微信小程序公司网站怎么制作桂林市网站建设公司

• 🍨 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CPU（如果有GPU就使用GPU，否则使用CPU）

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms,datasetsimport os,PIL,pathlib device = torch.device("cuda" if torch.cuda.is_available() else "cpu")device

device(type=‘cpu’)

2.导入数据

import os,PIL,random,pathlibdata_dir = './4-data/'
data_dir = pathlib.Path(data_dir)data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("/")[1] for path in data_paths]
classeNames

[‘.DS_Store’, ‘Others’, ‘Monkeypox’]

total_datadir = './4-data/'train_transforms = transforms.Compose([transforms.Resize([224,224]),         ## 将输入图片resize成统一尺寸transforms.ToTensor(),                ## 将PIL Image或numpy.ndarray转换成tensor并归一化到[0, 1]之间transforms.Normalize(                 ## 标准化处理-->转换为正态分布（高斯分布），使模型更加容易收敛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])从数据集随机抽样得到的])total_data = datasets.ImageFolder(total_datadir,transform=train_transforms)
total_data

Dataset ImageFolder
Number of datapoints: 2142
Root location: ./4-data/
StandardTransform
Transform: Compose(
Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=True)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)

total_data.class_to_idx

{‘Monkeypox’: 0, ‘Others’: 1}

3.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])
train_dataset, test_dataset

(<torch.utils.data.dataset.Subset at 0x1529b7fd0>,
<torch.utils.data.dataset.Subset at 0x1529b74f0>)

train_size, test_size

(1713, 429)

batch_size = 32train_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)

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

Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y torch.Size([32]) torch.int64

二、模型复现

import torch
import torch.nn as nn
import torch.nn.functional as Fclass inception_block(nn.Module):def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):super(inception_block, self).__init__()# 1x1 conv branchself.branch1 = nn.Sequential(nn.Conv2d(in_channels, ch1x1, kernel_size=1),nn.BatchNorm2d(ch1x1),nn.ReLU(inplace=True))# 1x1 conv -> 3x3 conv branchself.branch2 = nn.Sequential(nn.Conv2d(in_channels, ch3x3red, kernel_size=1),nn.BatchNorm2d(ch3x3red),nn.ReLU(inplace=True),nn.Conv2d(ch3x3red, ch3x3, kernel_size=3, padding=1),nn.BatchNorm2d(ch3x3),nn.ReLU(inplace=True))# 1x1 conv -> 5x5 conv branchself.branch3 = nn.Sequential(nn.Conv2d(in_channels, ch5x5red, kernel_size=1),nn.BatchNorm2d(ch5x5red),nn.ReLU(inplace=True),nn.Conv2d(ch5x5red, ch5x5, kernel_size=5, padding=2),nn.BatchNorm2d(ch5x5),nn.ReLU(inplace=True))# 3x3 max pooling -> 1x1 conv branchself.branch4 = nn.Sequential(nn.MaxPool2d(kernel_size=3, stride=1, padding=1),nn.Conv2d(in_channels, pool_proj, kernel_size=1),nn.BatchNorm2d(pool_proj),nn.ReLU(inplace=True))def forward(self, x):# Compute forward pass through all branches and concatenate the output feature mapsbranch1_output = self.branch1(x)branch2_output = self.branch2(x)branch3_output = self.branch3(x)branch4_output = self.branch4(x)outputs = [branch1_output, branch2_output, branch3_output, branch4_output]return torch.cat(outputs, 1)

