- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍖 原作者：K同学啊
IInception v3算法实战
python
import os, PIL, random, pathlib
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import torch.nn.functional as F
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
devicedevice(type='cuda')
网络结构
python
import torch.nn.functional as F
class BasicConv2d(nn.Module):
def __init__(self, in_channels, out_channels, **kwargs):
super(BasicConv2d, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs)
self.bn = nn.BatchNorm2d(out_channels, eps=0.001)
def forward(self, x):
x = self.conv(x)
x = self.bn(x)
return F.relu(x, inplace=True)
class InceptionV3(nn.Module):
def __init__(self, num_classes=1000, aux_logits=False, transform_input=False):
super(InceptionV3, self).__init__()
self.aux_logits = aux_logits
self.transform_input = transform_input
self.Conv2d_1a_3x3 = BasicConv2d(3, 32, kernel_size=3, stride=2)
self.Conv2d_2a_3x3 = BasicConv2d(32, 32, kernel_size=3)
self.Conv2d_2b_3x3 = BasicConv2d(32, 64, kernel_size=3, padding=1)
self.Conv2d_3b_1x1 = BasicConv2d(64, 80, kernel_size=1)
self.Conv2d_4a_3x3 = BasicConv2d(80, 192, kernel_size=3)
self.Mixed_5b = InceptionA(192, pool_features=32)
self.Mixed_5c = InceptionA(256, pool_features=64)
self.Mixed_5d = InceptionA(288, pool_features=64)
self.Mixed_6a = ReductionA(288)
self.Mixed_6b = InceptionB(768, channels_7x7=128)
self.Mixed_6c = InceptionB(768, channels_7x7=160)
self.Mixed_6d = InceptionB(768, channels_7x7=160)
self.Mixed_6e = InceptionB(768, channels_7x7=192)
if aux_logits:
self.AuxLogits = InceptionAux(768, num_classes)
self.Mixed_7a = ReductionB(768)
self.Mixed_7b = InceptionC(1280)
self.Mixed_7c = InceptionC(2048)
self.fc = nn.Linear(2048, num_classes)
def forward(self, x):
if self.transform_input: # 1
x = x.clone()
x[:, 0] = x[:, 0] * (0.229 / 0.5) + (0.485 - 0.5) / 0.5
x[:, 1] = x[:, 1] * (0.224 / 0.5) + (0.456 - 0.5) / 0.5
x[:, 2] = x[:, 2] * (0.225 / 0.5) + (0.406 - 0.5) / 0.5
# 299 x 299 x 3
x = self.Conv2d_1a_3x3(x)
# 149 x 149 x 32
x = self.Conv2d_2a_3x3(x)
# 147 x 147 x 32
x = self.Conv2d_2b_3x3(x)
# 147 x 147 x 64
x = F.max_pool2d(x, kernel_size=3, stride=2)
# 73 x 73 x 64
x = self.Conv2d_3b_1x1(x)
# 73 x 73 x 80
x = self.Conv2d_4a_3x3(x)
# 71 x 71 x 192
x = F.max_pool2d(x, kernel_size=3, stride=2)
# 35 x 35 x 192
x = self.Mixed_5b(x)
# 35 x 35 x 256
x = self.Mixed_5c(x)
# 35 x 35 x 288
x = self.Mixed_5d(x)
# 35 x 35 x 288
x = self.Mixed_6a(x)
# 17 x 17 x 768
x = self.Mixed_6b(x)
# 17 x 17 x 768
x = self.Mixed_6c(x)
# 17 x 17 x 768
x = self.Mixed_6d(x)
# 17 x 17 x 768
x = self.Mixed_6e(x)
# 17 x 17 x 768
if self.training and self.aux_logits:
aux = self.AuxLogits(x)
# 17 x 17 x 768
x = self.Mixed_7a(x)
# 8 x 8 x 1280
x = self.Mixed_7b(x)
# 8 x 8 x 2048
x = self.Mixed_7c(x)
# 8 x 8 x 2048
x = F.avg_pool2d(x, kernel_size=8)
# 1 x 1 x 2048
x = F.dropout(x, training=self.training)
# 1 x 1 x 2048
x = x.view(x.size(0), -1)
# 2048
x = self.fc(x)
# 1000 (num_classes)
if self.training and self.aux_logits:
return x, aux
return xInceptionA
python
class InceptionA(nn.Module):
def __init__(self, in_channels, pool_features):
super(InceptionA, self).__init__()
self.branch1x1 = BasicConv2d(in_channels, 64, kernel_size=1) # 1
self.branch5x5_1 = BasicConv2d(in_channels, 48, kernel_size=1)
self.branch5x5_2 = BasicConv2d(48, 64, kernel_size=5, padding=2)
self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1)
self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
self.branch3x3dbl_3 = BasicConv2d(96, 96, kernel_size=3, padding=1)
self.branch_pool = BasicConv2d(in_channels, pool_features, kernel_size=1)
def forward(self, x):
branch1x1 = self.branch1x1(x)
branch5x5 = self.branch5x5_1(x)
branch5x5 = self.branch5x5_2(branch5x5)
branch3x3dbl = self.branch3x3dbl_1(x)
branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)
branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
branch_pool = self.branch_pool(branch_pool)
outputs = [branch1x1, branch5x5, branch3x3dbl, branch_pool]
return torch.cat(outputs, 1)InceptionB
python
class InceptionB(nn.Module):
def __init__(self, in_channels, channels_7x7):
super(InceptionB, self).__init__()
self.branch1x1 = BasicConv2d(in_channels, 192, kernel_size=1)
c7 = channels_7x7
self.branch7x7_1 = BasicConv2d(in_channels, c7, kernel_size=1)
self.branch7x7_2 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3))
self.branch7x7_3 = BasicConv2d(c7, 192, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7dbl_1 = BasicConv2d(in_channels, c7, kernel_size=1)
self.branch7x7dbl_2 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7dbl_3 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3))
