PyTorch源码解读（四）torchvision.models

PyTorch框架中有一个非常重要且好用的包：torchvision，该包主要由3个子包组成，分别是：torchvision.datasets torchvision.models、torchvision.transforms。这3个子包的具体介绍可以参考官网https://pytorch.org/docs/master/torchvision/datasets.html。

我的另外两篇博客对其他两个部分做了介绍分别为：

torchvision.transformshttps://blog.csdn.net/sinat_42239797/article/details/93857364
torchvision.datasetshttps://blog.csdn.net/sinat_42239797/article/details/93916790

 

这篇博客介绍torchvision.models。torchvision.models这个包中alexnet、densenet、inception、resnet、squeezenet、vgg等常用的网络结构，并且提供了预训练模型，可以通过简单调用来读取网络结构和预训练模型。

如何调用上述模型？

	import torchvision 
	model = torchvision.models.densenet(pretrained=True)

这样就导入了densenet的预训练模型了。如果只需要网络结构，不需要用预训练模型的参数来初始化，那么就是:

	model = torchvision.models.densenet(pretrained=False)

由于pretrained参数默认是False，所以等价于：

​
	model = torchvision.models.densenet(pretrained=False)

接下来以导入densenet为例介绍具体导入模型时候的源码。运行model = torchvision.models.densenet(pretrained=True)的时候，是通过models包下的densenet.py脚本进行的，源码如下：

import re
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.model_zoo as model_zoo
from collections import OrderedDict

__all__ = ['DenseNet', 'densenet121', 'densenet169', 'densenet201', 'densenet161']


model_urls = {
    'densenet121': 'https://download.pytorch.org/models/densenet121-a639ec97.pth',
    'densenet169': 'https://download.pytorch.org/models/densenet169-b2777c0a.pth',
    'densenet201': 'https://download.pytorch.org/models/densenet201-c1103571.pth',
    'densenet161': 'https://download.pytorch.org/models/densenet161-8d451a50.pth',
}

首先是导入必要的库，其中model_zoo是和导入预训练模型相关的包，另外all变量定义了可以从外部import的函数名或类名。这也是前面为什么可以用torchvision.models.densenet()来调用的原因。
model_urls这个字典是用来引入预训练模型的下载地址。

def densenet121(pretrained=False, **kwargs):
    r"""Densenet-121 model from
    `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = DenseNet(num_init_features=64, growth_rate=32, block_config=(6, 12, 24, 16),
                     **kwargs)
    if pretrained:
        # '.'s are no longer allowed in module names, but pervious _DenseLayer
        # has keys 'norm.1', 'relu.1', 'conv.1', 'norm.2', 'relu.2', 'conv.2'.
        # They are also in the checkpoints in model_urls. This pattern is used
        # to find such keys.
        pattern = re.compile(
            r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$')
        state_dict = model_zoo.load_url(model_urls['densenet121'])
        for key in list(state_dict.keys()):
            res = pattern.match(key)
            if res:
                new_key = res.group(1) + res.group(2)
                state_dict[new_key] = state_dict[key]
                del state_dict[key]
        model.load_state_dict(state_dict)
    return model

DenseNet的网络结构和ResNet差不多，我们知道ResNet的核心是通过建立前面层与后面层之间的“短路连接”（shortcuts，skip connection），这有助于训练过程中梯度的反向传播，从而能训练出更深的CNN网络。DenseNet模型，它的基本思路与ResNet一致，但是它建立的是前面所有层与后面层的密集连接（dense connection），它的名称也是由此而来。DenseNet的另一大特色是通过特征在channel上的连接来实现特征重用（feature reuse）。

DenseNet模型主要由DenseBlock和Transition组成，其中：

DenseBlock是由多层模块组成，每层的特征图大小相同，层与层之间采用密集相连的。

Transition是连接两个相邻的DenseBlock，并通过pooling使得特征图大小降低，还能起到压缩模块的作用。

DenseBlock中的非线性组合函数H(.)采用的是：BN+Relu+3x3Conv结构

DenseBlock-B:采用瓶颈层来减少计算量，其结构为：BN+Relu+1x1Conv+BN+Relu+3x3Conv，主要是增加了1x1Conv，由1x1Conv得到4K（k为卷积核的个数，在本文中代表增长率）个特征图，起到的作用是降低特征数量，提升计算效率。