class InceptionV1(nn.Module):def __init__(self, num_classes=1000):super(InceptionV1, self).__init__()self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)self.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.conv2 = nn.Conv2d(64, 64, kernel_size=1, stride=1, padding=0)self.conv3 = nn.Conv2d(64, 192, kernel_size=3, stride=1, padding=1)self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.inception3a = inception_block(192, 64, 96, 128, 16, 32, 32)self.inception3b = inception_block(256, 128, 128, 192, 32, 96, 64)self.maxpool3    = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.inception4a = inception_block(480, 192, 96, 208, 16, 48, 64)self.inception4b = inception_block(512, 160, 112, 224, 24, 64, 64)self.inception4c = inception_block(512, 128, 128, 256, 24, 64, 64)self.inception4d = inception_block(512, 112, 144, 288, 32, 64, 64)self.inception4e = inception_block(528, 256, 160, 320, 32, 128, 128)self.maxpool4    = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.inception5a = inception_block(832, 256, 160, 320, 32, 128, 128)self.inception5b=nn.Sequential(inception_block(832, 384, 192, 384, 48, 128, 128),nn.AvgPool2d(kernel_size=7,stride=1,padding=0),nn.Dropout(0.4))# 全连接网络层，用于分类self.classifier = nn.Sequential(nn.Linear(in_features=1024, out_features=1024),nn.ReLU(),nn.Linear(in_features=1024, out_features=num_classes),nn.Softmax(dim=1))def forward(self, x):x = self.conv1(x)x = F.relu(x)x = self.maxpool1(x)x = self.conv2(x)x = F.relu(x)x = self.conv3(x)x = F.relu(x)x = self.maxpool2(x)x = self.inception3a(x)x = self.inception3b(x)x = self.maxpool3(x)x = self.inception4a(x)x = self.inception4b(x)x = self.inception4c(x)x = self.inception4d(x)x = self.inception4e(x)x = self.maxpool4(x)x = self.inception5a(x)x = self.inception5b(x)x = torch.flatten(x, start_dim=1)x = self.classifier(x)return x

# 统计模型参数量以及其他指标
import torchsummary # 调用并将模型转移到GPU中
model = InceptionV1().to(device)# 显示网络结构 
torchsummary.summary(model, (3, 224, 224))
print(model)

