深度学习-卷积神经网络-深度分离卷积(PyTorch)

深度可分离卷积-图例

计算流程        

        1. 数据特征图 - image图像

        2. 分组卷积 - 对应通道进行卷积操作 -核心

        3. 逐点卷积 - 调整通道 - 核心

        4. 输出数据特征图 - featuremap

代码 - torch

"""
    python - pytorch - 深度分离卷积
"""

import torch
import torch.nn as nn


class Depth_Wise_Conv(nn.Module):
    """
        深度可分离卷积 = 分组卷积 + 逐点卷积调整通道
    """
    def __init__(self, in_channel, out_channel):
        super(Depth_Wise_Conv, self).__init__()
        # 分组
        self.conv_group = nn.Conv2d(in_channel, in_channel, kernel_size=3, stride=1, padding=1, groups=in_channel)
        # 逐点
        self.conv_point = nn.Conv2d(in_channel, out_channel, kernel_size=1, stride=1, padding=1, groups=1)
        # BN
        self.bn = nn.BatchNorm2d(out_channel)
        # activate
        self.act = nn.ReLU()

    def forward(self, inputs):
        """
            前向传播
        """
        x = self.conv_group(inputs)
        x = self.conv_point(x)
        x = self.bn(x)
        x = self.act(x)
        return x


if __name__ == '__main__':
    # 均匀分布产生数据
    test = torch.rand(1, 3, 16, 16)
    model = Depth_Wise_Conv(3, 16)
    model = model(test)
    print(model)