resnet 的简单实现

import torch
from torch import nn
from torch.nn import functional as F

class ResBlk(nn.Module):

    """
    resnet block
    """
    def __init__(self, ch_in, ch_out,stride=1):
        """
        :param ch:
        :param ch_out:
        """
        super(ResBlk, self).__init__()

        self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=stride, padding=1)
        self.bn1 = nn.BatchNorm2d(ch_out)
        self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)
        self.bn2 = nn.BatchNorm2d(ch_out)

        self.extra = nn.Sequential()
        # x : [b, ch_in, h, w] => [b, ch_out, h, w]
        if ch_out != ch_in:
            self.extra = nn.Sequential(
                nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=stride),# 因为是作用于x，也就是说要和out相加，而out是[b, 128, 16, 16]
                nn.BatchNorm2d(ch_out)# 所以x本来是[b, 64, 32, 32] => [b, 128, 16, 16]
            )

    def forward(self, x):
        """
        :param x: [b, ch, h, w]
        :return:
        """

        out = F.relu(self.bn1(self.conv1(x)))
        out = F.relu(self.bn2(self.conv2(out)))

        #short cut
        #element-wise add
        # x : [b, ch_in, h, w] with [b, ch_out, h, w]
        # 因为x的通道数和g(x)的不一样，所以要用一个1x1的卷积，在不改变h和w的前提下改变通道数
        out = self.extra(x) + out

        return out

class Resnet18(nn.Module):
    def __init__(self):
        super(Resnet18, self).__init__()

        #预处理层，把3 => 64
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=3, padding=0),
            nn.BatchNorm2d(64)
        )

        #followed 4 blocks
        #[b, 64, h, w] => [b, 128, h, w]

        self.blk1 = ResBlk(64, 128, stride=2)
        self.blk2 = ResBlk(128, 256, stride=2)
        self.blk3 = ResBlk(256, 512, stride=2)
        self.blk4 = ResBlk(512, 512, stride=2)

        self.outlayer = nn.Linear(512, 10) #输入可以一开始瞎几把输， 输出为10类
        #self.outlayer = nn.Linear(102, 10) #输入可以一开始瞎几把输， 输出为10类
        #网络目前的趋势：通道数越来越多， 而图片越变越小（提取特征）

    def forward(self, x):
        """
        :param x:
        :return:
        """
        #[b, 64, h, w] => [b, 64, h, w]
        x = F.relu(self.conv1(x))
        x = self.blk1(x)
        x = self.blk2(x)
        x = self.blk3(x)
        x = self.blk4(x)

        print("after blk x.shape", x.shape)
        #[b, 512, 2, 2]
        x = F.adaptive_max_pool2d(x, [1, 1])
        # [b, 512, h, w] => [b, 512, 1, 1]
        #不管你的输入是多少，最终都会变成hw的均值
        print("after pool x.shape:", x.shape)
        x = x.view(x.size(0), -1)
        print("after view x.shape:", x.shape)
        x = self.outlayer(x)

        return x

def main():
    blk = ResBlk(64, 128)
    tmp = torch.randn(2, 64, 32, 32)
    out = blk(tmp)
    print("block:", out.shape) #[2, 128, 32, 32] 这表明resblk会把长宽保持不变，但是通道数变大，这会使得数据变臃肿

    #----------------接下来实现长宽减半的操作-----------------
    #----------------主要通过stride的操作，2就是1/2，3就是1/3, 4就是1/4---------
    blk2 = ResBlk(64, 128, stride = 2)
    tmp2 = torch.randn(2, 64, 32, 32)
    out2 = blk2(tmp2)
    print("block2:", out2.shape)
    # [2, 128, 16, 16]

    #-----------------测试resnet---------------

    x = torch.randn(2, 3, 32, 32)#网络的输入若是改变了，也就是32*32，那网络内部的这些参数都需要改变哦
    model = Resnet18()
    out = model(x)
    print("resnet:", out.shape)




if __name__ == '__main__':
    main()