pytorch----RetinaFace(models)

自己的一些理解，如有错误请各位大老指出。

models文件

文件目录

models为python文件自带__init__.py。
net.py:

import time
import torch
import torch.nn as nn
import torchvision.models._utils as _utils
import torchvision.models as models
import torch.nn.functional as F
from torch.autograd import Variable

def conv_bn(inp, oup, stride = 1, leaky = 0):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
        nn.BatchNorm2d(oup),
        nn.LeakyReLU(negative_slope=leaky, inplace=True)
    )

def conv_bn_no_relu(inp, oup, stride):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
        nn.BatchNorm2d(oup),
    )

def conv_bn1X1(inp, oup, stride, leaky=0):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 1, stride, padding=0, bias=False),
        nn.BatchNorm2d(oup),
        nn.LeakyReLU(negative_slope=leaky, inplace=True)
    )

def conv_dw(inp, oup, stride, leaky=0.1):
    return nn.Sequential(
        nn.Conv2d(inp, inp, 3, stride, 1, groups=inp, bias=False),
        nn.BatchNorm2d(inp),
        nn.LeakyReLU(negative_slope= leaky,inplace=True),

        nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
        nn.BatchNorm2d(oup),
        nn.LeakyReLU(negative_slope= leaky,inplace=True),
    )

class SSH(nn.Module):
    def __init__(self, in_channel, out_channel):
        super(SSH, self).__init__()
        assert out_channel % 4 == 0
        leaky = 0
        if (out_channel <= 64):
            leaky = 0.1
        self.conv3X3 = conv_bn_no_relu(in_channel, out_channel//2, stride=1)

        self.conv5X5_1 = conv_bn(in_channel, out_channel//4, stride=1, leaky = leaky)
        self.conv5X5_2 = conv_bn_no_relu(out_channel//4, out_channel//4, stride=1)

        self.conv7X7_2 = conv_bn(out_channel//4, out_channel//4, stride=1, leaky = leaky)
        self.conv7x7_3 = conv_bn_no_relu(out_channel//4, out_channel//4, stride=1)

    def forward(self, input):
        conv3X3 = self.conv3X3(input)

        conv5X5_1 = self.conv5X5_1(input)
        conv5X5 = self.conv5X5_2(conv5X5_1)

        conv7X7_2 = self.conv7X7_2(conv5X5_1)
        conv7X7 = self.conv7x7_3(conv7X7_2)

        out = torch.cat([conv3X3, conv5X5, conv7X7], dim=1)
        out = F.relu(out)
        return out

class FPN(nn.Module):
    def __init__(self,in_channels_list,out_channels):
        super(FPN,self).__init__()
        leaky = 0
        if (out_channels <= 64):
            leaky = 0.1
        self.output1 = conv_bn1X1(in_channels_list[0], out_channels, stride = 1, leaky = leaky)
        self.output2 = conv_bn1X1(in_channels_list[1], out_channels, stride = 1, leaky = leaky)
        self.output3 = conv_bn1X1(in_channels_list[2], out_channels, stride = 1, leaky = leaky)

        self.merge1 = conv_bn(out_channels, out_channels, leaky = leaky)
        self.merge2 = conv_bn(out_channels, out_channels, leaky = leaky)

    def forward(self, input):
        # names = list(input.keys())
        input = list(input.values())

        output1 = self.output1(input[0])
        output2 = self.output2(input[1])
        output3 = self.output3(input[2])

        up3 = F.interpolate(output3, size=[output2.size(2), output2.size(3)], mode="nearest")
        output2 = output2 + up3
        output2 = self.merge2(output2)

        up2 = F.interpolate(output2, size=[output1.size(2), output1.size(3)], mode="nearest")
        output1 = output1 + up2
        output1 = self.merge1(output1)

        out = [output1, output2, output3]
        return out



class MobileNetV1(nn.Module):
    def __init__(self):
        super(MobileNetV1, self).__init__()
        self.stage1 = nn.Sequential(
            conv_bn(3, 8, 2, leaky = 0.1),    # 3
            conv_dw(8, 16, 1),   # 7
            conv_dw(16, 32, 2),  # 11
            conv_dw(32, 32, 1),  # 19
            conv_dw(32, 64, 2),  # 27
            conv_dw(64, 64, 1),  # 43
        )
        self.stage2 = nn.Sequential(
            conv_dw(64, 128, 2),  # 43 + 16 = 59
            conv_dw(128, 128, 1), # 59 + 32 = 91
            conv_dw(128, 128, 1), # 91 + 32 = 123
            conv_dw(128, 128, 1), # 123 + 32 = 155
            conv_dw(128, 128, 1), # 155 + 32 = 187
            conv_dw(128, 128, 1), # 187 + 32 = 219
        )
        self.stage3 = nn.Sequential(
            conv_dw(128, 256, 2), # 219 +3 2 = 241
            conv_dw(256, 256, 1), # 241 + 64 = 301
        )
        self.avg = nn.AdaptiveAvgPool2d((1,1))
        self.fc = nn.Linear(256, 1000)

