import torch
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l
AlexNet
net = nn.Sequential(
nn.Conv2d(1, 96, kernel_size=11, stride=4, padding=0),nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(96, 256, kernel_size=5, padding=2), nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(256, 384, kernel_size=3, padding=1), nn.ReLU(),
nn.Conv2d(384, 384, kernel_size=3, padding=1), nn.ReLU(),
nn.Conv2d(384, 256, kernel_size=3, padding=1), nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Flatten(),
nn.Linear(6400, 4096), nn.ReLU(),nn.Dropout(0.5),
nn.Linear(4096, 4096), nn.ReLU(),nn.Dropout(0.5),
nn.Linear(4096, 10))
X = torch.randn(1,1,224,224)
for layer in net:
X = layer(X)
print(layer.__class__.__name__,'output shape:\t', X.shape)
Conv2d output shape: torch.Size([1, 96, 54, 54])
ReLU output shape: torch.Size([1, 96, 54, 54])
MaxPool2d output shape: torch.Size([1, 96, 26, 26])
Conv2d output shape: torch.Size([1, 256, 26, 26])
ReLU output shape: torch.Size([1, 256, 26, 26])
MaxPool2d output shape: torch.Size([1, 256, 12, 12])
Conv2d output shape: torch.Size([1, 384, 12, 12])
ReLU output shape: torch.Size([1, 384, 12, 12])
Conv2d output shape: torch.Size([1, 384, 12, 12])
ReLU output shape: torch.Size([1, 384, 12, 12])
Conv2d output shape: torch.Size([1, 256, 12, 12])
ReLU output shape: torch.Size([1, 256, 12, 12])
MaxPool2d output shape: torch.Size([1, 256, 5, 5])
Flatten output shape: torch.Size([1, 6400])
Linear output shape: torch.Size([1, 4096])
ReLU output shape: torch.Size([1, 4096])
Dropout output shape: torch.Size([1, 4096])
Linear output shape: torch.Size([1, 4096])
ReLU output shape: torch.Size([1, 4096])
Dropout output shape: torch.Size([1, 4096])
Linear output shape: torch.Size([1, 10])
VGG
def vgg_block(num_convs, in_channels, out_channels):
layers = []
for _ in range(num_convs):
layers.append(nn.Conv2d(in_channels, out_channels,
kernel_size=3, padding=1))
layers.append(nn.ReLU())
in_channels = out_channels
layers.append(nn.MaxPool2d(kernel_size=2,stride=2))
return nn.Sequential(*layers)
conv_arch = ((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))
def vgg(conv_arch):
conv_blks = []
in_channels = 1
# 卷积层部分
for (num_convs, out_channels) in conv_arch:
conv_blks.append(vgg_block(num_convs, in_channels, out_channels))
in_channels = out_channels
return nn.Sequential(
*conv_blks, nn.Flatten(),
# 全连接层部分
nn.Linear(out_channels * 7 * 7, 4096), nn.ReLU(), nn.Dropout(0.5),
nn.Linear(4096, 4096), nn.ReLU(), nn.Dropout(0.5),
nn.Linear(4096, 10))
vgg_net = vgg(conv_arch)
X = torch.randn(1,1,224,224)
for blk in vgg_net:
X = blk(X)
print(blk.__class__.__name__,'output shape:\t', X.shape)
Sequential output shape: torch.Size([1, 64, 112, 112])
Sequential output shape: torch.Size([1, 128, 56, 56])
Sequential output shape: torch.Size([1, 256, 28, 28])
Sequential output shape: torch.Size([1, 512, 14, 14])
Sequential output shape: torch.Size([1, 512, 7, 7])
Flatten output shape: torch.Size([1, 25088])
Linear output shape: torch.Size([1, 4096])
ReLU output shape: torch.Size([1, 4096])
Dropout output shape: torch.Size([1, 4096])
Linear output shape: torch.Size([1, 4096])
ReLU output shape: torch.Size([1, 4096])
Dropout output shape: torch.Size([1, 4096])
Linear output shape: torch.Size([1, 10])
NiN
def nin_block(in_channels, out_channels, kernel_size, strides, padding):
return nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size, strides, padding),
nn.ReLU(),
nn.Conv2d(out_channels, out_channels, kernel_size=1), nn.ReLU(),
nn.Conv2d(out_channels, out_channels, kernel_size=1), nn.ReLU())
nin_net = nn.Sequential(
nin_block(1, 96, kernel_size=11, strides=4, padding=0),
nn.MaxPool2d(3, stride=2),
nin_block(96, 256, kernel_size=5, strides=1, padding=2),
nn.MaxPool2d(3, stride=2),
nin_block(256, 384, kernel_size=3, strides=1, padding=1),
nn.MaxPool2d(3, stride=2),
nn.Dropout(0.5),
# 标签类别数是10
nin_block(384, 10, kernel_size=3, strides=1, padding=1),
nn.AdaptiveAvgPool2d((1, 1)),
# 将四维的输出转成二维的输出，其形状为(批量大小,10)
nn.Flatten())
X = torch.randn(1,1,224,224)
for layer in nin_net:
X = layer(X)
print(layer.__class__.__name__,'output shape:\t', X.shape)
Sequential output shape: torch.Size([1, 96, 54, 54])
MaxPool2d output shape: torch.Size([1, 96, 26, 26])
Sequential output shape: torch.Size([1, 256, 26, 26])
MaxPool2d output shape: torch.Size([1, 256, 12, 12])
Sequential output shape: torch.Size([1, 384, 12, 12])