self.branch7x7dbl_4 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7dbl_5 = BasicConv2d(c7, 192, kernel_size=(1, 7), padding=(0, 3))
self.branch_pool = BasicConv2d(in_channels, 192, kernel_size=1)
def forward(self, x):
branch1x1 = self.branch1x1(x)
branch7x7 = self.branch7x7_1(x)
branch7x7 = self.branch7x7_2(branch7x7)
branch7x7 = self.branch7x7_3(branch7x7)
branch7x7dbl = self.branch7x7dbl_1(x)
branch7x7dbl = self.branch7x7dbl_2(branch7x7dbl)
branch7x7dbl = self.branch7x7dbl_3(branch7x7dbl)
branch7x7dbl = self.branch7x7dbl_4(branch7x7dbl)
branch7x7dbl = self.branch7x7dbl_5(branch7x7dbl)
branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
branch_pool = self.branch_pool(branch_pool)
outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool]
return torch.cat(outputs, 1)InceptionC
python
class InceptionC(nn.Module):
def __init__(self, in_channels):
super(InceptionC, self).__init__()
self.branch1x1 = BasicConv2d(in_channels, 320, kernel_size=1)
self.branch3x3_1 = BasicConv2d(in_channels, 384, kernel_size=1)
self.branch3x3_2a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1))
self.branch3x3_2b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0))
self.branch3x3dbl_1 = BasicConv2d(in_channels, 448, kernel_size=1)
self.branch3x3dbl_2 = BasicConv2d(448, 384, kernel_size=3, padding=1)
self.branch3x3dbl_3a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1))
self.branch3x3dbl_3b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0))
self.branch_pool = BasicConv2d(in_channels, 192, kernel_size=1)
def forward(self, x):
branch1x1 = self.branch1x1(x)
branch3x3 = self.branch3x3_1(x)
branch3x3 = [
self.branch3x3_2a(branch3x3),
self.branch3x3_2b(branch3x3),
]
branch3x3 = torch.cat(branch3x3, 1)
branch3x3dbl = self.branch3x3dbl_1(x)
branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
branch3x3dbl = [
self.branch3x3dbl_3a(branch3x3dbl),
self.branch3x3dbl_3b(branch3x3dbl),
]
branch3x3dbl = torch.cat(branch3x3dbl, 1)
branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
branch_pool = self.branch_pool(branch_pool)
outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool]
return torch.cat(outputs, 1)ReductionA
python
class ReductionA(nn.Module):
def __init__(self, in_channels):
super(ReductionA, self).__init__()
self.branch3x3 = BasicConv2d(in_channels, 384, kernel_size=3, stride=2)
self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1)
self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
self.branch3x3dbl_3 = BasicConv2d(96, 96, kernel_size=3, stride=2)
def forward(self, x):
branch3x3 = self.branch3x3(x)
branch3x3dbl = self.branch3x3dbl_1(x)
branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)
branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
outputs = [branch3x3, branch3x3dbl, branch_pool]
return torch.cat(outputs, 1)ReductionB
python
class ReductionB(nn.Module):
def __init__(self, in_channels):
super(ReductionB, self).__init__()
self.branch3x3_1 = BasicConv2d(in_channels, 192, kernel_size=1)
self.branch3x3_2 = BasicConv2d(192, 320, kernel_size=3, stride=2)
self.branch7x7x3_1 = BasicConv2d(in_channels, 192, kernel_size=1)
self.branch7x7x3_2 = BasicConv2d(192, 192, kernel_size=(1, 7), padding=(0, 3))
self.branch7x7x3_3 = BasicConv2d(192, 192, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7x3_4 = BasicConv2d(192, 192, kernel_size=3, stride=2)
def forward(self, x):
branch3x3 = self.branch3x3_1(x)
branch3x3 = self.branch3x3_2(branch3x3)
branch7x7x3 = self.branch7x7x3_1(x)
branch7x7x3 = self.branch7x7x3_2(branch7x7x3)
branch7x7x3 = self.branch7x7x3_3(branch7x7x3)
branch7x7x3 = self.branch7x7x3_4(branch7x7x3)
branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
outputs = [branch3x3, branch7x7x3, branch_pool]
return torch.cat(outputs, 1)辅助分支
python
class InceptionAux(nn.Module):
def __init__(self, in_channels, num_classes):
super(InceptionAux, self).__init__()
self.conv0 = BasicConv2d(in_channels, 128, kernel_size=1)
self.conv1 = BasicConv2d(128, 768, kernel_size=5)
self.conv1.stddev = 0.01
self.fc = nn.Linear(768, num_classes)
self.fc.stddev = 0.001
def forward(self, x):
# 17 x 17 x 768
x = F.avg_pool2d(x, kernel_size=5, stride=3)
# 5 x 5 x 768
x = self.conv0(x)
# 5 x 5 x 128
x = self.conv1(x)
# 1 x 1 x 768
x = x.view(x.size(0), -1)
# 768
x = self.fc(x)
# 1000
return x
python
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = InceptionV3(4).to(device)
modelUsing cuda device
InceptionV3(
(Conv2d_1a_3x3): BasicConv2d(
(conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), bias=False)
(bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(Conv2d_2a_3x3): BasicConv2d(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(Conv2d_2b_3x3): BasicConv2d(
(conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(Conv2d_3b_1x1): BasicConv2d(
(conv): Conv2d(64, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(80, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(Conv2d_4a_3x3): BasicConv2d(
(conv): Conv2d(80, 192, kernel_size=(3, 3), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(Mixed_5b): InceptionA(
(branch1x1): BasicConv2d(
(conv): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_1): BasicConv2d(
(conv): Conv2d(192, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_2): BasicConv2d(
(conv): Conv2d(48, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3): BasicConv2d(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_5c): InceptionA(
(branch1x1): BasicConv2d(
(conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_1): BasicConv2d(
(conv): Conv2d(256, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_2): BasicConv2d(
(conv): Conv2d(48, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3): BasicConv2d(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_5d): InceptionA(
(branch1x1): BasicConv2d(
(conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_1): BasicConv2d(
(conv): Conv2d(288, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_2): BasicConv2d(
(conv): Conv2d(48, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3): BasicConv2d(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_6a): ReductionA(
(branch3x3): BasicConv2d(
(conv): Conv2d(288, 384, kernel_size=(3, 3), stride=(2, 2), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3): BasicConv2d(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_6b): InceptionB(
(branch1x1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_1): BasicConv2d(
(conv): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_2): BasicConv2d(
(conv): Conv2d(128, 128, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_3): BasicConv2d(
(conv): Conv2d(128, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_1): BasicConv2d(
(conv): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_2): BasicConv2d(
(conv): Conv2d(128, 128, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_3): BasicConv2d(
(conv): Conv2d(128, 128, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_4): BasicConv2d(
(conv): Conv2d(128, 128, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_5): BasicConv2d(
(conv): Conv2d(128, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_6c): InceptionB(
(branch1x1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_1): BasicConv2d(
(conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_2): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_3): BasicConv2d(
(conv): Conv2d(160, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_1): BasicConv2d(
(conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_2): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_3): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_4): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_5): BasicConv2d(
(conv): Conv2d(160, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_6d): InceptionB(
(branch1x1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_1): BasicConv2d(
(conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_2): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_3): BasicConv2d(
(conv): Conv2d(160, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_1): BasicConv2d(
(conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_2): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_3): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_4): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_5): BasicConv2d(
(conv): Conv2d(160, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_6e): InceptionB(
(branch1x1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_2): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_3): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_2): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_3): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_4): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_5): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_7a): ReductionB(
(branch3x3_1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_2): BasicConv2d(
(conv): Conv2d(192, 320, kernel_size=(3, 3), stride=(2, 2), bias=False)
(bn): BatchNorm2d(320, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7x3_1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7x3_2): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7x3_3): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7x3_4): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(2, 2), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_7b): InceptionC(
