手动搭建Inception V1模型（pytorch）
一、Inception V1模型结构
- Inception V1完整结构
二、代码示例
import torchvision
import torch
import torch.nn as nn
def ConvBNRelu(in_channels,out_channels,kernel_size):
return nn.Sequential(
nn.Conv2d(in_channels=in_channels,out_channels=out_channels,kernel_size=kernel_size,
stride=1,padding=kernel_size//2),
nn.BatchNorm2d(out_channels),
nn.ReLU6(inplace=True)
)
class InceptionV1Module(nn.Module):
def __init__(self,in_channels,out_channels1,out_channels2reduce,out_channels2,out_channels3reduce,out_channels3,out_channels4):
super(InceptionV1Module,self).__init__()
self.branch1_conv = ConvBNRelu(in_channels=in_channels,out_channels=out_channels1,kernel_size=1)
self.branch2_conv1 = ConvBNRelu(in_channels=in_channels,out_channels=out_channels2reduce,kernel_size=1)
self.branch2_conv2 = ConvBNRelu(in_channels=out_channels2reduce,out_channels=out_channels2,kernel_size=3)
self.branch3_conv1 = ConvBNRelu(in_channels=in_channels,out_channels=out_channels3reduce,kernel_size=1)
self.branch3_conv2 = ConvBNRelu(in_channels=out_channels3reduce,out_channels=out_channels3,kernel_size=5)
self.branch4_pool = nn.MaxPool2d(kernel_size=3,stride=1,padding=1)
self.branch4_conv1 = ConvBNRelu(in_channels=in_channels,out_channels=out_channels4,kernel_size=1)
def forward(self,x):
out1 = self.branch1_conv(x)
out2 = self.branch2_conv2(self.branch2_conv1(x))
out3 = self.branch3_conv2(self.branch3_conv1(x))
out4 = self.branch4_conv1(self.branch4_pool(x))
out = torch.cat([out1,out2,out3,out4],dim=1)
return out
class InceptionAux(nn.Module):
def __init__(self,in_channels,out_channels):
super(InceptionAux,self).__init__()
self.auxiliary_avgpool = nn.AvgPool2d(kernel_size=5,stride=3)
self.auxiliary_conv1 = ConvBNRelu(in_channels=in_channels,out_channels=128,kernel_size=1)
self.auxiliary_linear1 = nn.Linear(in_features=128*4*4,out_features=1024)
self.auxiliary_relu = nn.ReLU6(inplace=True)
self.auxiliary_dropout = nn.Dropout(p=0.7)
self.auxiliary_linear2 = nn.Linear(in_features=1024,out_features=out_channels)
def forward(self,x):
x = self.auxiliary_conv1(self.auxiliary_avgpool(x))
x = x.view(x.size(0),-1)
x = self.auxiliary_relu(self.auxiliary_linear1(x))
out = self.auxiliary_linear2(self.auxiliary_dropout(x))
return out
class InceptionV1(nn.Module):
def __init__(self,num_classes=1000,stage='train'):
super(InceptionV1,self).__init__()
self.stage = stage
self.block1 = nn.Sequential(
nn.Conv2d(in_channels=3,out_channels=64,kernel_size=7,stride=2,padding=3),
nn.BatchNorm2d(64),
nn.MaxPool2d(kernel_size=3,stride=2,padding=1),
nn.Conv2d(in_channels=64,out_channels=64,kernel_size=1,stride=1),
nn.BatchNorm2d(64)
)
self.block2 = nn.Sequential(
nn.Conv2d(in_channels=64,out_channels=192,kernel_size=3,padding=1,stride=1),
nn.BatchNorm2d(192),
nn.MaxPool2d(kernel_size=3,stride=2,padding=1)
)
self.block3 = nn.Sequential(
InceptionV1Module(in_channels=192,out_channels1=64,out_channels2reduce=96,out_channels2=128,
out_channels3reduce=16,out_channels3=32,out_channels4=32),
InceptionV1Module(in_channels=256,out_channels1=128,out_channels2reduce=128,out_channels2=192,
out_channels3reduce=32,out_channels3=96,out_channels4=64),
nn.MaxPool2d(kernel_size=3,stride=2,padding=1)
)
self.block4_1 = InceptionV1Module(in_channels=480,out_channels1=192,out_channels2reduce=96,out_channels2=208,
out_channels3reduce=16,out_channels3=48,out_channels4=64)
