【pytorch torchvision源码解读系列—2】VGG
最近开始学习一个新的深度学习框架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VGG的源码实现。
好的开始。
import torch.nn as nn
import torch.utils.model_zoo as model_zoo
__all__ = [
'VGG', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn',
'vgg19_bn', 'vgg19',
]
model_urls = {
'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth',
'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth',
'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth',
'vgg11_bn': 'https://download.pytorch.org/models/vgg11_bn-6002323d.pth',
'vgg13_bn': 'https://download.pytorch.org/models/vgg13_bn-abd245e5.pth',
'vgg16_bn': 'https://download.pytorch.org/models/vgg16_bn-6c64b313.pth',
'vgg19_bn': 'https://download.pytorch.org/models/vgg19_bn-c79401a0.pth',
}
首先是关于模型预训练的部分每一个模型都大同小异，因为VGG有多个版本所以不同的版本有不同的预训练模型下载地址。可以看看https://blog.csdn.net/sinat_33487968/article/details/83582299里的解释。
重点关注模型部分。VGG这个类里面的self.features就代表了卷积的部分，而self.classifer就是后面的全连接部分。因为每一个VGG的版本前面的卷积层数不同（其实卷积核的大小论文里面也是有不同，只是这里的torchvision为了简便将所有的卷积核大小都定义为3。）foward函数就是网络前向传播的过程，而_initialize_weights函数是对网络的一些权重进行初始化，初始化的方式有很多种，可以参考pytorch官网上面torch.nn.init部分https://pytorch.org/docs/stable/nn.html#torch-nn-init。
看到有一个方法是kaiming大神在Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification中提出的。有兴趣的可以去看。
class VGG(nn.Module):
def __init__(self, features, num_classes=1000, init_weights=True):
super(VGG, self).__init__()
self.features = features
self.classifer = nn.Sequential(
nn.Linear(512 * 7 * 7, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, num_classes),
)
if init_weights:
self._initialize_weights()
def forward(self, x):
x = self.features(x)
x = x.view(x.size(0), -1)
x = self.classifer(x)
return x
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0.01)
nn.init.constant_(m.bias, 0)
说到卷积部分具体可以参照下图：特别注意到代码实现全部采用了3*3的卷积
这么多重复的卷积不可能一个一个写吧所以使用了一个make layers的函数for循环产生卷积层。
def make_layers(cfg, batch_norm=False):
layers = []
in_channels = 3
for v in cfg:
if v == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
if batch_norm:
layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
else:
layers += [conv2d, nn.ReLU(inplace=True)]
in_channels = v
return nn.Sequential(*layers)这里的cfg就是我们对于每个版本的VGG卷积层的定义，其中'M'代表了maxpooling，数字代表了卷积核的数量。前面的字母可以和上图的论文上面截取的图片相匹配。
cfg = {
'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}下面这个就是vgg11的版本，可以看到我们能通过pretrained参数自己决定是否需要预训练的模型。然后就调用了make layers函数为我们产生根据版本定制的卷积层，他们会在VGG()里与后面的全连接层相连接，最后我们就能完整获得我们的model了。而其他的版本也是通过这么一个类似的函数获得，所以没必要重复展示，大概就是变了cfg[' ']里面的字母，所以卷积层的结构改变了，我们就能到了不同的版本的VGG。
def vgg11(pretrained=False, **kwargs):
"""VGG 11-layer model (configuration "A")
Args:
pretrained (bool): if True,returns a model pre-trained on ImageNet
"""
if pretrained:
kwargs['init_weights'] = False
model = VGG(make_layers(cfg['A']), **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['vgg11']))
return model
下面奉上vgg的所有源码 。
import torch.nn as nn
import torch.utils.model_zoo as model_zoo
__all__ = [
'VGG', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn',
'vgg19_bn', 'vgg19',
]
model_urls = {
'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth',
'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth',
'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth',
'vgg11_bn': 'https://download.pytorch.org/models/vgg11_bn-6002323d.pth',
'vgg13_bn': 'https://download.pytorch.org/models/vgg13_bn-abd245e5.pth',
'vgg16_bn': 'https://download.pytorch.org/models/vgg16_bn-6c64b313.pth',
'vgg19_bn': 'https://download.pytorch.org/models/vgg19_bn-c79401a0.pth',
}
class VGG(nn.Module):
def __init__(self, features, num_classes=1000, init_weights=True):
super(VGG, self).__init__()
self.features = features
self.classifer = nn.Sequential(
nn.Linear(512 * 7 * 7, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, num_classes),
)
if init_weights:
self._initialize_weights()
def forward(self, x):
x = self.features(x)
x = x.view(x.size(0), -1)
x = self.classifer(x)
return x
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0.01)
nn.init.constant_(m.bias, 0)
def make_layers(cfg, batch_norm=False):
layers = []
in_channels = 3
for v in cfg:
if v == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
if batch_norm:
layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
else:
layers += [conv2d, nn.ReLU(inplace=True)]
in_channels = v
return nn.Sequential(*layers)
cfg = {
'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}
def vgg11(pretrained=False, **kwargs):
"""VGG 11-layer model (configuration "A")
Args:
pretrained (bool): if True,returns a model pre-trained on ImageNet
"""
if pretrained:
kwargs['init_weights'] = False
model = VGG(make_layers(cfg['A']), **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['vgg11']))
return model
def vgg11_bn(pretrained=False, **kwargs):
"""VGG 11-layer model (configuration "A") with batch normalization
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
if pretrained:
kwargs['init_weights'] = False
model = VGG(make_layers(cfg['A'], batch_norm=True), **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['vgg11_bn']))
return model
def vgg13(pretrained=False, **kwargs):
"""VGG 13-layer model (configuration "B")
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
if pretrained:
kwargs['init_weights'] = False
model = VGG(make_layers(cfg['B']), **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['vgg13']))
return model
def vgg13_bn(pretrained=False, **kwargs):
"""VGG 13-layer model (configuration "B") with batch normalization
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
if pretrained:
kwargs['init_weights'] = False
model = VGG(make_layers(cfg['B'], batch_norm=True), **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['vgg13_bn']))
return model
def vgg16(pretrained=False, **kwargs):
"""VGG 16-layer model (configuration "D")
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
if pretrained:
kwargs['init_weights'] = False
model = VGG(make_layers(cfg['D']), **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['vgg16']))
return model
def vgg16_bn(pretrained=False, **kwargs):
"""VGG 16-layer model (configuration "D") with batch normalization
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
if pretrained:
kwargs['init_weights'] = False
model = VGG(make_layers(cfg['D'], batch_norm=True), **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['vgg16_bn']))
return model
def vgg19(pretrained=False, **kwargs):
"""VGG 19-layer model (configuration "E")
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
if pretrained:
kwargs['init_weights'] = False
model = VGG(make_layers(cfg['E']), **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['vgg19']))
return model
def vgg19_bn(pretrained=False, **kwargs):
"""VGG 19-layer model (configuration 'E') with batch normalization
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
if pretrained:
kwargs['init_weights'] = False
model = VGG(make_layers(cfg['E'], batch_norm=True), **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['vgg19_bn']))
return model
if __name__ == '__main__':
model = vgg19_bn()
print(model)