(branch1x1): BasicConv2d(
(conv): Conv2d(1280, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(320, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_1): BasicConv2d(
(conv): Conv2d(1280, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_2a): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_2b): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(1280, 448, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(448, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(448, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3a): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3b): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(1280, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_7c): InceptionC(
(branch1x1): BasicConv2d(
(conv): Conv2d(2048, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(320, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_1): BasicConv2d(
(conv): Conv2d(2048, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_2a): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_2b): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(2048, 448, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(448, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(448, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3a): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3b): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(2048, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(fc): Linear(in_features=2048, out_features=4, bias=True)
)
python
# 统计模型参数量以及其他指标
import torchsummary as summary
summary.summary(model, (3, 299, 299))----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 32, 149, 149] 864
BatchNorm2d-2 [-1, 32, 149, 149] 64
BasicConv2d-3 [-1, 32, 149, 149] 0
Conv2d-4 [-1, 32, 147, 147] 9,216
BatchNorm2d-5 [-1, 32, 147, 147] 64
BasicConv2d-6 [-1, 32, 147, 147] 0
Conv2d-7 [-1, 64, 147, 147] 18,432
BatchNorm2d-8 [-1, 64, 147, 147] 128
BasicConv2d-9 [-1, 64, 147, 147] 0
Conv2d-10 [-1, 80, 73, 73] 5,120
BatchNorm2d-11 [-1, 80, 73, 73] 160
BasicConv2d-12 [-1, 80, 73, 73] 0
Conv2d-13 [-1, 192, 71, 71] 138,240
BatchNorm2d-14 [-1, 192, 71, 71] 384
BasicConv2d-15 [-1, 192, 71, 71] 0
Conv2d-16 [-1, 64, 35, 35] 12,288
BatchNorm2d-17 [-1, 64, 35, 35] 128
BasicConv2d-18 [-1, 64, 35, 35] 0
Conv2d-19 [-1, 48, 35, 35] 9,216
BatchNorm2d-20 [-1, 48, 35, 35] 96
BasicConv2d-21 [-1, 48, 35, 35] 0
Conv2d-22 [-1, 64, 35, 35] 76,800
BatchNorm2d-23 [-1, 64, 35, 35] 128
BasicConv2d-24 [-1, 64, 35, 35] 0
Conv2d-25 [-1, 64, 35, 35] 12,288
BatchNorm2d-26 [-1, 64, 35, 35] 128
BasicConv2d-27 [-1, 64, 35, 35] 0
Conv2d-28 [-1, 96, 35, 35] 55,296
BatchNorm2d-29 [-1, 96, 35, 35] 192
BasicConv2d-30 [-1, 96, 35, 35] 0
Conv2d-31 [-1, 96, 35, 35] 82,944
BatchNorm2d-32 [-1, 96, 35, 35] 192
BasicConv2d-33 [-1, 96, 35, 35] 0
Conv2d-34 [-1, 32, 35, 35] 6,144
BatchNorm2d-35 [-1, 32, 35, 35] 64
BasicConv2d-36 [-1, 32, 35, 35] 0
InceptionA-37 [-1, 256, 35, 35] 0
Conv2d-38 [-1, 64, 35, 35] 16,384
BatchNorm2d-39 [-1, 64, 35, 35] 128
BasicConv2d-40 [-1, 64, 35, 35] 0
Conv2d-41 [-1, 48, 35, 35] 12,288
BatchNorm2d-42 [-1, 48, 35, 35] 96
BasicConv2d-43 [-1, 48, 35, 35] 0
Conv2d-44 [-1, 64, 35, 35] 76,800
BatchNorm2d-45 [-1, 64, 35, 35] 128
BasicConv2d-46 [-1, 64, 35, 35] 0
Conv2d-47 [-1, 64, 35, 35] 16,384
BatchNorm2d-48 [-1, 64, 35, 35] 128
BasicConv2d-49 [-1, 64, 35, 35] 0
Conv2d-50 [-1, 96, 35, 35] 55,296
BatchNorm2d-51 [-1, 96, 35, 35] 192
BasicConv2d-52 [-1, 96, 35, 35] 0
Conv2d-53 [-1, 96, 35, 35] 82,944
BatchNorm2d-54 [-1, 96, 35, 35] 192
BasicConv2d-55 [-1, 96, 35, 35] 0
Conv2d-56 [-1, 64, 35, 35] 16,384
BatchNorm2d-57 [-1, 64, 35, 35] 128
BasicConv2d-58 [-1, 64, 35, 35] 0
InceptionA-59 [-1, 288, 35, 35] 0
Conv2d-60 [-1, 64, 35, 35] 18,432
BatchNorm2d-61 [-1, 64, 35, 35] 128
BasicConv2d-62 [-1, 64, 35, 35] 0
Conv2d-63 [-1, 48, 35, 35] 13,824
BatchNorm2d-64 [-1, 48, 35, 35] 96
BasicConv2d-65 [-1, 48, 35, 35] 0
Conv2d-66 [-1, 64, 35, 35] 76,800
BatchNorm2d-67 [-1, 64, 35, 35] 128
BasicConv2d-68 [-1, 64, 35, 35] 0
Conv2d-69 [-1, 64, 35, 35] 18,432
BatchNorm2d-70 [-1, 64, 35, 35] 128
BasicConv2d-71 [-1, 64, 35, 35] 0
Conv2d-72 [-1, 96, 35, 35] 55,296
BatchNorm2d-73 [-1, 96, 35, 35] 192
BasicConv2d-74 [-1, 96, 35, 35] 0
Conv2d-75 [-1, 96, 35, 35] 82,944
BatchNorm2d-76 [-1, 96, 35, 35] 192
BasicConv2d-77 [-1, 96, 35, 35] 0
Conv2d-78 [-1, 64, 35, 35] 18,432
BatchNorm2d-79 [-1, 64, 35, 35] 128
BasicConv2d-80 [-1, 64, 35, 35] 0
InceptionA-81 [-1, 288, 35, 35] 0
Conv2d-82 [-1, 384, 17, 17] 995,328
BatchNorm2d-83 [-1, 384, 17, 17] 768
BasicConv2d-84 [-1, 384, 17, 17] 0