if self.stage == 'train':
self.aux_logits1 = InceptionAux(in_channels=512,out_channels=num_classes)
self.block4_2 = nn.Sequential(
InceptionV1Module(in_channels=512,out_channels1=160,out_channels2reduce=112,out_channels2=224,
out_channels3reduce=24,out_channels3=64,out_channels4=64),
InceptionV1Module(in_channels=512,out_channels1=128,out_channels2reduce=128,out_channels2=256,
out_channels3reduce=24,out_channels3=64,out_channels4=64),
InceptionV1Module(in_channels=512,out_channels1=112,out_channels2reduce=144,out_channels2=288,
out_channels3reduce=32,out_channels3=64,out_channels4=64)
)
if self.stage == 'train':
self.aux_logits2 = InceptionAux(in_channels=528,out_channels=num_classes)
self.block4_3 = nn.Sequential(
InceptionV1Module(in_channels=528,out_channels1=256,out_channels2reduce=160,out_channels2=320,
out_channels3reduce=32,out_channels3=128,out_channels4=128),
nn.MaxPool2d(kernel_size=3,stride=2,padding=1)
)
self.block5 = nn.Sequential(
InceptionV1Module(in_channels=832,out_channels1=256,out_channels2reduce=160,out_channels2=320,
out_channels3reduce=32,out_channels3=128,out_channels4=128),
InceptionV1Module(in_channels=832,out_channels1=384,out_channels2reduce=192,out_channels2=384,
out_channels3reduce=48,out_channels3=128,out_channels4=128)
)
self.avgpool = nn.AvgPool2d(kernel_size=7,stride=1)
self.dropout = nn.Dropout(p=0.4)
self.linear = nn.Linear(in_features=1024,out_features=num_classes)
def forward(self,x):
x = self.block1(x)
x = self.block2(x)
x = self.block3(x)
aux1 = self.block4_1(x)
aux2 = self.block4_2(aux1)
x = self.block4_3(aux2)
out = self.block5(x)
out = self.avgpool(out)
out = self.dropout(out)
out = out.view(out.size(0),-1)
out = self.linear(out)
if self.stage == 'train':
aux1 = self.aux_logits1(aux1)
aux2 = self.aux_logits2(aux2)
return aux1,aux2,out
else:
return out
if __name__ == '__main__':
from torchsummary import summary
model = InceptionV1()
print (model)
input = torch.randn(1,3,224,224)
summary(model,(3,224,224))
aux1,aux2,out = model(input)
print (aux1.shape)
print (aux2.shape)
print (out.shape)
InceptionV1(
(block1): Sequential(
(0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3))
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(3): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(block2): Sequential(
(0): Conv2d(64, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
)
(block3): Sequential(
(0): InceptionV1Module(
(branch1_conv): Sequential(
(0): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv1): Sequential(
(0): Conv2d(192, 96, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv2): Sequential(
(0): Conv2d(96, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv1): Sequential(
(0): Conv2d(192, 16, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv2): Sequential(
(0): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch4_pool): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(branch4_conv1): Sequential(
(0): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
(1): InceptionV1Module(
(branch1_conv): Sequential(
(0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv1): Sequential(
(0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv2): Sequential(
(0): Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv1): Sequential(
(0): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv2): Sequential(
