每日Attention学习21——Cascade Multi-Receptive Fields

模块出处

[MICCAI 24] [link] TinyU-Net: Lighter Yet Better U-Net with Cascaded Multi-receptive Fields

---

模块名称

Cascade Multi-Receptive Fields (CMRF)

---

模块作用

轻量感受野块

---

模块结构

---

模块特点

• 起点使用PWConv(PointWise Convolution, 1×1卷积)压缩通道，终点使用PWConv恢复通道，构成bottle neck结构
• 中间使用级联的DWConv(Depthwise Convolution, 深度卷积)提取特征

---

模块代码

import torch
import torch.nn as nn
import torch.nn.functional as F
import math


def autopad(k, p=None, d=1):  
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k] # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
    return p


class Conv(nn