Conv2d-85 [-1, 64, 35, 35] 18,432
BatchNorm2d-86 [-1, 64, 35, 35] 128
BasicConv2d-87 [-1, 64, 35, 35] 0
Conv2d-88 [-1, 96, 35, 35] 55,296
BatchNorm2d-89 [-1, 96, 35, 35] 192
BasicConv2d-90 [-1, 96, 35, 35] 0
Conv2d-91 [-1, 96, 17, 17] 82,944
BatchNorm2d-92 [-1, 96, 17, 17] 192
BasicConv2d-93 [-1, 96, 17, 17] 0
ReductionA-94 [-1, 768, 17, 17] 0
Conv2d-95 [-1, 192, 17, 17] 147,456
BatchNorm2d-96 [-1, 192, 17, 17] 384
BasicConv2d-97 [-1, 192, 17, 17] 0
Conv2d-98 [-1, 128, 17, 17] 98,304
BatchNorm2d-99 [-1, 128, 17, 17] 256
BasicConv2d-100 [-1, 128, 17, 17] 0
Conv2d-101 [-1, 128, 17, 17] 114,688
BatchNorm2d-102 [-1, 128, 17, 17] 256
BasicConv2d-103 [-1, 128, 17, 17] 0
Conv2d-104 [-1, 192, 17, 17] 172,032
BatchNorm2d-105 [-1, 192, 17, 17] 384
BasicConv2d-106 [-1, 192, 17, 17] 0
Conv2d-107 [-1, 128, 17, 17] 98,304
BatchNorm2d-108 [-1, 128, 17, 17] 256
BasicConv2d-109 [-1, 128, 17, 17] 0
Conv2d-110 [-1, 128, 17, 17] 114,688
BatchNorm2d-111 [-1, 128, 17, 17] 256
BasicConv2d-112 [-1, 128, 17, 17] 0
Conv2d-113 [-1, 128, 17, 17] 114,688
BatchNorm2d-114 [-1, 128, 17, 17] 256
BasicConv2d-115 [-1, 128, 17, 17] 0
Conv2d-116 [-1, 128, 17, 17] 114,688
BatchNorm2d-117 [-1, 128, 17, 17] 256
BasicConv2d-118 [-1, 128, 17, 17] 0
Conv2d-119 [-1, 192, 17, 17] 172,032
BatchNorm2d-120 [-1, 192, 17, 17] 384
BasicConv2d-121 [-1, 192, 17, 17] 0
Conv2d-122 [-1, 192, 17, 17] 147,456
BatchNorm2d-123 [-1, 192, 17, 17] 384
BasicConv2d-124 [-1, 192, 17, 17] 0
InceptionB-125 [-1, 768, 17, 17] 0
Conv2d-126 [-1, 192, 17, 17] 147,456
BatchNorm2d-127 [-1, 192, 17, 17] 384
BasicConv2d-128 [-1, 192, 17, 17] 0
Conv2d-129 [-1, 160, 17, 17] 122,880
BatchNorm2d-130 [-1, 160, 17, 17] 320
BasicConv2d-131 [-1, 160, 17, 17] 0
Conv2d-132 [-1, 160, 17, 17] 179,200
BatchNorm2d-133 [-1, 160, 17, 17] 320
BasicConv2d-134 [-1, 160, 17, 17] 0
Conv2d-135 [-1, 192, 17, 17] 215,040
BatchNorm2d-136 [-1, 192, 17, 17] 384
BasicConv2d-137 [-1, 192, 17, 17] 0
Conv2d-138 [-1, 160, 17, 17] 122,880
BatchNorm2d-139 [-1, 160, 17, 17] 320
BasicConv2d-140 [-1, 160, 17, 17] 0
Conv2d-141 [-1, 160, 17, 17] 179,200
BatchNorm2d-142 [-1, 160, 17, 17] 320
BasicConv2d-143 [-1, 160, 17, 17] 0
Conv2d-144 [-1, 160, 17, 17] 179,200
BatchNorm2d-145 [-1, 160, 17, 17] 320
BasicConv2d-146 [-1, 160, 17, 17] 0
Conv2d-147 [-1, 160, 17, 17] 179,200
BatchNorm2d-148 [-1, 160, 17, 17] 320
BasicConv2d-149 [-1, 160, 17, 17] 0
Conv2d-150 [-1, 192, 17, 17] 215,040
BatchNorm2d-151 [-1, 192, 17, 17] 384
BasicConv2d-152 [-1, 192, 17, 17] 0
Conv2d-153 [-1, 192, 17, 17] 147,456
BatchNorm2d-154 [-1, 192, 17, 17] 384
BasicConv2d-155 [-1, 192, 17, 17] 0
InceptionB-156 [-1, 768, 17, 17] 0
Conv2d-157 [-1, 192, 17, 17] 147,456
BatchNorm2d-158 [-1, 192, 17, 17] 384
BasicConv2d-159 [-1, 192, 17, 17] 0
Conv2d-160 [-1, 160, 17, 17] 122,880
BatchNorm2d-161 [-1, 160, 17, 17] 320
BasicConv2d-162 [-1, 160, 17, 17] 0
Conv2d-163 [-1, 160, 17, 17] 179,200
BatchNorm2d-164 [-1, 160, 17, 17] 320
BasicConv2d-165 [-1, 160, 17, 17] 0
Conv2d-166 [-1, 192, 17, 17] 215,040
BatchNorm2d-167 [-1, 192, 17, 17] 384
BasicConv2d-168 [-1, 192, 17, 17] 0
Conv2d-169 [-1, 160, 17, 17] 122,880
BatchNorm2d-170 [-1, 160, 17, 17] 320
BasicConv2d-171 [-1, 160, 17, 17] 0
Conv2d-172 [-1, 160, 17, 17] 179,200
BatchNorm2d-173 [-1, 160, 17, 17] 320
BasicConv2d-174 [-1, 160, 17, 17] 0
Conv2d-175 [-1, 160, 17, 17] 179,200
BatchNorm2d-176 [-1, 160, 17, 17] 320
BasicConv2d-177 [-1, 160, 17, 17] 0
Conv2d-178 [-1, 160, 17, 17] 179,200
BatchNorm2d-179 [-1, 160, 17, 17] 320
BasicConv2d-180 [-1, 160, 17, 17] 0
Conv2d-181 [-1, 192, 17, 17] 215,040
BatchNorm2d-182 [-1, 192, 17, 17] 384
BasicConv2d-183 [-1, 192, 17, 17] 0
Conv2d-184 [-1, 192, 17, 17] 147,456
BatchNorm2d-185 [-1, 192, 17, 17] 384
BasicConv2d-186 [-1, 192, 17, 17] 0
InceptionB-187 [-1, 768, 17, 17] 0
Conv2d-188 [-1, 192, 17, 17] 147,456
BatchNorm2d-189 [-1, 192, 17, 17] 384
BasicConv2d-190 [-1, 192, 17, 17] 0
Conv2d-191 [-1, 192, 17, 17] 147,456
BatchNorm2d-192 [-1, 192, 17, 17] 384
BasicConv2d-193 [-1, 192, 17, 17] 0
Conv2d-194 [-1, 192, 17, 17] 258,048
BatchNorm2d-195 [-1, 192, 17, 17] 384
BasicConv2d-196 [-1, 192, 17, 17] 0
Conv2d-197 [-1, 192, 17, 17] 258,048
BatchNorm2d-198 [-1, 192, 17, 17] 384
BasicConv2d-199 [-1, 192, 17, 17] 0
Conv2d-200 [-1, 192, 17, 17] 147,456
BatchNorm2d-201 [-1, 192, 17, 17] 384
BasicConv2d-202 [-1, 192, 17, 17] 0
Conv2d-203 [-1, 192, 17, 17] 258,048
BatchNorm2d-204 [-1, 192, 17, 17] 384
BasicConv2d-205 [-1, 192, 17, 17] 0
Conv2d-206 [-1, 192, 17, 17] 258,048
BatchNorm2d-207 [-1, 192, 17, 17] 384
BasicConv2d-208 [-1, 192, 17, 17] 0
Conv2d-209 [-1, 192, 17, 17] 258,048
BatchNorm2d-210 [-1, 192, 17, 17] 384
