【Halcon深度学习 预训练网络模型介绍】

---

一.compact模型

网络的优点是节省内存以及运行效率高，模型支持‘real’图像类型。如果想知道网络模型各参数值，可以使用算子get_dl_classifier_param获取，网络没有全连接层。网络架构支持改变训练图像尺寸，但最小尺寸不能低于15 x 15。

Halcon虽说不开源，但是通过一些方法还是可以获得里面的网络架构，这也为自己搭建网络模型提供了可能。Halcon框架里面定义了卷积，池化，上采样等算子。但说实话，如果要自己搭建网络就我个人经验来说还不如选用Tensorflow和Pytorch开源框架，教程多debug方便。但有时做项目规定了必须用halcon，那也没办法。

pretrained_dl_classifier_compact.hdl模型的原理是SqueezeNet网络，由这位大佬提出，具体原理可以看论文。

SqueezeNet网络介绍：
SqueezeNet在保证精度不损失的同时，将原始AlexNet压缩至原来的510倍。（Squeezenet比AlexNet参数少50倍，再使用了deep compression使得模型压缩至原来的510倍）。SqueezeNet的核心指导思想是——在保证精度的同时使用最少的参数。

SqueezeNet提出了一种多分支结构—fire model。这个结构由squeeze层和expand层构成。squeeze层是由1×1卷积组成，expand层利用1×1和3×3卷积构成多分支结构提取输入特征，以此提高网络的精度。

二.alexnet模型

第一层卷积核比compact更大，更有利于特征提取。

三.enhanced模型

对比compact网络，此网络拥有更多的隐含层，因此可以胜任更复杂的分类任务。但是代价是更大内存以及更长的训练时间，另外由于隐含层的增多，计算相较于上面的网络更复杂，所以batch_size不能设置太大。同样此网络架构也支持改变训练图像尺寸，但是最小尺寸不能低于47 x 47。虽然网络架构没有对图像尺寸设置上限，但是如果图像尺寸越大，那么需要占用的内存资源就越多，对内存的要求就更高，同时耗时更多。更改图像大小将重新初始化全连接层的权重，因此需要重新训练网络。

四.resnet50模型

对比pretrained_dl_classifier_enhanced.hdl网络模型，此模型对更复杂的分类任务表现效果更好。它的网络结构不同于以上两个模型，训练时稳定性以及鲁棒性更好。同样此网络架构也支持改变训练图像尺寸，但是最小尺寸不能低于32 x 32。尽管同样是全连接层，图像大小的改变不会导致权重的重新初始化。

方括号中为残差块

import torch 
import torchvision
from torch import nn
from torch.nn import functional as F
# from torchsummary import summary


class ResidualBlock(nn.Module):
    """
    实现子module: Residual Block
    """

    def __init__(self, inchannel, outchannel, stride=1, shortcut=None):
        super(ResidualBlock, self).__init__()
        self.left = nn.Sequential(
            nn.Conv2d(inchannel, outchannel, 3, stride, 1, bias=False),
            nn.BatchNorm2d(outchannel),
            nn.ReLU(inplace=True),
            nn.Conv2d(outchannel, outchannel, 3, 1, 1, bias=False),
            nn.BatchNorm2d(outchannel)
        )
        self.right = shortcut

    def forward(self, x):
        out = self.left(x)
        residual = x if self.right is None else self.right(x)
        out += residual
        return F.relu(out)


class ResNet(nn.Module):
    """
    实现主module：ResNet34
    ResNet34包含多个layer，每个layer又包含多个Residual block
    用子module来实现Residual block，用_make_layer函数来实现layer
    """

    def __init__(self, blocks, num_classes=1000):
        super(ResNet, self).__init__()
        self.model_name = 'resnet34'

        # 前几层: 图像转换
        self.pre = nn.Sequential(
            nn.Conv2d(3, 64, 7, 2, 3, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(3, 2, 1))

        # 重复的layer，分别有3，4，6，3个residual block
        self.layer1 = self._make_layer(64, 64, blocks[0])
        self.layer2 = self._make_layer(64, 128, blocks[1], stride=2)
        self.layer3 = self._make_layer(128, 256, blocks[2], stride=2)
        self.layer4 = self._make_layer(256, 512, blocks[3], stride=2)

