FPN+ResNet的Pytorch实现

终于把拖了两周的ResNet和FPN实现了（也不叫实现，照着改的…）。真是应了那句话：纸上得来终觉浅，须知此事要coding。
先贴FPN：

这只是FPN结构，具体的FPN网络就比较复杂了，也贴个，万一哪天也自己实现了呢…
稍微讲一下FPN结构吧，用的原理就是图像处理中很简单但很重要的金字塔结构。以ResNet50为例，四层结构得到的特征图尺寸应为：（ResNet50可看我上一篇博客）
c1:torch.Size([1, 64, 56, 56])
c2:torch.Size([1, 256, 56, 56])
c3:torch.Size([1, 512, 28, 28])
c4:torch.Size([1, 1024, 14, 14])
c5:torch.Size([1, 2048, 7, 7])
之后对c1-c5进行处理。我们的目标是输出四种特征图，其尺寸不同，但深度都为256。
P2:torch.Size([1, 256, 56, 56])
P3:torch.Size([1, 256, 28, 28])
P4:torch.Size([1, 256, 14, 14])
P5:torch.Size([1, 256, 7, 7])
具体做法是：
1.将c5降到256，经过33的卷积处理输出P5.
2.c5上采样后与经过11降维处理过的c4相加，再经3*3卷积处理，得到P4。
以此类推…
FPN结构实现还是比较简单的，主要是把ResNet搞明白…彻底搞明白ResNet花了一个晚上，FPN用了一小时…

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
class Bottleneck(nn.Module):
    expansion = 4
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, stride=stride, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride
    def forward(self, x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)
        out = self.conv3(out)
        out = self.bn3(out)
        if self.downsample is not None:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out
class FPN(nn.Module):
    def __init__(self, block, layers):
        super(FPN, self).__init__()
        self.in_planes = 64
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        # Bottom-up layers
        self.layer1 = self._make_layer(block,  64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        # Top layer
        self.toplayer = nn.Conv2d(2048, 256, kernel_size=1, stride=1, padding=0)  # Reduce channels
        # Smooth layers
        self.smooth1 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1)
        self.smooth2 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1)
        self.smooth3 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1)
        # Lateral layers
        self.latlayer1 = nn.Conv2d(1024, 256, kernel_size=1, stride=1, padding=0)
        self.latlayer2 = nn.Conv2d( 512, 256, kernel_size=1, stride=1, padding=0)
        self.latlayer3 = nn.Conv2d( 256, 256, kernel_size=1, stride=1, padding=0)

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.in_planes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.in_planes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )
        layers = []
        layers.append(block(self.in_planes, planes, stride, downsample))
        self.in_planes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.in_planes, planes))
        return nn.Sequential(*layers)
    def _upsample_add(self, x, y):
        _,_,H,W = y.size()
        return F.interpolate(x, size=(H,W), mode='bilinear',align_corners=True) + y
    def forward(self, x):
        # Bottom-up
        c1 = F.relu(self.bn1(self.conv1(x)))
        c1 = F.max_pool2d(c1, kernel_size=3, stride=2, padding=1)
        #print(f'c1:{c1.shape}')
        c2 = self.layer1(c1)
        #print(f'c2:{c2.shape}')
        c3 = self.layer2(c2)
        #print(f'c3:{c3.shape}')
        c4 = self.layer3(c3)
        #print(f'c4:{c4.shape}')
        c5 = self.layer4(c4)
        #print(f'c5:{c5.shape}')
        # Top-down
        p5 = self.toplayer(c5)
        #print(f'p5:{p5.shape}')
        p4 = self._upsample_add(p5, self.latlayer1(c4))
        #print(f'latlayer1(c4):{self.latlayer1(c4).shape}, p4:{p4.shape}')
        p3 = self._upsample_add(p4, self.latlayer2(c3))
        #print(f'latlayer1(c3):{self.latlayer2(c3).shape}, p3:{p3.shape}')
        p2 = self._upsample_add(p3, self.latlayer3(c2))
        #print(f'latlayer1(c2):{self.latlayer3(c2).shape}, p2:{p2.shape}')
        # Smooth
        p4 = self.smooth1(p4)
        p3 = self.smooth2(p3)
        p2 = self.smooth3(p2)
        return p2, p3, p4, p5
def FPN101():
    # return FPN(Bottleneck, [2,4,23,3])
    return FPN(Bottleneck, [3,4,6,3])
def test():
    net = FPN101()
    fms = net(Variable(torch.randn(1,3,224,224)))
    for fm in fms:
        print(fm.size())