BasicConv2d-211 [-1, 192, 17, 17] 0
Conv2d-212 [-1, 192, 17, 17] 258,048
BatchNorm2d-213 [-1, 192, 17, 17] 384
BasicConv2d-214 [-1, 192, 17, 17] 0
Conv2d-215 [-1, 192, 17, 17] 147,456
BatchNorm2d-216 [-1, 192, 17, 17] 384
BasicConv2d-217 [-1, 192, 17, 17] 0
InceptionB-218 [-1, 768, 17, 17] 0
Conv2d-219 [-1, 192, 17, 17] 147,456
BatchNorm2d-220 [-1, 192, 17, 17] 384
BasicConv2d-221 [-1, 192, 17, 17] 0
Conv2d-222 [-1, 320, 8, 8] 552,960
BatchNorm2d-223 [-1, 320, 8, 8] 640
BasicConv2d-224 [-1, 320, 8, 8] 0
Conv2d-225 [-1, 192, 17, 17] 147,456
BatchNorm2d-226 [-1, 192, 17, 17] 384
BasicConv2d-227 [-1, 192, 17, 17] 0
Conv2d-228 [-1, 192, 17, 17] 258,048
BatchNorm2d-229 [-1, 192, 17, 17] 384
BasicConv2d-230 [-1, 192, 17, 17] 0
Conv2d-231 [-1, 192, 17, 17] 258,048
BatchNorm2d-232 [-1, 192, 17, 17] 384
BasicConv2d-233 [-1, 192, 17, 17] 0
Conv2d-234 [-1, 192, 8, 8] 331,776
BatchNorm2d-235 [-1, 192, 8, 8] 384
BasicConv2d-236 [-1, 192, 8, 8] 0
ReductionB-237 [-1, 1280, 8, 8] 0
Conv2d-238 [-1, 320, 8, 8] 409,600
BatchNorm2d-239 [-1, 320, 8, 8] 640
BasicConv2d-240 [-1, 320, 8, 8] 0
Conv2d-241 [-1, 384, 8, 8] 491,520
BatchNorm2d-242 [-1, 384, 8, 8] 768
BasicConv2d-243 [-1, 384, 8, 8] 0
Conv2d-244 [-1, 384, 8, 8] 442,368
BatchNorm2d-245 [-1, 384, 8, 8] 768
BasicConv2d-246 [-1, 384, 8, 8] 0
Conv2d-247 [-1, 384, 8, 8] 442,368
BatchNorm2d-248 [-1, 384, 8, 8] 768
BasicConv2d-249 [-1, 384, 8, 8] 0
Conv2d-250 [-1, 448, 8, 8] 573,440
BatchNorm2d-251 [-1, 448, 8, 8] 896
BasicConv2d-252 [-1, 448, 8, 8] 0
Conv2d-253 [-1, 384, 8, 8] 1,548,288
BatchNorm2d-254 [-1, 384, 8, 8] 768
BasicConv2d-255 [-1, 384, 8, 8] 0
Conv2d-256 [-1, 384, 8, 8] 442,368
BatchNorm2d-257 [-1, 384, 8, 8] 768
BasicConv2d-258 [-1, 384, 8, 8] 0
Conv2d-259 [-1, 384, 8, 8] 442,368
BatchNorm2d-260 [-1, 384, 8, 8] 768
BasicConv2d-261 [-1, 384, 8, 8] 0
Conv2d-262 [-1, 192, 8, 8] 245,760
BatchNorm2d-263 [-1, 192, 8, 8] 384
BasicConv2d-264 [-1, 192, 8, 8] 0
InceptionC-265 [-1, 2048, 8, 8] 0
Conv2d-266 [-1, 320, 8, 8] 655,360
BatchNorm2d-267 [-1, 320, 8, 8] 640
BasicConv2d-268 [-1, 320, 8, 8] 0
Conv2d-269 [-1, 384, 8, 8] 786,432
BatchNorm2d-270 [-1, 384, 8, 8] 768
BasicConv2d-271 [-1, 384, 8, 8] 0
Conv2d-272 [-1, 384, 8, 8] 442,368
BatchNorm2d-273 [-1, 384, 8, 8] 768
BasicConv2d-274 [-1, 384, 8, 8] 0
Conv2d-275 [-1, 384, 8, 8] 442,368
BatchNorm2d-276 [-1, 384, 8, 8] 768
BasicConv2d-277 [-1, 384, 8, 8] 0
Conv2d-278 [-1, 448, 8, 8] 917,504
BatchNorm2d-279 [-1, 448, 8, 8] 896
BasicConv2d-280 [-1, 448, 8, 8] 0
Conv2d-281 [-1, 384, 8, 8] 1,548,288
BatchNorm2d-282 [-1, 384, 8, 8] 768
BasicConv2d-283 [-1, 384, 8, 8] 0
Conv2d-284 [-1, 384, 8, 8] 442,368
BatchNorm2d-285 [-1, 384, 8, 8] 768
BasicConv2d-286 [-1, 384, 8, 8] 0
Conv2d-287 [-1, 384, 8, 8] 442,368
BatchNorm2d-288 [-1, 384, 8, 8] 768
BasicConv2d-289 [-1, 384, 8, 8] 0
Conv2d-290 [-1, 192, 8, 8] 393,216
BatchNorm2d-291 [-1, 192, 8, 8] 384
BasicConv2d-292 [-1, 192, 8, 8] 0
InceptionC-293 [-1, 2048, 8, 8] 0
Linear-294 [-1, 4] 8,196
================================================================
Total params: 21,793,764
Trainable params: 21,793,764
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 1.02
Forward/backward pass size (MB): 224.12
Params size (MB): 83.14
Estimated Total Size (MB): 308.28
----------------------------------------------------------------
python
# 导入数据
data_dir = r'C:\Users\11054\Desktop\kLearning\p1_data'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[-1] for path in data_paths]
print(classeNames)
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为：", image_count)['cloudy', 'rain', 'shine', 'sunrise']
图片总数为： 1125
python
# 数据预处理
train_transforms = transforms.Compose([
transforms.Resize([299, 299]), # 将输入图片resize成统一尺寸
# transforms.RandomHorizontalFlip(), # 随机水平翻转
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
transforms.Normalize( # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])
test_transform = transforms.Compose([
transforms.Resize([299, 299]), # 将输入图片resize成统一尺寸
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
transforms.Normalize( # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])
total_data = datasets.ImageFolder(data_dir, transform=train_transforms)
print(total_data.class_to_idx)
# 划分数据集
train_size = int(0.8 * len(total_data))
test_size = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
batch_size = 8 #根据自己的显卡，选择合适的batch_size大小
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
for X, y in test_dl:
print("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
break{'cloudy': 0, 'rain': 1, 'shine': 2, 'sunrise': 3}
Shape of X [N, C, H, W]: torch.Size([8, 3, 299, 299])
Shape of y: torch.Size([8]) torch.int64
python