MaxPool2d output shape: torch.Size([1, 384, 5, 5])
Dropout output shape: torch.Size([1, 384, 5, 5])
Sequential output shape: torch.Size([1, 10, 5, 5])
AdaptiveAvgPool2d output shape: torch.Size([1, 10, 1, 1])
Flatten output shape: torch.Size([1, 10])
GoogLeNet
class Inception(nn.Module):
# c1--c4 是每条路径的通道数
def __init__(self, in_channels, c1, c2, c3 ,c4, **kwargs):
super(Inception, self).__init__(**kwargs)
# 线路1 ，1*1 卷积层
self.p1_1 = nn.Conv2d(in_channels, c1, kernel_size=1)
# 线路2， 1*1 卷积层 + 3*3 卷积层
self.p2_1 = nn.Conv2d(in_channels, c2[0], kernel_size=1)
self.p2_2 = nn.Conv2d(c2[0], c2[1], kernel_size=3, padding=1)
# 线路3， 1*1 卷积层 + 5*5 卷积层
self.p3_1 = nn.Conv2d(in_channels, c3[0], kernel_size=1)
self.p3_2 = nn.Conv2d(c3[0], c3[1], kernel_size=5, padding=2)
# 线路4， 3*3 最大汇聚 + 1*1 卷积层
self.p4_1 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
self.p4_2 = nn.Conv2d(in_channels, c4, kernel_size=1)
def forward(self, x):
p1 = F.relu(self.p1_1(x))
p2 = F.relu(self.p2_2(F.relu(self.p2_1(x))))
p3 = F.relu(self.p3_2(F.relu(self.p3_1(x))))
p4 = F.relu(self.p4_2(self.p4_1(x)))
# 在通道维度上连结输出
return torch.cat((p1, p2, p3, p4), dim=1)
b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b2 = nn.Sequential(nn.Conv2d(64, 64, kernel_size=1),
nn.ReLU(),
nn.Conv2d(64, 192, kernel_size=3, padding=1),
nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b3 = nn.Sequential(Inception(192, 64, (96, 128), (16, 32), 32),
Inception(256, 128, (128, 192), (32, 96), 64),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b4 = nn.Sequential(Inception(480, 192, (96, 208), (16, 48), 64),
Inception(512, 160, (112, 224), (24, 64), 64),
Inception(512, 128, (128, 256), (24, 64), 64),
Inception(512, 112, (144, 288), (32, 64), 64),
Inception(528, 256, (160, 320), (32, 128), 128),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b5 = nn.Sequential(Inception(832, 256, (160, 320), (32, 128), 128),
Inception(832, 384, (192, 384), (48, 128), 128),
nn.AdaptiveAvgPool2d((1,1)),
nn.Flatten())
google_net = nn.Sequential(b1, b2, b3, b4, b5, nn.Linear(1024, 10))
X = torch.rand(size=(1, 1, 96, 96))
for layer in google_net:
X = layer(X)
print(layer.__class__.__name__,'output shape:\t', X.shape)
Sequential output shape: torch.Size([1, 64, 24, 24])
Sequential output shape: torch.Size([1, 192, 12, 12])
Sequential output shape: torch.Size([1, 480, 6, 6])
Sequential output shape: torch.Size([1, 832, 3, 3])
Sequential output shape: torch.Size([1, 1024])
Linear output shape: torch.Size([1, 10])
ResNet
class Residual(nn.Module):
def __init__(self, input_channels, num_channels, use_1x1conv = False, strides =1):
super().__init__()
self.conv1 = nn.Conv2d(input_channels, num_channels, kernel_size = 3, padding =1, stride = strides)
self.conv2 = nn.Conv2d(num_channels, num_channels, kernel_size = 3, padding =1)
if use_1x1conv:
self.conv3 = nn.Conv2d(input_channels, num_channels, kernel_size=1, stride= strides)
else:
self.conv3 = None
self.bn1 = nn.BatchNorm2d(num_channels)
self.bn2 = nn.BatchNorm2d(num_channels)
def forward(self, X):
Y = F.relu(self.bn1(self.conv1(X)))
Y = self.bn2(self.conv2(Y))
if self.conv3:
X = self.conv3(X)
Y += X
return F.relu(Y)
b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
nn.BatchNorm2d(64), nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
def resnet_block(input_channels, num_channels, num_residuals,
first_block=False):
blk = []
for i in range(num_residuals):
if i == 0 and not first_block:
blk.append(Residual(input_channels, num_channels,
use_1x1conv=True, strides=2))
else:
blk.append(Residual(num_channels, num_channels))
return blk
b2 = nn.Sequential(*resnet_block(64, 64, 2, first_block=True))
b3 = nn.Sequential(*resnet_block(64, 128, 2))
b4 = nn.Sequential(*resnet_block(128, 256, 2))
b5 = nn.Sequential(*resnet_block(256, 512, 2))
res_net = nn.Sequential(b1, b2, b3, b4, b5,
nn.AdaptiveAvgPool2d((1,1)),
nn.Flatten(), nn.Linear(512, 10))
X = torch.rand(size=(1, 1, 224, 224))
for layer in res_net:
X = layer(X)
print(layer.__class__.__name__,'output shape:\t', X.shape)
Sequential output shape: torch.Size([1, 64, 56, 56])
Sequential output shape: torch.Size([1, 64, 56, 56])
Sequential output shape: torch.Size([1, 128, 28, 28])
Sequential output shape: torch.Size([1, 256, 14, 14])
Sequential output shape: torch.Size([1, 512, 7, 7])
AdaptiveAvgPool2d output shape: torch.Size([1, 512, 1, 1])
Flatten output shape: torch.Size([1, 512])
Linear output shape: torch.Size([1, 10])