【pytorch torchvision源码解读系列—5】DenseNet
pytorch框架中有一个非常重要且好用的包：torchvision，顾名思义这个包主要是关于计算机视觉cv的。这个包主要由3个子包组成，分别是：torchvision.datasets、torchvision.models、torchvision.transforms。
具体介绍可以参考官网：https://pytorch.org/docs/master/torchvision
具体代码可以参考github：https://github.com/pytorch/vision
torchvision.models这个包中包含alexnet、densenet、inception、resnet、squeezenet、vgg等常用经典的网络结构，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。
今天我们来解读一下DenseNet的源码实现。如果对DenseNet不是很了解 可以查看这里的论文笔记
https://blog.csdn.net/sinat_33487968/article/details/83684453
DenseNet由Dense Block组成，而Dense Block石油DenseLayer组成，下面就是DenseLayer类，可以看到每一层卷积之前都是用了batchnorm和relu，然后就是1*1的卷积和3*3的卷积。bn_size参数是bottleneck layer瓶颈层数的乘法因子。bottleneck layer就是指在3*3的卷积之前的那层1*1的卷积，它降低输入的feature map的数量。drop_rate是drop out的概率大小。
注意到最后返回值是torch.cat([x, new_features], 1)，也就是包括自己本身和提取的feature层堆叠在一起。
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)有了DenseLayer，就能用它来构建Dense Block。解释一下一些参数的含义：growth_rate (int) - 代表每一层有多少个新的feature层添加进去 (paper里面是k)，num_input features（int） - 输入的feature层数，num_layers（int）- 代表了Dense Block有多少层DenseLayers。
for循环就是根据num_layers逐层添加Dense Block注意每一层的输入num_input features不一样，是因为每一个DenseLayer之后feature的数目都会增加growth rate。直观一点理解，其实就是每一层的DenseLayer附带了自己学习到的feature还有自己本身一起传入下一个DenseLayer。所以后面的输出的结果会不断的增加，下图不能体现数据流动这一点，因为下图不是数据本身，而是代表卷积层。
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)
DenseBlock的结构可以看下图。
在Dense Block与Dense Block之间，论文添加了Transition层，这个层的作用是为了进一步提高模型的紧凑性，可以减少过渡层的特征图数量。这里直接就把num_input_features压缩成num_output_features，使用一层卷积实现的。
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))
接下来就可以组合成一个DenseNet。DenseNet有不同的版本，不同版本之间可以参考论文给出结构：
每个版本的共同特征就是一开始是7*7的卷积和3*3的maxpooling，中间还加了batchnorm和relu，这部分都被写进了OrderedDict里。接着就要开始遍历构造DenseBlock和Transition Layer，而不同版本的Dense Block每一层具体多少层Dense Layer，是由block_config（一个由4个整数组成的列表）决定。
这里关于Transition的操作，先判断是否是最后一个DenseBlock（最后一个DenseBlock不需要，前面不同的DenseBlock需要Transition Layer），然后就添加一层Transition Layer，输出是输入feature的一半，这样设定应该是根据实验效果确定的。但直观的理解就是这么做之后不管我们多少层DenseBlock，最后输出的数据都是紧凑的，不会无限增大它的厚度。
最后就是常规操作，添加batchnorm和一层线性分类器。后面还未每层的权重参数初始化，如果是卷积核，就使用kaiming_normal，具体可以参考pytorch官网。
class DenseNet(nn.Module):
r"""Densenet-BC model class, based on
`"Densely Connected Convolutional Networks" `_
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)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.constant_(m.bias, 0)
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 那么我们就来看看一个具体的版本是怎么构建的：拿DenseNet121举例，block_config=(6,12,24,16)就是上图论文中的参数。pretrained是定义是否需要预训练模型，这里不必太在意他们是怎么确定的，只要知道如果pretrained是True就返回一个已经训练好的模型。
其他不同版本的DeseNet都大同小异，只是block_config的参数不同。这里就不贴出来了。
def densenet121(pretrained=False, **kwargs):
r"""Densenet-121 model from
`"Densely Connected Convolutional Networks" `_
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))$')
state_dict = model_zoo.load_url(model_urls['densenet121'])
for key in list(state_dict.keys()):
res = pattern.match(key)
if res:
new_key = res.group(1) + res.group(2)
state_dict[new_key] = state_dict[key]
del state_dict[key]
model.load_state_dict(state_dict)
return model 最后贴上源码：
import re
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.model_zoo as model_zoo
from collections import OrderedDict
__all__ = ['DenseNet', 'densenet121', 'densenet169', 'densenet201', 'densenet161']
model_urls = {
'densenet121': 'https://download.pytorch.org/models/densenet121-a639ec97.pth',
'densenet169': 'https://download.pytorch.org/models/densenet169-b2777c0a.pth',
'densenet201': 'https://download.pytorch.org/models/densenet201-c1103571.pth',
'densenet161': 'https://download.pytorch.org/models/densenet161-8d451a50.pth',
}
def densenet121(pretrained=False, **kwargs):
r"""Densenet-121 model from
`"Densely Connected Convolutional Networks" `_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = DenseNet(num_init_features=64, growth_rate=32, block_config=(6, 12, 24, 16),
**kwargs)
if pretrained:
# '.'s are no longer allowed in module names, but pervious _DenseLayer
# has keys 'norm.1', 'relu.1', 'conv.1', 'norm.2', 'relu.2', 'conv.2'.
# They are also in the checkpoints in model_urls. This pattern is used
# to find such keys.
pattern = re.compile(
r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$')
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
def densenet169(pretrained=False, **kwargs):
r"""Densenet-169 model from
`"Densely Connected Convolutional Networks" `_
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, 32, 32),
**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))$')
state_dict = model_zoo.load_url(model_urls['densenet169'])
for key in list(state_dict.keys()):
res = pattern.match(key)
if res:
new_key = res.group(1) + res.group(2)
state_dict[new_key] = state_dict[key]
del state_dict[key]
model.load_state_dict(state_dict)
return model
def densenet201(pretrained=False, **kwargs):
r"""Densenet-201 model from
`"Densely Connected Convolutional Networks" `_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = DenseNet(num_init_features=64, growth_rate=32, block_config=(6, 12, 48, 32),
**kwargs)
if pretrained:
# '.'s are no longer allowed in module names, but pervious _DenseLayer
# has keys 'norm.1', 'relu.1', 'conv.1', 'norm.2', 'relu.2', 'conv.2'.
# They are also in the checkpoints in model_urls. This pattern is used
# to find such keys.
pattern = re.compile(
r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$')
state_dict = model_zoo.load_url(model_urls['densenet201'])
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
def densenet161(pretrained=False, **kwargs):
r"""Densenet-161 model from
`"Densely Connected Convolutional Networks" `_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = DenseNet(num_init_features=96, growth_rate=48, block_config=(6, 12, 36, 24),
**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['densenet161'])
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
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" `_
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)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.constant_(m.bias, 0)
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