# 训练和测试函数
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset) # 训练集的大小
num_batches = len(dataloader) # 批次数目, (size/batch_size，向上取整)
train_loss, train_acc = 0, 0 # 初始化训练损失和正确率
for X, y in dataloader: # 获取图片及其标签
X, y = X.to(device), y.to(device)
# 计算预测误差
pred = model(X) # 网络输出
loss = loss_fn(pred, y) # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失
# 反向传播
optimizer.zero_grad() # grad属性归零
loss.backward() # 反向传播
optimizer.step() # 每一步自动更新
# 记录acc与loss
train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
train_loss += loss.item()
train_acc /= size
train_loss /= num_batches
return train_acc, train_loss
def test(dataloader, model, loss_fn):
size = len(dataloader.dataset) # 测试集的大小
num_batches = len(dataloader) # 批次数目
test_loss, test_acc = 0, 0
# 当不进行训练时，停止梯度更新，节省计算内存消耗
with torch.no_grad():
for imgs, target in dataloader:
imgs, target = imgs.to(device), target.to(device)
# 计算loss
target_pred = model(imgs)
loss = loss_fn(target_pred, target)
test_loss += loss.item()
test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()
test_acc /= size
test_loss /= num_batches
return test_acc, test_loss
python
# 正式训练
import copy
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
epochs = 50
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0 # 设置一个最佳准确率，作为最佳模型的判别指标
for epoch in range(epochs):
# 更新学习率（使用自定义学习率时使用）
# adjust_learning_rate(optimizer, epoch, learn_rate)
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
# scheduler.step() # 更新学习率（调用官方动态学习率接口时使用）
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
# 保存最佳模型到 best_model
if epoch_test_acc > best_acc:
best_acc = epoch_test_acc
best_model = copy.deepcopy(model)
train_acc.append(epoch_train_acc)
train_loss.append(epoch_train_loss)
test_acc.append(epoch_test_acc)
test_loss.append(epoch_test_loss)
# 获取当前的学习率
lr = optimizer.state_dict()['param_groups'][0]['lr']
template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')
print(template.format(epoch + 1, epoch_train_acc * 100, epoch_train_loss,
epoch_test_acc * 100, epoch_test_loss, lr))
# 保存最佳模型到文件中
PATH = r'C:/Users/11054/Desktop/kLearning/J9_learning/best_model.pth' # 保存的参数文件名
torch.save(model.state_dict(), PATH)
print('Done')Epoch: 1, Train_acc:73.0%, Train_loss:0.729, Test_acc:89.3%, Test_loss:0.296, Lr:1.00E-04
Epoch: 2, Train_acc:80.9%, Train_loss:0.540, Test_acc:89.8%, Test_loss:0.336, Lr:1.00E-04
Epoch: 3, Train_acc:82.0%, Train_loss:0.506, Test_acc:85.3%, Test_loss:0.486, Lr:1.00E-04
Epoch: 4, Train_acc:83.8%, Train_loss:0.443, Test_acc:87.1%, Test_loss:0.352, Lr:1.00E-04
Epoch: 5, Train_acc:85.0%, Train_loss:0.458, Test_acc:87.1%, Test_loss:0.317, Lr:1.00E-04
Epoch: 6, Train_acc:85.8%, Train_loss:0.421, Test_acc:92.0%, Test_loss:0.303, Lr:1.00E-04
Epoch: 7, Train_acc:86.7%, Train_loss:0.393, Test_acc:88.4%, Test_loss:0.335, Lr:1.00E-04
Epoch: 8, Train_acc:89.1%, Train_loss:0.314, Test_acc:94.7%, Test_loss:0.186, Lr:1.00E-04
Epoch: 9, Train_acc:88.3%, Train_loss:0.344, Test_acc:90.7%, Test_loss:0.233, Lr:1.00E-04
Epoch:10, Train_acc:88.4%, Train_loss:0.337, Test_acc:80.9%, Test_loss:0.435, Lr:1.00E-04
Epoch:11, Train_acc:89.3%, Train_loss:0.342, Test_acc:94.7%, Test_loss:0.200, Lr:1.00E-04
Epoch:12, Train_acc:90.1%, Train_loss:0.298, Test_acc:92.9%, Test_loss:0.221, Lr:1.00E-04
Epoch:13, Train_acc:89.0%, Train_loss:0.344, Test_acc:87.6%, Test_loss:0.325, Lr:1.00E-04
Epoch:14, Train_acc:90.1%, Train_loss:0.288, Test_acc:93.3%, Test_loss:0.219, Lr:1.00E-04
Epoch:15, Train_acc:91.0%, Train_loss:0.260, Test_acc:91.1%, Test_loss:0.238, Lr:1.00E-04
Epoch:16, Train_acc:89.9%, Train_loss:0.296, Test_acc:96.9%, Test_loss:0.128, Lr:1.00E-04
Epoch:17, Train_acc:90.6%, Train_loss:0.310, Test_acc:95.1%, Test_loss:0.167, Lr:1.00E-04
Epoch:18, Train_acc:89.7%, Train_loss:0.288, Test_acc:92.9%, Test_loss:0.207, Lr:1.00E-04
Epoch:19, Train_acc:92.7%, Train_loss:0.225, Test_acc:95.6%, Test_loss:0.153, Lr:1.00E-04
Epoch:20, Train_acc:92.8%, Train_loss:0.210, Test_acc:92.0%, Test_loss:0.340, Lr:1.00E-04
Epoch:21, Train_acc:92.9%, Train_loss:0.210, Test_acc:94.2%, Test_loss:0.163, Lr:1.00E-04
Epoch:22, Train_acc:92.1%, Train_loss:0.258, Test_acc:92.9%, Test_loss:0.215, Lr:1.00E-04
Epoch:23, Train_acc:91.3%, Train_loss:0.270, Test_acc:92.9%, Test_loss:0.210, Lr:1.00E-04
Epoch:24, Train_acc:92.2%, Train_loss:0.251, Test_acc:92.0%, Test_loss:0.289, Lr:1.00E-04
Epoch:25, Train_acc:93.6%, Train_loss:0.194, Test_acc:94.7%, Test_loss:0.135, Lr:1.00E-04
Epoch:26, Train_acc:95.7%, Train_loss:0.156, Test_acc:93.3%, Test_loss:0.248, Lr:1.00E-04
Epoch:27, Train_acc:94.6%, Train_loss:0.178, Test_acc:87.1%, Test_loss:0.395, Lr:1.00E-04