    def forward(self, x):
        x = self.stage1(x)
        x = self.stage2(x)
        x = self.stage3(x)
        x = self.avg(x)
        # x = self.model(x)
        x = x.view(-1, 256)
        x = self.fc(x)
        return x

retinaface.py:

import torch
import torch.nn as nn
import torchvision.models.detection.backbone_utils as backbone_utils
import torchvision.models._utils as _utils
import torch.nn.functional as F
from collections import OrderedDict

from models.net import MobileNetV1 as MobileNetV1
from models.net import FPN as FPN
from models.net import SSH as SSH



class ClassHead(nn.Module):
    def __init__(self,inchannels=512,num_anchors=3):
        super(ClassHead,self).__init__()
        self.num_anchors = num_anchors
        self.conv1x1 = nn.Conv2d(inchannels,self.num_anchors*2,kernel_size=(1,1),stride=1,padding=0)

    def forward(self,x):
        out = self.conv1x1(x)
        out = out.permute(0,2,3,1).contiguous()
        
        return out.view(out.shape[0], -1, 2)

class BboxHead(nn.Module):
    def __init__(self,inchannels=512,num_anchors=3):
        super(BboxHead,self).__init__()
        self.conv1x1 = nn.Conv2d(inchannels,num_anchors*4,kernel_size=(1,1),stride=1,padding=0)

    def forward(self,x):
        out = self.conv1x1(x)
        out = out.permute(0,2,3,1).contiguous()

        return out.view(out.shape[0], -1, 4)

class LandmarkHead(nn.Module):
    def __init__(self,inchannels=512,num_anchors=3):
        super(LandmarkHead,self).__init__()
        self.conv1x1 = nn.Conv2d(inchannels,num_anchors*10,kernel_size=(1,1),stride=1,padding=0)

    def forward(self,x):
        out = self.conv1x1(x)
        out = out.permute(0,2,3,1).contiguous()

        return out.view(out.shape[0], -1, 10)

class RetinaFace(nn.Module):
    def __init__(self, cfg = None, phase = 'train'):
        """
        :param cfg:  Network related settings.
        :param phase: train or test.
        """
        super(RetinaFace,self).__init__()
        self.phase = phase
        backbone = None
        if cfg['name'] == 'mobilenet0.25':
            backbone = MobileNetV1()
            if cfg['pretrain']:
                checkpoint = torch.load("./weights/mobilenetV1X0.25_pretrain.tar", map_location=torch.device('cpu'))
                from collections import OrderedDict
                new_state_dict = OrderedDict()
                for k, v in checkpoint['state_dict'].items():
                    name = k[7:]  # remove module.
                    new_state_dict[name] = v
                # load params
                backbone.load_state_dict(new_state_dict)
        elif cfg['name'] == 'Resnet50':
            import torchvision.models as models
            backbone = models.resnet50(pretrained=cfg['pretrain'])

        self.body = _utils.IntermediateLayerGetter(backbone, cfg['return_layers'])
        in_channels_stage2 = cfg['in_channel']
        in_channels_list = [
            in_channels_stage2 * 2,
            in_channels_stage2 * 4,
            in_channels_stage2 * 8,
        ]
        out_channels = cfg['out_channel']
        self.fpn = FPN(in_channels_list,out_channels)
        self.ssh1 = SSH(out_channels, out_channels)
        self.ssh2 = SSH(out_channels, out_channels)
        self.ssh3 = SSH(out_channels, out_channels)

        self.ClassHead = self._make_class_head(fpn_num=3, inchannels=cfg['out_channel'])
        self.BboxHead = self._make_bbox_head(fpn_num=3, inchannels=cfg['out_channel'])
        self.LandmarkHead = self._make_landmark_head(fpn_num=3, inchannels=cfg['out_channel'])

    def _make_class_head(self,fpn_num=3,inchannels=64,anchor_num=2):
        classhead = nn.ModuleList()
        for i in range(fpn_num):
            classhead.append(ClassHead(inchannels,anchor_num))
        return classhead
    
    def _make_bbox_head(self,fpn_num=3,inchannels=64,anchor_num=2):
        bboxhead = nn.ModuleList()
        for i in range(fpn_num):
            bboxhead.append(BboxHead(inchannels,anchor_num))
        return bboxhead

    def _make_landmark_head(self,fpn_num=3,inchannels=64,anchor_num=2):
        landmarkhead = nn.ModuleList()
        for i in range(fpn_num):
            landmarkhead.append(LandmarkHead(inchannels,anchor_num))
        return landmarkhead

    def forward(self,inputs):
        out = self.body(inputs)