(0): Conv2d(32, 96, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch4_pool): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(branch4_conv1): Sequential(
(0): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
(2): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
)
(block4_1): InceptionV1Module(
(branch1_conv): Sequential(
(0): Conv2d(480, 192, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv1): Sequential(
(0): Conv2d(480, 96, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv2): Sequential(
(0): Conv2d(96, 208, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv1): Sequential(
(0): Conv2d(480, 16, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv2): Sequential(
(0): Conv2d(16, 48, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch4_pool): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(branch4_conv1): Sequential(
(0): Conv2d(480, 64, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
(aux_logits1): InceptionAux(
(auxiliary_avgpool): AvgPool2d(kernel_size=5, stride=3, padding=0)
(auxiliary_conv1): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(auxiliary_linear1): Linear(in_features=2048, out_features=1024, bias=True)
(auxiliary_relu): ReLU6(inplace=True)
(auxiliary_dropout): Dropout(p=0.7, inplace=False)
(auxiliary_linear2): Linear(in_features=1024, out_features=1000, bias=True)
)
(block4_2): Sequential(
(0): InceptionV1Module(
(branch1_conv): Sequential(
(0): Conv2d(512, 160, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv1): Sequential(
(0): Conv2d(512, 112, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv2): Sequential(
(0): Conv2d(112, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv1): Sequential(
(0): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv2): Sequential(
(0): Conv2d(24, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch4_pool): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(branch4_conv1): Sequential(
(0): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
(1): InceptionV1Module(
(branch1_conv): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv1): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv2): Sequential(
(0): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv1): Sequential(
(0): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv2): Sequential(
(0): Conv2d(24, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch4_pool): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(branch4_conv1): Sequential(
(0): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
(2): InceptionV1Module(
(branch1_conv): Sequential(
(0): Conv2d(512, 112, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv1): Sequential(
(0): Conv2d(512, 144, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv2): Sequential(
(0): Conv2d(144, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv1): Sequential(
(0): Conv2d(512, 32, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv2): Sequential(
(0): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch4_pool): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(branch4_conv1): Sequential(
(0): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
)
(aux_logits2): InceptionAux(
(auxiliary_avgpool): AvgPool2d(kernel_size=5, stride=3, padding=0)
(auxiliary_conv1): Sequential(
(0): Conv2d(528, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(auxiliary_linear1): Linear(in_features=2048, out_features=1024, bias=True)
