conveying_belt_recognition/deep-hough-transform-master/model/backbone/res2net.py

import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
import torch
import torch.nn.functional as F
__all__ = ['Res2Net', 'res2net50']

class Bottle2neck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None, baseWidth=26, scale = 4, stype='normal'):
        """ Constructor
        Args:
            inplanes: input channel dimensionality
            planes: output channel dimensionality
            stride: conv stride. Replaces pooling layer.
            downsample: None when stride = 1
            baseWidth: basic width of conv3x3
            scale: number of scale.
            type: 'normal': normal set. 'stage': first block of a new stage.
        """
        super(Bottle2neck, self).__init__()

        width = int(math.floor(planes * (baseWidth/64.0)))
        self.conv1 = nn.Conv2d(inplanes, width*scale, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(width*scale)
        
        if scale == 1:
          self.nums = 1
        else:
          self.nums = scale -1
        if stype == 'stage':
            self.pool = nn.AvgPool2d(kernel_size=3, stride = stride, padding=1)
        convs = []
        bns = []
        for i in range(self.nums):
          convs.append(nn.Conv2d(width, width, kernel_size=3, stride = stride, padding=1, bias=False))
          bns.append(nn.BatchNorm2d(width))
        self.convs = nn.ModuleList(convs)
        self.bns = nn.ModuleList(bns)

        self.conv3 = nn.Conv2d(width*scale, planes * self.expansion, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * self.expansion)

        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stype = stype
        self.scale = scale
        self.width  = width

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        spx = torch.split(out, self.width, 1)
        for i in range(self.nums):
          if i==0 or self.stype=='stage':
            sp = spx[i]
          else:
            sp = sp + spx[i]
          sp = self.convs[i](sp)
          sp = self.relu(self.bns[i](sp))
          if i==0:
            out = sp
          else:
            out = torch.cat((out, sp), 1)
        if self.scale != 1 and self.stype=='normal':
          out = torch.cat((out, spx[self.nums]),1)
        elif self.scale != 1 and self.stype=='stage':
          out = torch.cat((out, self.pool(spx[self.nums])),1)

        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 Res2Net(nn.Module):

    def __init__(self, block, layers, baseWidth = 26, scale = 4, num_classes=1000):
        self.inplanes = 64
        super(Res2Net, self).__init__()
        self.baseWidth = baseWidth
        self.scale = scale
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        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)

        self.toplayer = nn.Conv2d(2048, 256, kernel_size=1, stride=1, padding=0)
        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)

        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)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
        
        self._load_pretrained_model()

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample=downsample, 
                        stype='stage', baseWidth = self.baseWidth, scale=self.scale))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes, baseWidth = self.baseWidth, scale=self.scale))

        return nn.Sequential(*layers)

    def forward(self, input):
       # Bottom-up
        x = self.conv1(input)
        x = self.bn1(x)
        x = self.relu(x)
        c1 = self.maxpool(x)
        c2 = self.layer1(c1)  # x4
        c3 = self.layer2(c2) #x8
        c4 = self.layer3(c3) #x16
        c5 = self.layer4(c4) #x32
        # Top-down
        p5 = self.toplayer(c5)
        p4 = nn.functional.upsample(p5, size=c4.size()[2:], mode='bilinear') + self.latlayer1(c4)
        p3 = nn.functional.upsample(p4, size=c3.size()[2:], mode='bilinear') + self.latlayer2(c3)
        p2 = nn.functional.upsample(p3, size=c2.size()[2:], mode='bilinear') + self.latlayer3(c2)
        
        p4 = self.smooth1(p4)
        p3 = self.smooth2(p3)
        p2 = self.smooth3(p2)
        
        return p2, p3, p4, p5

    def _load_pretrained_model(self):
        
        pretrain_dict = model_zoo.load_url('https://shanghuagao.oss-cn-beijing.aliyuncs.com/res2net/res2net50_26w_4s-06e79181.pth')
        model_dict = {}
        state_dict = self.state_dict()
        for k, v in pretrain_dict.items():
            if k in state_dict:
                model_dict[k] = v
        state_dict.update(model_dict)
        self.load_state_dict(state_dict)

def res2net50_FPN(pretrained=True, **kwargs):
    """Constructs a Res2Net-50 model.
    Res2Net-50 refers to the Res2Net-50_26w_4s.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = Res2Net(Bottle2neck, [3, 4, 6, 3], baseWidth = 26, scale = 4, **kwargs)
    
    return model