0.基礎知識
0.1. torch.nn.init.kaiming_normal_(m.weight, mode=‘fan_out’, nonlinearity=‘relu’)
- 用正态分布來,填充輸入張量
0.2.torch.nn.init.constant_(m.weight, 1)
用常量1,來填充輸入張量
0.3.nn.BatchNorm2d
-
2維資料歸一化層(把資料按比例縮放,使之落入一個小小的特定區間)
使得資料在進行Relu之前不會因為資料過大而導緻網絡性能的不穩定
0.4.torch.nn.init.normal_(tensor, mean=0, std=1),
- 用服從正态分布N(mean,std)的資料來填充張量tensor
1.VGG16結構圖
1.1.導包
import torch
import torch.nn as nn
from hub import *
__all__=[
'VGG','vgg11','vgg11_bn','vgg13','vgg13_bn','vgg16','vgg16_bn',
'vgg_19','vgg19_bn',
]
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',
}
1.2.定義VGG類方法
class VGG(nn.Module):
def __init__(self, features, num_classes=1000, init_weights=True):
super(VGG, self).__init__()
self.features = features
self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
self.classifier = 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 = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.classifier(x)
return x
def _initialize_weights(self):
for m in self.modules():
#如果m是2維卷積層
if isinstance(m, nn.Conv2d):
#按照《深入整流器:在ImageNet分類上超越人類水準的性能》中描述的方法,用正态分布填充輸入張量
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
#如果m,是2維資料歸一化層(把資料按比例縮放,使之落入一個小小的特定區間)
#使得資料在進行Relu之前不會因為資料過大而導緻網絡性能的不穩定
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
#如果m是線性層
elif isinstance(m, nn.Linear):
#torch.nn.init.normal_(tensor, mean=0, std=1),用服從正态分布N(mean,std)的資料來填充張量tensor
nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)
1.3.神經網絡層合成函數
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)
cfgs = {
'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'],
}
#print(cfgs['A'])
def _vgg(arch, cfg, batch_norm, pretrained, progress, **kwargs):
if pretrained:
kwargs['init_weights'] = False
model = VGG(make_layers(cfgs[cfg],batch_norm=batch_norm), **kwargs)
if pretrained:
state_dict = load_state_dict_from_url(model_urls[arch],
progress=progress)
model.load_state_dict(state_dict)
return model
1.4.調用合成vgg16
def vgg16(pretrained=False,progress=True,**kwargs):
return _vgg('vgg16','D',False,pretrained,progress,**kwargs)
r"""VGG 16-layer model (configuration "D")
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
1.5.輸出vgg16網絡層參數
VGG_16_Net =vgg16()
print(VGG_16_Net)