(auxiliary_relu): ReLU6(inplace=True)
(auxiliary_dropout): Dropout(p=0.7, inplace=False)
(auxiliary_linear2): Linear(in_features=1024, out_features=1000, bias=True)
)
(block4_3): Sequential(
(0): InceptionV1Module(
(branch1_conv): Sequential(
(0): Conv2d(528, 256, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv1): Sequential(
(0): Conv2d(528, 160, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv2): Sequential(
(0): Conv2d(160, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv1): Sequential(
(0): Conv2d(528, 32, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv2): Sequential(
(0): Conv2d(32, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch4_pool): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(branch4_conv1): Sequential(
(0): Conv2d(528, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
(1): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
)
(block5): Sequential(
(0): InceptionV1Module(
(branch1_conv): Sequential(
(0): Conv2d(832, 256, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv1): Sequential(
(0): Conv2d(832, 160, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv2): Sequential(
(0): Conv2d(160, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv1): Sequential(
(0): Conv2d(832, 32, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv2): Sequential(
(0): Conv2d(32, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch4_pool): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(branch4_conv1): Sequential(
(0): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
(1): InceptionV1Module(
(branch1_conv): Sequential(
(0): Conv2d(832, 384, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv1): Sequential(
(0): Conv2d(832, 192, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch2_conv2): Sequential(
(0): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv1): Sequential(
(0): Conv2d(832, 48, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch3_conv2): Sequential(
(0): Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(branch4_pool): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(branch4_conv1): Sequential(
(0): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
)
(avgpool): AvgPool2d(kernel_size=7, stride=1, padding=0)
(dropout): Dropout(p=0.4, inplace=False)
(linear): Linear(in_features=1024, out_features=1000, bias=True)
)
----------------------------------------------------------------
Layer (type) Output Shape Param
================================================================
Conv2d-1 [-1, 64, 112, 112] 9,472
BatchNorm2d-2 [-1, 64, 112, 112] 128
MaxPool2d-3 [-1, 64, 56, 56] 0
Conv2d-4 [-1, 64, 56, 56] 4,160
BatchNorm2d-5 [-1, 64, 56, 56] 128
Conv2d-6 [-1, 192, 56, 56] 110,784
BatchNorm2d-7 [-1, 192, 56, 56] 384
MaxPool2d-8 [-1, 192, 28, 28] 0
Conv2d-9 [-1, 64, 28, 28] 12,352
BatchNorm2d-10 [-1, 64, 28, 28] 128
ReLU6-11 [-1, 64, 28, 28] 0
Conv2d-12 [-1, 96, 28, 28] 18,528
BatchNorm2d-13 [-1, 96, 28, 28] 192
ReLU6-14 [-1, 96, 28, 28] 0
Conv2d-15 [-1, 128, 28, 28] 110,720
BatchNorm2d-16 [-1, 128, 28, 28] 256
ReLU6-17 [-1, 128, 28, 28] 0
Conv2d-18 [-1, 16, 28, 28] 3,088
BatchNorm2d-19 [-1, 16, 28, 28] 32
ReLU6-20 [-1, 16, 28, 28] 0
Conv2d-21 [-1, 32, 28, 28] 12,832
BatchNorm2d-22 [-1, 32, 28, 28] 64
ReLU6-23 [-1, 32, 28, 28] 0
MaxPool2d-24 [-1, 192, 28, 28] 0