        # FPN
        fpn = self.fpn(out)

        # SSH
        feature1 = self.ssh1(fpn[0])
        feature2 = self.ssh2(fpn[1])
        feature3 = self.ssh3(fpn[2])
        features = [feature1, feature2, feature3]

        bbox_regressions = torch.cat([self.BboxHead[i](feature) for i, feature in enumerate(features)], dim=1)
        classifications = torch.cat([self.ClassHead[i](feature) for i, feature in enumerate(features)],dim=1)
        ldm_regressions = torch.cat([self.LandmarkHead[i](feature) for i, feature in enumerate(features)], dim=1)

        if self.phase == 'train':
            output = (bbox_regressions, classifications, ldm_regressions)
        else:
            # print(111111)
            output = (bbox_regressions, F.softmax(classifications, dim=-1), ldm_regressions)
        return output

分析：
这个文件主要是建立retinaface神经网络：
net.py主要使用nn.Sequential（一个有序的容器，神经网络模块将按照在传入构造器的顺序依次被添加到计算图中执行，同时以神经网络模块为元素的有序字典也可以作为传入参数。）主要是构建MobileNetV1骨干网络。
nn.Conv2d(self, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True))
参数：
  in_channel:　输入数据的通道数，例RGB图片通道数为3；
  out_channel: 输出数据的通道数，这个根据模型调整；
  kennel_size: 卷积核大小，可以是int，或tuple；kennel_size=2,意味着卷积大小(2,2)， kennel_size=（2,3），意味着卷积大小（2，3）即非正方形卷积
  stride：步长，默认为1，与kennel_size类似，stride=2,意味着步长上下左右扫描皆为2， stride=（2,3），左右扫描步长为2，上下为3；
  padding：　零填充
  bias被设置False，也就是没有用到偏置
在卷积神经网络的卷积层之后总会添加BatchNorm2d进行数据的归一化处理，这使得数据在进行Relu之前不会因为数据过大而导致网络性能的不稳定，BatchNorm2d()函数数学原理如下：

BatchNorm2d()内部的参数如下：

1.num_features：一般输入参数为batch_sizenum_featuresheight*width，即为其中特征的数量

2.eps：分母中添加的一个值，目的是为了计算的稳定性，默认为：1e-5

3.momentum：一个用于运行过程中均值和方差的一个估计参数（我的理解是一个稳定系数，类似于SGD中的momentum的系数）

4.affine：当设为true时，会给定可以学习的系数矩阵gamma和beta

torch.nn.LeakyReLU(negative_slope=0.01, inplace=False)

对输入的每一个元素运用$f(x)=max(0,x)+negativ{e}_{s}lope\ast min(0,x)$

参数：

negative_slope：控制负斜率的角度，默认等于0.01
inplace-选择是否进行覆盖运算

F.interpolate（）
根据给定 size 或 scale_factor，上采样或下采样输入数据input.

当前支持 temporal, spatial 和 volumetric 输入数据的上采样，其shape 分别为：3-D, 4-D 和 5-D.
输入数据的形式为：mini-batch x channels x [optional depth] x [optional height] x width.

上采样算法有：nearest, linear(3D-only), bilinear(4D-only), trilinear(5D-only).

参数:
- input (Tensor): input tensor
- size (int or Tuple[int] or Tuple[int, int] or Tuple[int, int, int]):输出的 spatial 尺寸.
- scale_factor (float or Tuple[float]): spatial 尺寸的缩放因子.
- mode (string): 上采样算法:nearest, linear, bilinear, trilinear, area. 默认为 nearest.
- align_corners (bool, optional): 如果 align_corners=True，则对齐 input 和 output 的角点像素(corner pixels)，保持在角点像素的值. 只会对 mode=linear, bilinear 和 trilinear 有作用. 默认是 False.

retinaface.py:定义retinaface网络