Epoch:28, Train_acc:93.2%, Train_loss:0.224, Test_acc:95.6%, Test_loss:0.136, Lr:1.00E-04
Epoch:29, Train_acc:94.4%, Train_loss:0.161, Test_acc:94.7%, Test_loss:0.177, Lr:1.00E-04
Epoch:30, Train_acc:94.6%, Train_loss:0.157, Test_acc:94.7%, Test_loss:0.162, Lr:1.00E-04
Epoch:31, Train_acc:92.2%, Train_loss:0.219, Test_acc:94.7%, Test_loss:0.261, Lr:1.00E-04
Epoch:32, Train_acc:94.2%, Train_loss:0.199, Test_acc:95.6%, Test_loss:0.154, Lr:1.00E-04
Epoch:33, Train_acc:94.1%, Train_loss:0.194, Test_acc:96.9%, Test_loss:0.104, Lr:1.00E-04
Epoch:34, Train_acc:95.3%, Train_loss:0.132, Test_acc:92.9%, Test_loss:0.201, Lr:1.00E-04
Epoch:35, Train_acc:95.9%, Train_loss:0.119, Test_acc:94.2%, Test_loss:0.148, Lr:1.00E-04
Epoch:36, Train_acc:94.6%, Train_loss:0.144, Test_acc:95.6%, Test_loss:0.129, Lr:1.00E-04
Epoch:37, Train_acc:97.0%, Train_loss:0.107, Test_acc:93.3%, Test_loss:0.194, Lr:1.00E-04
Epoch:38, Train_acc:96.9%, Train_loss:0.109, Test_acc:95.6%, Test_loss:0.135, Lr:1.00E-04
Epoch:39, Train_acc:95.1%, Train_loss:0.155, Test_acc:93.8%, Test_loss:0.212, Lr:1.00E-04
Epoch:40, Train_acc:94.3%, Train_loss:0.155, Test_acc:96.9%, Test_loss:0.087, Lr:1.00E-04
Epoch:41, Train_acc:94.7%, Train_loss:0.164, Test_acc:96.0%, Test_loss:0.129, Lr:1.00E-04
Epoch:42, Train_acc:94.2%, Train_loss:0.165, Test_acc:96.9%, Test_loss:0.097, Lr:1.00E-04
Epoch:43, Train_acc:96.6%, Train_loss:0.115, Test_acc:95.6%, Test_loss:0.171, Lr:1.00E-04
Epoch:44, Train_acc:96.8%, Train_loss:0.108, Test_acc:95.6%, Test_loss:0.142, Lr:1.00E-04
Epoch:45, Train_acc:95.0%, Train_loss:0.151, Test_acc:97.3%, Test_loss:0.116, Lr:1.00E-04
Epoch:46, Train_acc:94.6%, Train_loss:0.152, Test_acc:95.1%, Test_loss:0.134, Lr:1.00E-04
Epoch:47, Train_acc:96.7%, Train_loss:0.105, Test_acc:94.7%, Test_loss:0.175, Lr:1.00E-04
Epoch:48, Train_acc:97.1%, Train_loss:0.094, Test_acc:94.7%, Test_loss:0.168, Lr:1.00E-04
Epoch:49, Train_acc:96.6%, Train_loss:0.108, Test_acc:95.6%, Test_loss:0.161, Lr:1.00E-04
Epoch:50, Train_acc:96.4%, Train_loss:0.097, Test_acc:96.0%, Test_loss:0.146, Lr:1.00E-04
Done
python
# 结果可视化
import matplotlib.pyplot as plt
# 隐藏警告
import warnings
warnings.filterwarnings("ignore") # 忽略警告信息
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号
plt.rcParams['figure.dpi'] = 100 # 分辨率
epochs_range = range(epochs)
plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
from PIL import Image
classes = list(total_data.class_to_idx)
print(classes)
print(total_data.class_to_idx)
def predict_one_image(image_path, model, transform, classes):
test_img = Image.open(image_path).convert('RGB')
plt.imshow(test_img) # 展示预测的图片
test_img = transform(test_img)
img = test_img.to(device).unsqueeze(0)
model.eval()
output = model(img)
_, pred = torch.max(output, 1)
pred_class = classes[pred]
print(f'预测结果是：{pred_class}')
# 预测训练集中的某张照片
predict_one_image(image_path=r'C:\Users\11054\Desktop\kLearning\p1_data\rain\rain1.jpg',
model=model,
transform=train_transforms,
classes=classes)
['cloudy', 'rain', 'shine', 'sunrise']
{'cloudy': 0, 'rain': 1, 'shine': 2, 'sunrise': 3}
预测结果是：rain
个人总结
- Inception v3 的核心思想是使用Inception模块，在同一层中并行使用不同大小的卷积核（如 1x1、3x3、5x5），以捕捉不同尺度的特征。
通过模块化设计，网络可以在不同层次上提取多尺度的特征，从而提高模型的泛化能力 - Inception v3 将输入尺寸增大到 299 * 299，优点如下：
捕捉更多细节：较大的输入尺寸可以保留更多的图像细节，尤其是在高分辨率图像上。
更深的特征提取：较大的输入尺寸允许卷积层在更大的感受野内提取特征，从而提高模型的表达能力。
推理时间的权衡：虽然增大了输入尺寸会稍微增加计算量，但 Inception v3 通过优化网络结构（如使用更小的卷积核和分解卷积操作），整体推理时间仍然可以控制在合理范围内。 - InceptionA
InceptionA模块是Inception V3网络中第一个主要的Inception模块，它主要用于在网络的早期阶段提取大量的低级特征。InceptionA模块包含几个并行的卷积路径，这些路径的输出在深度维度上进行拼接。具体结构如下：
1x1卷积：用于降低通道数，减少计算量。
5x5卷积：通过前一个1x1卷积降维后，进行5x5卷积，提取更复杂的特征。
3x3卷积（两次）：通过1x1卷积降维后，进行两次3x3卷积，等效于一次5x5卷积，但计算量更小。
3x3最大池化：进行最大池化操作，然后通过1x1卷积恢复通道数。
- InceptionB
InceptionB模块出现在网络的中段，用于提取中级特征。它进一步增加了网络的深度和复杂性，同时保持了计算效率。具体结构如下：
1x1卷积：用于降维和减少计算量。
1x7卷积：通过前一个1x1卷积降维后，进行1x7卷积，捕捉水平方向的特征。
7x1卷积：通过前一个1x1卷积降维后，进行7x1卷积，捕捉垂直方向的特征。
3x3最大池化：进行最大池化操作，然后通过1x1卷积恢复通道数。
- InceptionC
InceptionC模块出现在网络的后段，用于提取高级特征。它更加复杂，使用了更多非对称的卷积核组合。具体结构如下：
1x1卷积：用于降维和减少计算量。
1x3和3x1卷积：通过前一个1x1卷积降维后，进行1x3和3x1卷积，分别捕捉不同方向的特征。
3x3最大池化：进行最大池化操作，然后通过1x1卷积恢复通道数。
- ReductionA
ReductionA模块用于在网络的中段减少特征图的尺寸，同时增加通道数。它通过不同的路径组合来实现这一点，具体结构如下：
3x3最大池化：直接进行最大池化操作，减少特征图尺寸。
3x3卷积：通过1x1卷积降维后，进行3x3卷积，减少特征图尺寸。
两个3x3卷积（两次3x3卷积）：通过1x1卷积降维后，进行两次3x3卷积，等效于一次5x5卷积，减少特征图尺寸。
- ReductionB
ReductionB模块用于在网络的后段进一步减少特征图的尺寸，同时增加通道数。它的结构更加复杂，具体如下：
3x3最大池化：直接进行最大池化操作，减少特征图尺寸。
3x3卷积：通过1x1卷积降维后，进行3x3卷积，减少特征图尺寸。
两个1x7和7x1卷积（两次1x7和7x1卷积）：通过1x1卷积降维后，进行两次1x7和7x1卷积，捕捉不同方向的特征，然后通过3x3卷积减少特征图尺寸。
- 辅助分支
辅助分支是Inception V3网络中的一个特殊设计，用于在网络的中间层增加额外的监督信号，从而帮助网络更快地收敛和提高模型的鲁棒性。辅助分支的具体结构如下：
平均池化：在中间层的特征图上进行平均池化操作，减少特征图的尺寸。
1x1卷积：降维，减少通道数。
全连接层：将降维后的特征图展平，通过全连接层生成辅助分类器的输出。
辅助分类器：用于计算中间层的损失，这个损失在训练过程中会被加到最终的损失函数中。