|
理论部分见：机器学习笔记：VGG 16_UQI-LIUWJ的博客-CSDN博客
1 直接调用
import torch, torchvision
model = torchvision.models.vgg16()
1.1 torchsummary 查看模型和参数
from torchsummary import summary
summary(model, (3, 224, 224))
'''
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 64, 224, 224] 1,792
ReLU-2 [-1, 64, 224, 224] 0
Conv2d-3 [-1, 64, 224, 224] 36,928
ReLU-4 [-1, 64, 224, 224] 0
MaxPool2d-5 [-1, 64, 112, 112] 0
Conv2d-6 [-1, 128, 112, 112] 73,856
ReLU-7 [-1, 128, 112, 112] 0
Conv2d-8 [-1, 128, 112, 112] 147,584
ReLU-9 [-1, 128, 112, 112] 0
MaxPool2d-10 [-1, 128, 56, 56] 0
Conv2d-11 [-1, 256, 56, 56] 295,168
ReLU-12 [-1, 256, 56, 56] 0
Conv2d-13 [-1, 256, 56, 56] 590,080
ReLU-14 [-1, 256, 56, 56] 0
Conv2d-15 [-1, 256, 56, 56] 590,080
ReLU-16 [-1, 256, 56, 56] 0
MaxPool2d-17 [-1, 256, 28, 28] 0
Conv2d-18 [-1, 512, 28, 28] 1,180,160
ReLU-19 [-1, 512, 28, 28] 0
Conv2d-20 [-1, 512, 28, 28] 2,359,808
ReLU-21 [-1, 512, 28, 28] 0
Conv2d-22 [-1, 512, 28, 28] 2,359,808
ReLU-23 [-1, 512, 28, 28] 0
MaxPool2d-24 [-1, 512, 14, 14] 0
Conv2d-25 [-1, 512, 14, 14] 2,359,808
ReLU-26 [-1, 512, 14, 14] 0
Conv2d-27 [-1, 512, 14, 14] 2,359,808
ReLU-28 [-1, 512, 14, 14] 0
Conv2d-29 [-1, 512, 14, 14] 2,359,808
ReLU-30 [-1, 512, 14, 14] 0
MaxPool2d-31 [-1, 512, 7, 7] 0
AdaptiveAvgPool2d-32 [-1, 512, 7, 7] 0
Linear-33 [-1, 4096] 102,764,544
ReLU-34 [-1, 4096] 0
Dropout-35 [-1, 4096] 0
Linear-36 [-1, 4096] 16,781,312
ReLU-37 [-1, 4096] 0
Dropout-38 [-1, 4096] 0
Linear-39 [-1, 1000] 4,097,000
================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 218.78
Params size (MB): 527.79
Estimated Total Size (MB): 747.15
----------------------------------------------------------------
'''
2 自己动手搭建
除了第32层的AdaptiveAvgPool2d 之外，其他的和直接调用的是一样的
import torch.nn as nn
import torch
class VGG16(nn.Module):
def __init__(self):
super(VGG16,self).__init__()
#输入该模块数据大小 224*224*3
self.block1=nn.Sequential(
nn.Conv2d(
in_channels=3,
out_channels=64,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.Conv2d(
in_channels=64,
out_channels=64,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2)
)
#输入该模块数据大小 112*112*64
self.block2=nn.Sequential(
nn.Conv2d(
in_channels=64,
out_channels=128,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.Conv2d(
in_channels=128,
out_channels=128,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2)
)
#输入该模块数据大小 56*56*128
self.block3=nn.Sequential(
nn.Conv2d(
in_channels=128,
out_channels=256,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.Conv2d(
in_channels=256,
out_channels=256,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.Conv2d(
in_channels=256,
out_channels=256,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2)
)
#输入该模块数据大小 28*28*256
self.block4=nn.Sequential(
nn.Conv2d(
in_channels=256,
out_channels=512,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.Conv2d(
in_channels=512,
out_channels=512,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.Conv2d(
in_channels=512,
out_channels=512,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2)
)
#输入该模块数据大小 14*14*512
self.block5=nn.Sequential(
nn.Conv2d(
in_channels=512,
out_channels=512,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.Conv2d(
in_channels=512,
out_channels=512,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.Conv2d(
in_channels=512,
out_channels=512,
kernel_size=3,
stride=1,
padding=1),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2)
)
#输入该模块数据大小 7*7*512
self.fc_layer=nn.Sequential(
nn.Linear(7*7*512,4096),
nn.ReLU(),
nn.Dropout(p=0.5),
nn.Linear(4096,4096),
nn.ReLU(),
nn.Dropout(p=0.5),
nn.Linear(4096,1000)
)
#输入该模块数据大小 1000
self.Softmax=nn.Softmax(dim=0)
def forward(self,x):
x=self.block1(x)
x=self.block2(x)
x=self.block3(x)
x=self.block4(x)
x=self.block5(x)
x=x.view(x.shape[0],-1)
x=self.fc_layer(x)
x=self.Softmax(x)
return x
vgg = VGG16()
from torchsummary import summary
summary(vgg,(3,244,244))
'''
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 64, 244, 244] 1,792
ReLU-2 [-1, 64, 244, 244] 0
Conv2d-3 [-1, 64, 244, 244] 36,928
ReLU-4 [-1, 64, 244, 244] 0
MaxPool2d-5 [-1, 64, 122, 122] 0
Conv2d-6 [-1, 128, 122, 122] 73,856
ReLU-7 [-1, 128, 122, 122] 0
Conv2d-8 [-1, 128, 122, 122] 147,584
ReLU-9 [-1, 128, 122, 122] 0
MaxPool2d-10 [-1, 128, 61, 61] 0
Conv2d-11 [-1, 256, 61, 61] 295,168
ReLU-12 [-1, 256, 61, 61] 0
Conv2d-13 [-1, 256, 61, 61] 590,080
ReLU-14 [-1, 256, 61, 61] 0
Conv2d-15 [-1, 256, 61, 61] 590,080
ReLU-16 [-1, 256, 61, 61] 0
MaxPool2d-17 [-1, 256, 30, 30] 0
Conv2d-18 [-1, 512, 30, 30] 1,180,160
ReLU-19 [-1, 512, 30, 30] 0
Conv2d-20 [-1, 512, 30, 30] 2,359,808
ReLU-21 [-1, 512, 30, 30] 0
Conv2d-22 [-1, 512, 30, 30] 2,359,808
ReLU-23 [-1, 512, 30, 30] 0
MaxPool2d-24 [-1, 512, 15, 15] 0
Conv2d-25 [-1, 512, 15, 15] 2,359,808
ReLU-26 [-1, 512, 15, 15] 0
Conv2d-27 [-1, 512, 15, 15] 2,359,808
ReLU-28 [-1, 512, 15, 15] 0
Conv2d-29 [-1, 512, 15, 15] 2,359,808
ReLU-30 [-1, 512, 15, 15] 0
MaxPool2d-31 [-1, 512, 7, 7] 0
Linear-32 [-1, 4096] 102,764,544
ReLU-33 [-1, 4096] 0
Dropout-34 [-1, 4096] 0
Linear-35 [-1, 4096] 16,781,312
ReLU-36 [-1, 4096] 0
Dropout-37 [-1, 4096] 0
Linear-38 [-1, 1000] 4,097,000
Softmax-39 [-1, 1000] 0
================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.68
Forward/backward pass size (MB): 258.33
Params size (MB): 527.79
Estimated Total Size (MB): 786.80
----------------------------------------------------------------
'''
|