        # 分类用的全连接
        self.fc = nn.Linear(512, num_classes)

    def _make_layer(self, inchannel, outchannel, block_num, stride=1):
        """
        构建layer,包含多个residual block
        """
        shortcut = nn.Sequential(
            nn.Conv2d(inchannel, outchannel, 1, stride, bias=False),
            nn.BatchNorm2d(outchannel),
            nn.ReLU()
        )

        layers = []
        layers.append(ResidualBlock(inchannel, outchannel, stride, shortcut))

        for i in range(1, block_num):
            layers.append(ResidualBlock(outchannel, outchannel))
        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.pre(x)
        l1_out = self.layer1(x)
        l2_out = self.layer2(l1_out)
        l3_out = self.layer3(l2_out)
        l4_out = self.layer4(l3_out)
        p_out = F.avg_pool2d(l4_out, 7)
        fea = p_out.view(p_out.size(0), -1)
        out=self.fc(fea)
        return l1_out,l2_out,l3_out,l4_out,fea,out

def ResNet18():
    return ResNet([2, 2, 2, 2])


def ResNet34():
    return ResNet([3, 4, 6, 3])


if __name__ == '__main__':
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    model = ResNet34()
    model.to(device)
    # summary(model, (3, 224, 224))

import torch 
import torch.nn as nn
import torchvision
import numpy as np

print("PyTorch Version: ", torch.__version__)
print("Torchvision Version: ", torchvision.__version__)

__all__ = ['ResNet50', 'ResNet101', 'ResNet152']


def Conv1(in_planes, places, stride=2):
    return nn.Sequential(
        nn.Conv2d(in_channels=in_planes, out_channels=places, kernel_size=7, stride=stride, padding=3, bias=False),
        nn.BatchNorm2d(places),
        nn.ReLU(inplace=True),
        nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
    )


class Bottleneck(nn.Module):
    def __init__(self, in_places, places, stride=1, downsampling=False, expansion=4):
        super(Bottleneck, self).__init__()
        self.expansion = expansion
        self.downsampling = downsampling

        self.bottleneck = nn.Sequential(
            nn.Conv2d(in_channels=in_places, out_channels=places, kernel_size=1, stride=1, bias=False),
            nn.BatchNorm2d(places),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False),
            nn.BatchNorm2d(places),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_channels=places, out_channels=places * self.expansion, kernel_size=1, stride=1, bias=False),
            nn.BatchNorm2d(places * self.expansion),
        )

        if self.downsampling:
            self.downsample = nn.Sequential(
                nn.Conv2d(in_channels=in_places, out_channels=places * self.expansion, kernel_size=1, stride=stride,
                          bias=False),
                nn.BatchNorm2d(places * self.expansion)
            )
        self.relu = nn.ReLU(inplace=True)

    def forward(self, x):
        residual = x
        out = self.bottleneck(x)

        if self.downsampling:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)
        return out


class ResNet(nn.Module):
    def __init__(self, blocks, num_classes=1000, expansion=4):
        super(ResNet, self).__init__()
        self.expansion = expansion

        self.conv1 = Conv1(in_planes=3, places=64)

        self.layer1 = self.make_layer(in_places=64, places=64, block=blocks[0], stride=1)
        self.layer2 = self.make_layer(in_places=256, places=128, block=blocks[1], stride=2)
        self.layer3 = self.make_layer(in_places=512, places=256, block=blocks[2], stride=2)
        self.layer4 = self.make_layer(in_places=1024, places=512, block=blocks[3], stride=2)

        self.avgpool = nn.AvgPool2d(7, stride=1)
        self.fc = nn.Linear(2048, num_classes)

        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)

    def make_layer(self, in_places, places, block, stride):
        layers = []
        layers.append(Bottleneck(in_places, places, stride, downsampling=True))
        for i in range(1, block):
            layers.append(Bottleneck(places * self.expansion, places))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        l1_out = self.layer1(x)
        l2_out = self.layer2(l1_out)
        l3_out = self.layer3(l2_out)
        l4_out = self.layer4(l3_out)
        p_out = self.avgpool(l4_out)
        fea = p_out.view(p_out.size(0), -1)
        out = self.fc(fea)
        return l1_out, l2_out, l3_out, l4_out, fea, out


def ResNet50():
    return ResNet([3, 4, 6, 3])


def ResNet101():
    return ResNet([3, 4, 23, 3])


def ResNet152():
    return ResNet([3, 8, 36, 3])


if __name__ == '__main__':
    # model = torchvision.models.resnet50()
    model = ResNet50()
    print(model)

    input = torch.randn(1, 3, 224, 224)
    out = model(input)
    print(out.shape)

五.mobilenet_v2模型

体积小，功耗低，适合移动和嵌入式视觉应用。