文章目录
- 一、前期准备
- 二、搭建网络模型
-
- [1. Inception-A](#1. Inception-A)
- [3. Inception-C](#3. Inception-C)
- [4. Reduction-A](#4. Reduction-A)
- [5. Reduction-B](#5. Reduction-B)
- [6. 辅助分支](#6. 辅助分支)
- [7. 模型搭建](#7. 模型搭建)
- [8. 查看模型详情](#8. 查看模型详情)
- 三、训练模型
- 四、结果可视化
- 总结：
- 🍨 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
一、前期准备
1.设置GPU/CPU
python
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,random
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
devicedevice(type='cpu')
2.导入数据
python
data_dir = './weather_photos/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("/")[1] for path in data_paths]
classeNames
python
import matplotlib.pyplot as plt
from PIL import Image
## 指定图像文件夹路径
image_folder = './weather_photos/shine/'
## 获取文件夹中的所有图像文件
image_files = [f for f in os.listdir(image_folder) if f.endswith((".jpg", ".png", ".jpeg"))]
## 创建Matplotlib图像
fig, axes = plt.subplots(3, 8, figsize=(16, 6))
## 使用列表推导式加载和显示图像
for ax, img_file in zip(axes.flat, image_files):
img_path = os.path.join(image_folder, img_file)
img = Image.open(img_path)
ax.imshow(img)
ax.axis('off')
## 显示图像
plt.tight_layout()
plt.show() 
python
total_datadir = './weather_photos/'
train_transforms = 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-->转换为标准正态分布（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(total_datadir, transform=train_transforms)
total_dataDataset ImageFolder
Number of datapoints: 1125
Root location: ./weather_photos/
StandardTransform
Transform: Compose(
Resize(size=[299, 299], interpolation=bilinear, max_size=None, antialias=True)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)
3.划分数据集
● train_size表示训练集大小，通过将总体数据长度的80%转换为整数得到；
● test_size表示测试集大小，是总体数据长度减去训练集大小。
使用torch.utils.data.random_split()方法进行数据集划分。该方法将总体数据total_data按照指定的大小比例（[train_size, test_size]）随机划分为训练集和测试集，并将划分结果分别赋值给train_dataset和test_dataset两个变量。
python
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])
train_dataset, test_dataset(<torch.utils.data.dataset.Subset at 0x16554d2a0>,
<torch.utils.data.dataset.Subset at 0x16603bd60>)
python
train_size,test_size(900, 225)
python
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1)
python
for X, y in test_dl:
print("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
breakShape of X [N, C, H, W]: torch.Size([32, 3, 299, 299])
Shape of y: torch.Size([32]) torch.int64
二、搭建网络模型
1. Inception-A
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)- Inception-B
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)3. Inception-C
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)4. Reduction-A
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)5. Reduction-B
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)6. 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 x7. 模型搭建
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 x
python
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = InceptionV3().to(device)
modelUsing cpu 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=1000, bias=True)
)
8. 查看模型详情
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, 1000] 2,049,000
================================================================
Total params: 23,834,568
Trainable params: 23,834,568
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 1.02
Forward/backward pass size (MB): 224.12
Params size (MB): 90.92
Estimated Total Size (MB): 316.07
----------------------------------------------------------------三、训练模型
1.设置超参数
python
loss_fn = nn.CrossEntropyLoss() ##创建损失函数
learn_rate = 1e-4 ## 学习率
opt = torch.optim.Adam(model.parameters(),lr=learn_rate, weight_decay=1e-4)
scheduler = torch.optim.lr_scheduler.StepLR(opt, step_size=5, gamma=0.1)2.编写训练函数
python
## 训练循环
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset) ## 训练集的大小，一共60000张图片
num_batches = len(dataloader) ## 批次数目， 1875（60000/32）
train_loss, train_acc = 0, 0. ## 初始化训练损失和正确率
for X, y in dataloader: ## 获取图片及其比标签
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
## 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 3.编写测试函数
python
def test (dataloader, model, loss_fn):
size = len(dataloader.dataset) ## 测试集大小一共10000张图片
num_batches = len(dataloader) ## 批次数目，313（10000/32=312.5，向上取整）
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
4.正式训练
python
epochs = 20
train_loss = []
train_acc = []
test_loss = []
test_acc = []
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
train_acc.append(epoch_train_acc)
train_loss.append(epoch_train_loss)
test_acc.append(epoch_test_acc)
test_loss.append(epoch_test_loss)
template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}')
print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')Epoch: 1, Train_acc:71.8%, Train_loss:2.577, Test_acc:25.3%, Test_loss:6.160
Epoch: 2, Train_acc:86.0%, Train_loss:0.786, Test_acc:91.1%, Test_loss:0.296
Epoch: 3, Train_acc:90.4%, Train_loss:0.340, Test_acc:89.3%, Test_loss:0.372
Epoch: 4, Train_acc:90.2%, Train_loss:0.341, Test_acc:95.6%, Test_loss:0.169
Epoch: 5, Train_acc:91.1%, Train_loss:0.273, Test_acc:95.1%, Test_loss:0.135
Epoch: 6, Train_acc:93.1%, Train_loss:0.212, Test_acc:93.8%, Test_loss:0.217
Epoch: 7, Train_acc:91.4%, Train_loss:0.266, Test_acc:94.2%, Test_loss:0.145
Epoch: 8, Train_acc:93.4%, Train_loss:0.278, Test_acc:91.1%, Test_loss:0.252
Epoch: 9, Train_acc:90.9%, Train_loss:0.334, Test_acc:91.6%, Test_loss:0.204
Epoch:10, Train_acc:91.4%, Train_loss:0.339, Test_acc:88.9%, Test_loss:0.345
Epoch:11, Train_acc:94.2%, Train_loss:0.171, Test_acc:96.0%, Test_loss:0.105
Epoch:12, Train_acc:95.0%, Train_loss:0.166, Test_acc:95.6%, Test_loss:0.096
Epoch:13, Train_acc:95.6%, Train_loss:0.103, Test_acc:96.0%, Test_loss:0.119
Epoch:14, Train_acc:97.3%, Train_loss:0.190, Test_acc:94.7%, Test_loss:0.138
Epoch:15, Train_acc:94.6%, Train_loss:0.218, Test_acc:90.2%, Test_loss:0.242
Epoch:16, Train_acc:92.9%, Train_loss:0.189, Test_acc:96.9%, Test_loss:0.109
Epoch:17, Train_acc:95.6%, Train_loss:0.132, Test_acc:93.8%, Test_loss:0.116
Epoch:18, Train_acc:96.3%, Train_loss:0.123, Test_acc:96.9%, Test_loss:0.082
Epoch:19, Train_acc:96.9%, Train_loss:0.170, Test_acc:96.4%, Test_loss:0.085
Epoch:20, Train_acc:94.9%, Train_loss:0.190, Test_acc:96.4%, Test_loss:0.118
Done四、结果可视化
python
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()
总结：
本周主要学习了Inception V3，了解到了该模型相对于Inception V1做出的改进，同时通过实践更加深入地了解到了Inception V3的结构。