Transition层包括一个1x1Conv和2x2AvgPooling,结构为：BN+Relu+1x1Conv+2x2AvgPooling。

DenseBlock-BC：使用DenseBlock结构和压缩系数小于1的Transition组合结构

其源代码如下：

class _DenseLayer(nn.Sequential):
    def __init__(self, num_input_features, growth_rate, bn_size, drop_rate):
        super(_DenseLayer, self).__init__()
        self.add_module('norm1', nn.BatchNorm2d(num_input_features)),
        self.add_module('relu1', nn.ReLU(inplace=True)),
        self.add_module('conv1', nn.Conv2d(num_input_features, bn_size *
                        growth_rate, kernel_size=1, stride=1, bias=False)),
        self.add_module('norm2', nn.BatchNorm2d(bn_size * growth_rate)),
        self.add_module('relu2', nn.ReLU(inplace=True)),
        self.add_module('conv2', nn.Conv2d(bn_size * growth_rate, growth_rate,
                        kernel_size=3, stride=1, padding=1, bias=False)),
        self.drop_rate = drop_rate

    def forward(self, x):
        new_features = super(_DenseLayer, self).forward(x)
        if self.drop_rate > 0:
            new_features = F.dropout(new_features, p=self.drop_rate, training=self.training)
        return torch.cat([x, new_features], 1)


class _DenseBlock(nn.Sequential):
    def __init__(self, num_layers, num_input_features, bn_size, growth_rate, drop_rate):
        super(_DenseBlock, self).__init__()
        for i in range(num_layers):
            layer = _DenseLayer(num_input_features + i * growth_rate, growth_rate, bn_size, drop_rate)
            self.add_module('denselayer%d' % (i + 1), layer)


class _Transition(nn.Sequential):
    def __init__(self, num_input_features, num_output_features):
        super(_Transition, self).__init__()
        self.add_module('norm', nn.BatchNorm2d(num_input_features))
        self.add_module('relu', nn.ReLU(inplace=True))
        self.add_module('conv', nn.Conv2d(num_input_features, num_output_features,
                                          kernel_size=1, stride=1, bias=False))
        self.add_module('pool', nn.AvgPool2d(kernel_size=2, stride=2))


class DenseNet(nn.Module):
    r"""Densenet-BC model class, based on
    `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_

    Args:
        growth_rate (int) - how many filters to add each layer (`k` in paper)
        block_config (list of 4 ints) - how many layers in each pooling block
        num_init_features (int) - the number of filters to learn in the first convolution layer
        bn_size (int) - multiplicative factor for number of bottle neck layers
          (i.e. bn_size * k features in the bottleneck layer)
        drop_rate (float) - dropout rate after each dense layer
        num_classes (int) - number of classification classes
    """
    def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16),
                 num_init_features=64, bn_size=4, drop_rate=0, num_classes=1000):

        super(DenseNet, self).__init__()

        # First convolution
        self.features = nn.Sequential(OrderedDict([
            ('conv0', nn.Conv2d(3, num_init_features, kernel_size=7, stride=2, padding=3, bias=False)),
            ('norm0', nn.BatchNorm2d(num_init_features)),
            ('relu0', nn.ReLU(inplace=True)),
            ('pool0', nn.MaxPool2d(kernel_size=3, stride=2, padding=1)),
        ]))

        # Each denseblock
        num_features = num_init_features
        for i, num_layers in enumerate(block_config):
            block = _DenseBlock(num_layers=num_layers, num_input_features=num_features,
                                bn_size=bn_size, growth_rate=growth_rate, drop_rate=drop_rate)
            self.features.add_module('denseblock%d' % (i + 1), block)
            num_features = num_features + num_layers * growth_rate
            if i != len(block_config) - 1:
                trans = _Transition(num_input_features=num_features, num_output_features=num_features // 2)
                self.features.add_module('transition%d' % (i + 1), trans)
                num_features = num_features // 2

        # Final batch norm
        self.features.add_module('norm5', nn.BatchNorm2d(num_features))

        # Linear layer
        self.classifier = nn.Linear(num_features, num_classes)

        # Official init from torch repo.
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal(m.weight.data)
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                m.bias.data.zero_()

    def forward(self, x):
        features = self.features(x)
        out = F.relu(features, inplace=True)
        out = F.avg_pool2d(out, kernel_size=7, stride=1).view(features.size(0), -1)
        out = self.classifier(out)
        return out
def densenet121(pretrained=False, **kwargs):
    r"""Densenet-121 model from
    `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = DenseNet(num_init_features=64, growth_rate=32, block_config=(6, 12, 24, 16),
                     **kwargs)
    if pretrained:
        # '.'s are no longer allowed in module names, but pervious _DenseLayer
        # has keys 'norm.1', 'relu.1', 'conv.1', 'norm.2', 'relu.2', 'conv.2'.
        # They are also in the checkpoints in model_urls. This pattern is used
        # to find such keys.
        pattern = re.compile(
            r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$')
        state_dict = model_zoo.load_url(model_urls['densenet121'])
        for key in list(state_dict.keys()):
            res = pattern.match(key)
            if res:
                new_key = res.group(1) + res.group(2)
                state_dict[new_key] = state_dict[key]
                del state_dict[key]
        model.load_state_dict(state_dict)
    return model

densenet原文链接为https://arxiv.org/abs/1608.06993