling implementations in files like 'dlib/dnn/core.h' and 'dlib/dnn/layers.h'. Reference how other libraries (PyTorch, TensorFlow) implement 3D convolutions to guide the design. Also review the comments on the issue for further user requirements and potential integration challenges.