Conv2d-25 [-1, 32, 28, 28] 6,176
BatchNorm2d-26 [-1, 32, 28, 28] 64
ReLU6-27 [-1, 32, 28, 28] 0
InceptionV1Module-28 [-1, 256, 28, 28] 0
Conv2d-29 [-1, 128, 28, 28] 32,896
BatchNorm2d-30 [-1, 128, 28, 28] 256
ReLU6-31 [-1, 128, 28, 28] 0
Conv2d-32 [-1, 128, 28, 28] 32,896
BatchNorm2d-33 [-1, 128, 28, 28] 256
ReLU6-34 [-1, 128, 28, 28] 0
Conv2d-35 [-1, 192, 28, 28] 221,376
BatchNorm2d-36 [-1, 192, 28, 28] 384
ReLU6-37 [-1, 192, 28, 28] 0
Conv2d-38 [-1, 32, 28, 28] 8,224
BatchNorm2d-39 [-1, 32, 28, 28] 64
ReLU6-40 [-1, 32, 28, 28] 0
Conv2d-41 [-1, 96, 28, 28] 76,896
BatchNorm2d-42 [-1, 96, 28, 28] 192
ReLU6-43 [-1, 96, 28, 28] 0
MaxPool2d-44 [-1, 256, 28, 28] 0
Conv2d-45 [-1, 64, 28, 28] 16,448
BatchNorm2d-46 [-1, 64, 28, 28] 128
ReLU6-47 [-1, 64, 28, 28] 0
InceptionV1Module-48 [-1, 480, 28, 28] 0
MaxPool2d-49 [-1, 480, 14, 14] 0
Conv2d-50 [-1, 192, 14, 14] 92,352
BatchNorm2d-51 [-1, 192, 14, 14] 384
ReLU6-52 [-1, 192, 14, 14] 0
Conv2d-53 [-1, 96, 14, 14] 46,176
BatchNorm2d-54 [-1, 96, 14, 14] 192
ReLU6-55 [-1, 96, 14, 14] 0
Conv2d-56 [-1, 208, 14, 14] 179,920
BatchNorm2d-57 [-1, 208, 14, 14] 416
ReLU6-58 [-1, 208, 14, 14] 0
Conv2d-59 [-1, 16, 14, 14] 7,696
BatchNorm2d-60 [-1, 16, 14, 14] 32
ReLU6-61 [-1, 16, 14, 14] 0
Conv2d-62 [-1, 48, 14, 14] 19,248
BatchNorm2d-63 [-1, 48, 14, 14] 96
ReLU6-64 [-1, 48, 14, 14] 0
MaxPool2d-65 [-1, 480, 14, 14] 0
Conv2d-66 [-1, 64, 14, 14] 30,784
BatchNorm2d-67 [-1, 64, 14, 14] 128
ReLU6-68 [-1, 64, 14, 14] 0
InceptionV1Module-69 [-1, 512, 14, 14] 0
Conv2d-70 [-1, 160, 14, 14] 82,080
BatchNorm2d-71 [-1, 160, 14, 14] 320
ReLU6-72 [-1, 160, 14, 14] 0
Conv2d-73 [-1, 112, 14, 14] 57,456
BatchNorm2d-74 [-1, 112, 14, 14] 224
ReLU6-75 [-1, 112, 14, 14] 0
Conv2d-76 [-1, 224, 14, 14] 226,016
BatchNorm2d-77 [-1, 224, 14, 14] 448
ReLU6-78 [-1, 224, 14, 14] 0
Conv2d-79 [-1, 24, 14, 14] 12,312
BatchNorm2d-80 [-1, 24, 14, 14] 48
ReLU6-81 [-1, 24, 14, 14] 0
Conv2d-82 [-1, 64, 14, 14] 38,464
BatchNorm2d-83 [-1, 64, 14, 14] 128
ReLU6-84 [-1, 64, 14, 14] 0
MaxPool2d-85 [-1, 512, 14, 14] 0
Conv2d-86 [-1, 64, 14, 14] 32,832
BatchNorm2d-87 [-1, 64, 14, 14] 128
ReLU6-88 [-1, 64, 14, 14] 0
InceptionV1Module-89 [-1, 512, 14, 14] 0
Conv2d-90 [-1, 128, 14, 14] 65,664
BatchNorm2d-91 [-1, 128, 14, 14] 256
ReLU6-92 [-1, 128, 14, 14] 0
Conv2d-93 [-1, 128, 14, 14] 65,664
BatchNorm2d-94 [-1, 128, 14, 14] 256
ReLU6-95 [-1, 128, 14, 14] 0
Conv2d-96 [-1, 256, 14, 14] 295,168
BatchNorm2d-97 [-1, 256, 14, 14] 512
ReLU6-98 [-1, 256, 14, 14] 0
Conv2d-99 [-1, 24, 14, 14] 12,312
BatchNorm2d-100 [-1, 24, 14, 14] 48
ReLU6-101 [-1, 24, 14, 14] 0
Conv2d-102 [-1, 64, 14, 14] 38,464
BatchNorm2d-103 [-1, 64, 14, 14] 128
ReLU6-104 [-1, 64, 14, 14] 0
MaxPool2d-105 [-1, 512, 14, 14] 0
Conv2d-106 [-1, 64, 14, 14] 32,832
BatchNorm2d-107 [-1, 64, 14, 14] 128
ReLU6-108 [-1, 64, 14, 14] 0
InceptionV1Module-109 [-1, 512, 14, 14] 0
Conv2d-110 [-1, 112, 14, 14] 57,456
BatchNorm2d-111 [-1, 112, 14, 14] 224
ReLU6-112 [-1, 112, 14, 14] 0
Conv2d-113 [-1, 144, 14, 14] 73,872
BatchNorm2d-114 [-1, 144, 14, 14] 288
ReLU6-115 [-1, 144, 14, 14] 0
Conv2d-116 [-1, 288, 14, 14] 373,536
BatchNorm2d-117 [-1, 288, 14, 14] 576
ReLU6-118 [-1, 288, 14, 14] 0
Conv2d-119 [-1, 32, 14, 14] 16,416
BatchNorm2d-120 [-1, 32, 14, 14] 64
ReLU6-121 [-1, 32, 14, 14] 0
Conv2d-122 [-1, 64, 14, 14] 51,264
BatchNorm2d-123 [-1, 64, 14, 14] 128
ReLU6-124 [-1, 64, 14, 14] 0
MaxPool2d-125 [-1, 512, 14, 14] 0
Conv2d-126 [-1, 64, 14, 14] 32,832
BatchNorm2d-127 [-1, 64, 14, 14] 128
ReLU6-128 [-1, 64, 14, 14] 0
InceptionV1Module-129 [-1, 528, 14, 14] 0
Conv2d-130 [-1, 256, 14, 14] 135,424
BatchNorm2d-131 [-1, 256, 14, 14] 512
ReLU6-132 [-1, 256, 14, 14] 0
Conv2d-133 [-1, 160, 14, 14] 84,640
BatchNorm2d-134 [-1, 160, 14, 14] 320
ReLU6-135 [-1, 160, 14, 14] 0
Conv2d-136 [-1, 320, 14, 14] 461,120
BatchNorm2d-137 [-1, 320, 14, 14] 640
ReLU6-138 [-1, 320, 14, 14] 0
Conv2d-139 [-1, 32, 14, 14] 16,928
BatchNorm2d-140 [-1, 32, 14, 14] 64
ReLU6-141 [-1, 32, 14, 14] 0
Conv2d-142 [-1, 128, 14, 14] 102,528
BatchNorm2d-143 [-1, 128, 14, 14] 256
ReLU6-144 [-1, 128, 14, 14] 0
MaxPool2d-145 [-1, 528, 14, 14] 0
Conv2d-146 [-1, 128, 14, 14] 67,712
BatchNorm2d-147 [-1, 128, 14, 14] 256
ReLU6-148 [-1, 128, 14, 14] 0
InceptionV1Module-149 [-1, 832, 14, 14] 0
MaxPool2d-150 [-1, 832, 7, 7] 0
Conv2d-151 [-1, 256, 7, 7] 213,248
BatchNorm2d-152 [-1, 256, 7, 7] 512
ReLU6-153 [-1, 256, 7, 7] 0
Conv2d-154 [-1, 160, 7, 7] 133,280
BatchNorm2d-155 [-1, 160, 7, 7] 320
ReLU6-156 [-1, 160, 7, 7] 0
Conv2d-157 [-1, 320, 7, 7] 461,120
BatchNorm2d-158 [-1, 320, 7, 7] 640
ReLU6-159 [-1, 320, 7, 7] 0
Conv2d-160 [-1, 32, 7, 7] 26,656
BatchNorm2d-161 [-1, 32, 7, 7] 64
ReLU6-162 [-1, 32, 7, 7] 0
Conv2d-163 [-1, 128, 7, 7] 102,528
BatchNorm2d-164 [-1, 128, 7, 7] 256
ReLU6-165 [-1, 128, 7, 7] 0
MaxPool2d-166 [-1, 832, 7, 7] 0
Conv2d-167 [-1, 128, 7, 7] 106,624
BatchNorm2d-168 [-1, 128, 7, 7] 256
ReLU6-169 [-1, 128, 7, 7] 0
InceptionV1Module-170 [-1, 832, 7, 7] 0
Conv2d-171 [-1, 384, 7, 7] 319,872
BatchNorm2d-172 [-1, 384, 7, 7] 768
ReLU6-173 [-1, 384, 7, 7] 0
Conv2d-174 [-1, 192, 7, 7] 159,936
BatchNorm2d-175 [-1, 192, 7, 7] 384
ReLU6-176 [-1, 192, 7, 7] 0
Conv2d-177 [-1, 384, 7, 7] 663,936
BatchNorm2d-178 [-1, 384, 7, 7] 768
ReLU6-179 [-1, 384, 7, 7] 0
Conv2d-180 [-1, 48, 7, 7] 39,984
BatchNorm2d-181 [-1, 48, 7, 7] 96
ReLU6-182 [-1, 48, 7, 7] 0
Conv2d-183 [-1, 128, 7, 7] 153,728
BatchNorm2d-184 [-1, 128, 7, 7] 256
ReLU6-185 [-1, 128, 7, 7] 0
MaxPool2d-186 [-1, 832, 7, 7] 0
Conv2d-187 [-1, 128, 7, 7] 106,624
BatchNorm2d-188 [-1, 128, 7, 7] 256
ReLU6-189 [-1, 128, 7, 7] 0
InceptionV1Module-190 [-1, 1024, 7, 7] 0
AvgPool2d-191 [-1, 1024, 1, 1] 0
Dropout-192 [-1, 1024, 1, 1] 0
Linear-193 [-1, 1000] 1,025,000
AvgPool2d-194 [-1, 512, 4, 4] 0
Conv2d-195 [-1, 128, 4, 4] 65,664
BatchNorm2d-196 [-1, 128, 4, 4] 256
ReLU6-197 [-1, 128, 4, 4] 0
Linear-198 [-1, 1024] 2,098,176
ReLU6-199 [-1, 1024] 0
Dropout-200 [-1, 1024] 0
Linear-201 [-1, 1000] 1,025,000
InceptionAux-202 [-1, 1000] 0
AvgPool2d-203 [-1, 528, 4, 4] 0
Conv2d-204 [-1, 128, 4, 4] 67,712
BatchNorm2d-205 [-1, 128, 4, 4] 256
ReLU6-206 [-1, 128, 4, 4] 0
Linear-207 [-1, 1024] 2,098,176
ReLU6-208 [-1, 1024] 0
Dropout-209 [-1, 1024] 0
Linear-210 [-1, 1000] 1,025,000
InceptionAux-211 [-1, 1000] 0
================================================================
Total params: 13,393,352
Trainable params: 13,393,352
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 82.15
Params size (MB): 51.09
Estimated Total Size (MB): 133.82
----------------------------------------------------------------
torch.Size([1, 1000])
torch.Size([1, 1000])
torch.Size([1, 1000])
三、参考链接
2509
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