----------------------------------------------------------------Layer (type)               Output Shape         Param #
================================================================Conv2d-1         [-1, 64, 112, 112]           9,472MaxPool2d-2           [-1, 64, 56, 56]               0Conv2d-3           [-1, 64, 56, 56]           4,160Conv2d-4          [-1, 192, 56, 56]         110,784MaxPool2d-5          [-1, 192, 28, 28]               0Conv2d-6           [-1, 64, 28, 28]          12,352BatchNorm2d-7           [-1, 64, 28, 28]             128ReLU-8           [-1, 64, 28, 28]               0Conv2d-9           [-1, 96, 28, 28]          18,528BatchNorm2d-10           [-1, 96, 28, 28]             192ReLU-11           [-1, 96, 28, 28]               0Conv2d-12          [-1, 128, 28, 28]         110,720BatchNorm2d-13          [-1, 128, 28, 28]             256ReLU-14          [-1, 128, 28, 28]               0Conv2d-15           [-1, 16, 28, 28]           3,088BatchNorm2d-16           [-1, 16, 28, 28]              32ReLU-17           [-1, 16, 28, 28]               0Conv2d-18           [-1, 32, 28, 28]          12,832BatchNorm2d-19           [-1, 32, 28, 28]              64ReLU-20           [-1, 32, 28, 28]               0MaxPool2d-21          [-1, 192, 28, 28]               0Conv2d-22           [-1, 32, 28, 28]           6,176BatchNorm2d-23           [-1, 32, 28, 28]              64ReLU-24           [-1, 32, 28, 28]               0inception_block-25          [-1, 256, 28, 28]               0Conv2d-26          [-1, 128, 28, 28]          32,896BatchNorm2d-27          [-1, 128, 28, 28]             256ReLU-28          [-1, 128, 28, 28]               0Conv2d-29          [-1, 128, 28, 28]          32,896BatchNorm2d-30          [-1, 128, 28, 28]             256ReLU-31          [-1, 128, 28, 28]               0Conv2d-32          [-1, 192, 28, 28]         221,376BatchNorm2d-33          [-1, 192, 28, 28]             384ReLU-34          [-1, 192, 28, 28]               0Conv2d-35           [-1, 32, 28, 28]           8,224BatchNorm2d-36           [-1, 32, 28, 28]              64ReLU-37           [-1, 32, 28, 28]               0Conv2d-38           [-1, 96, 28, 28]          76,896BatchNorm2d-39           [-1, 96, 28, 28]             192ReLU-40           [-1, 96, 28, 28]               0MaxPool2d-41          [-1, 256, 28, 28]               0Conv2d-42           [-1, 64, 28, 28]          16,448BatchNorm2d-43           [-1, 64, 28, 28]             128ReLU-44           [-1, 64, 28, 28]               0inception_block-45          [-1, 480, 28, 28]               0MaxPool2d-46          [-1, 480, 14, 14]               0Conv2d-47          [-1, 192, 14, 14]          92,352BatchNorm2d-48          [-1, 192, 14, 14]             384ReLU-49          [-1, 192, 14, 14]               0Conv2d-50           [-1, 96, 14, 14]          46,176BatchNorm2d-51           [-1, 96, 14, 14]             192ReLU-52           [-1, 96, 14, 14]               0Conv2d-53          [-1, 208, 14, 14]         179,920BatchNorm2d-54          [-1, 208, 14, 14]             416ReLU-55          [-1, 208, 14, 14]               0Conv2d-56           [-1, 16, 14, 14]           7,696BatchNorm2d-57           [-1, 16, 14, 14]              32ReLU-58           [-1, 16, 14, 14]               0Conv2d-59           [-1, 48, 14, 14]          19,248BatchNorm2d-60           [-1, 48, 14, 14]              96ReLU-61           [-1, 48, 14, 14]               0MaxPool2d-62          [-1, 480, 14, 14]               0Conv2d-63           [-1, 64, 14, 14]          30,784BatchNorm2d-64           [-1, 64, 14, 14]             128ReLU-65           [-1, 64, 14, 14]               0inception_block-66          [-1, 512, 14, 14]               0Conv2d-67          [-1, 160, 14, 14]          82,080BatchNorm2d-68          [-1, 160, 14, 14]             320ReLU-69          [-1, 160, 14, 14]               0Conv2d-70          [-1, 112, 14, 14]          57,456BatchNorm2d-71          [-1, 112, 14, 14]             224ReLU-72          [-1, 112, 14, 14]               0Conv2d-73          [-1, 224, 14, 14]         226,016BatchNorm2d-74          [-1, 224, 14, 14]             448ReLU-75          [-1, 224, 14, 14]               0Conv2d-76           [-1, 24, 14, 14]          12,312BatchNorm2d-77           [-1, 24, 14, 14]              48ReLU-78           [-1, 24, 14, 14]               0Conv2d-79           [-1, 64, 14, 14]          38,464BatchNorm2d-80           [-1, 64, 14, 14]             128ReLU-81           [-1, 64, 14, 14]               0MaxPool2d-82          [-1, 512, 14, 14]               0Conv2d-83           [-1, 64, 14, 14]          32,832BatchNorm2d-84           [-1, 64, 14, 14]             128ReLU-85           [-1, 64, 14, 14]               0inception_block-86          [-1, 512, 14, 14]               0Conv2d-87          [-1, 128, 14, 14]          65,664BatchNorm2d-88          [-1, 128, 14, 14]             256ReLU-89          [-1, 128, 14, 14]               0Conv2d-90          [-1, 128, 14, 14]          65,664BatchNorm2d-91          [-1, 128, 14, 14]             256ReLU-92          [-1, 128, 14, 14]               0Conv2d-93          [-1, 256, 14, 14]         295,168BatchNorm2d-94          [-1, 256, 14, 14]             512ReLU-95          [-1, 256, 14, 14]               0Conv2d-96           [-1, 24, 14, 14]          12,312BatchNorm2d-97           [-1, 24, 14, 14]              48ReLU-98           [-1, 24, 14, 14]               0Conv2d-99           [-1, 64, 14, 14]          38,464BatchNorm2d-100           [-1, 64, 14, 14]             128ReLU-101           [-1, 64, 14, 14]               0MaxPool2d-102          [-1, 512, 14, 14]               0Conv2d-103           [-1, 64, 14, 14]          32,832BatchNorm2d-104           [-1, 64, 14, 14]             128ReLU-105           [-1, 64, 14, 14]               0inception_block-106          [-1, 512, 14, 14]               0Conv2d-107          [-1, 112, 14, 14]          57,456BatchNorm2d-108          [-1, 112, 14, 14]             224ReLU-109          [-1, 112, 14, 14]               0Conv2d-110          [-1, 144, 14, 14]          73,872BatchNorm2d-111          [-1, 144, 14, 14]             288ReLU-112          [-1, 144, 14, 14]               0Conv2d-113          [-1, 288, 14, 14]         373,536BatchNorm2d-114          [-1, 288, 14, 14]             576ReLU-115          [-1, 288, 14, 14]               0Conv2d-116           [-1, 32, 14, 14]          16,416BatchNorm2d-117           [-1, 32, 14, 14]              64ReLU-118           [-1, 32, 14, 14]               0Conv2d-119           [-1, 64, 14, 14]          51,264BatchNorm2d-120           [-1, 64, 14, 14]             128ReLU-121           [-1, 64, 14, 14]               0MaxPool2d-122          [-1, 512, 14, 14]               0Conv2d-123           [-1, 64, 14, 14]          32,832BatchNorm2d-124           [-1, 64, 14, 14]             128ReLU-125           [-1, 64, 14, 14]               0inception_block-126          [-1, 528, 14, 14]               0Conv2d-127          [-1, 256, 14, 14]         135,424BatchNorm2d-128          [-1, 256, 14, 14]             512ReLU-129          [-1, 256, 14, 14]               0Conv2d-130          [-1, 160, 14, 14]          84,640BatchNorm2d-131          [-1, 160, 14, 14]             320ReLU-132          [-1, 160, 14, 14]               0Conv2d-133          [-1, 320, 14, 14]         461,120BatchNorm2d-134          [-1, 320, 14, 14]             640ReLU-135          [-1, 320, 14, 14]               0Conv2d-136           [-1, 32, 14, 14]          16,928BatchNorm2d-137           [-1, 32, 14, 14]              64ReLU-138           [-1, 32, 14, 14]               0Conv2d-139          [-1, 128, 14, 14]         102,528BatchNorm2d-140          [-1, 128, 14, 14]             256ReLU-141          [-1, 128, 14, 14]               0MaxPool2d-142          [-1, 528, 14, 14]               0Conv2d-143          [-1, 128, 14, 14]          67,712BatchNorm2d-144          [-1, 128, 14, 14]             256ReLU-145          [-1, 128, 14, 14]               0inception_block-146          [-1, 832, 14, 14]               0MaxPool2d-147            [-1, 832, 7, 7]               0Conv2d-148            [-1, 256, 7, 7]         213,248BatchNorm2d-149            [-1, 256, 7, 7]             512ReLU-150            [-1, 256, 7, 7]               0Conv2d-151            [-1, 160, 7, 7]         133,280BatchNorm2d-152            [-1, 160, 7, 7]             320ReLU-153            [-1, 160, 7, 7]               0Conv2d-154            [-1, 320, 7, 7]         461,120BatchNorm2d-155            [-1, 320, 7, 7]             640ReLU-156            [-1, 320, 7, 7]               0Conv2d-157             [-1, 32, 7, 7]          26,656BatchNorm2d-158             [-1, 32, 7, 7]              64ReLU-159             [-1, 32, 7, 7]               0Conv2d-160            [-1, 128, 7, 7]         102,528BatchNorm2d-161            [-1, 128, 7, 7]             256ReLU-162            [-1, 128, 7, 7]               0MaxPool2d-163            [-1, 832, 7, 7]               0Conv2d-164            [-1, 128, 7, 7]         106,624BatchNorm2d-165            [-1, 128, 7, 7]             256ReLU-166            [-1, 128, 7, 7]               0inception_block-167            [-1, 832, 7, 7]               0Conv2d-168            [-1, 384, 7, 7]         319,872BatchNorm2d-169            [-1, 384, 7, 7]             768ReLU-170            [-1, 384, 7, 7]               0Conv2d-171            [-1, 192, 7, 7]         159,936BatchNorm2d-172            [-1, 192, 7, 7]             384ReLU-173            [-1, 192, 7, 7]               0Conv2d-174            [-1, 384, 7, 7]         663,936BatchNorm2d-175            [-1, 384, 7, 7]             768ReLU-176            [-1, 384, 7, 7]               0Conv2d-177             [-1, 48, 7, 7]          39,984BatchNorm2d-178             [-1, 48, 7, 7]              96ReLU-179             [-1, 48, 7, 7]               0Conv2d-180            [-1, 128, 7, 7]         153,728BatchNorm2d-181            [-1, 128, 7, 7]             256ReLU-182            [-1, 128, 7, 7]               0MaxPool2d-183            [-1, 832, 7, 7]               0Conv2d-184            [-1, 128, 7, 7]         106,624BatchNorm2d-185            [-1, 128, 7, 7]             256ReLU-186            [-1, 128, 7, 7]               0inception_block-187           [-1, 1024, 7, 7]               0AvgPool2d-188           [-1, 1024, 1, 1]               0Dropout-189           [-1, 1024, 1, 1]               0Linear-190                 [-1, 1024]       1,049,600ReLU-191                 [-1, 1024]               0Linear-192                 [-1, 1000]       1,025,000Softmax-193                 [-1, 1000]               0
================================================================
Total params: 8,062,072
Trainable params: 8,062,072
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 69.63
Params size (MB): 30.75
Estimated Total Size (MB): 100.96
----------------------------------------------------------------
InceptionV1((conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3))(maxpool1): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)(conv2): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))(conv3): Conv2d(64, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(maxpool2): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)(inception3a): inception_block((branch1): Sequential((0): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True))(branch2): Sequential((0): Conv2d(192, 96, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(96, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch3): Sequential((0): Conv2d(192, 16, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch4): Sequential((0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)(1): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1))(2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(3): ReLU(inplace=True)))(inception3b): inception_block((branch1): Sequential((0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True))(branch2): Sequential((0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(4): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch3): Sequential((0): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(32, 96, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(4): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch4): Sequential((0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)(1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1))(2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(3): ReLU(inplace=True)))(maxpool3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)(inception4a): inception_block((branch1): Sequential((0): Conv2d(480, 192, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True))(branch2): Sequential((0): Conv2d(480, 96, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(96, 208, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(4): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch3): Sequential((0): Conv2d(480, 16, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(16, 48, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch4): Sequential((0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)(1): Conv2d(480, 64, kernel_size=(1, 1), stride=(1, 1))(2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(3): ReLU(inplace=True)))(inception4b): inception_block((branch1): Sequential((0): Conv2d(512, 160, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True))(branch2): Sequential((0): Conv2d(512, 112, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(112, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(4): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch3): Sequential((0): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(24, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch4): Sequential((0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)(1): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))(2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(3): ReLU(inplace=True)))(inception4c): inception_block((branch1): Sequential((0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True))(branch2): Sequential((0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch3): Sequential((0): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(24, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch4): Sequential((0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)(1): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))(2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(3): ReLU(inplace=True)))(inception4d): inception_block((branch1): Sequential((0): Conv2d(512, 112, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True))(branch2): Sequential((0): Conv2d(512, 144, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(144, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(4): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch3): Sequential((0): Conv2d(512, 32, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch4): Sequential((0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)(1): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))(2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(3): ReLU(inplace=True)))(inception4e): inception_block((branch1): Sequential((0): Conv2d(528, 256, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True))(branch2): Sequential((0): Conv2d(528, 160, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(160, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(4): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch3): Sequential((0): Conv2d(528, 32, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(32, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch4): Sequential((0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)(1): Conv2d(528, 128, kernel_size=(1, 1), stride=(1, 1))(2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(3): ReLU(inplace=True)))(maxpool4): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)(inception5a): inception_block((branch1): Sequential((0): Conv2d(832, 256, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True))(branch2): Sequential((0): Conv2d(832, 160, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(160, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(4): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch3): Sequential((0): Conv2d(832, 32, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(32, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch4): Sequential((0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)(1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1))(2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(3): ReLU(inplace=True)))(inception5b): Sequential((0): inception_block((branch1): Sequential((0): Conv2d(832, 384, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True))(branch2): Sequential((0): Conv2d(832, 192, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(4): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch3): Sequential((0): Conv2d(832, 48, kernel_size=(1, 1), stride=(1, 1))(1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True))(branch4): Sequential((0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)(1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1))(2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(3): ReLU(inplace=True)))(1): AvgPool2d(kernel_size=7, stride=1, padding=0)(2): Dropout(p=0.4, inplace=False))(classifier): Sequential((0): Linear(in_features=1024, out_features=1024, bias=True)(1): ReLU()(2): Linear(in_features=1024, out_features=1000, bias=True)(3): Softmax(dim=1))
)

三、训练模型

1.设置超参数

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=10, gamma=0.1)

2.编写训练函数

## 训练循环def train(dataloader, model, loss_fn, optimizer):size = len(dataloader.dataset)num_batches = len(dataloader)train_loss, train_acc = 0, 0for X, y in dataloader: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losstrain_acc += (pred.argmax(1) == y).type(torch.float).sum().item()  ##train_loss += loss.item()train_acc /= sizetrain_loss /= num_batchesreturn train_acc, train_loss

3.编写测试函数

def test (dataloader, model, loss_fn):size = len(dataloader.dataset)num_batches = len(dataloader)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losstarget_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 /= sizetest_loss /= num_batchesreturn test_acc, test_loss

4.正式训练

epochs = 10
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:57.0%, Train_loss:6.653, Test_acc:55.7%, Test_loss:6.356
Epoch: 2, Train_acc:64.5%, Train_loss:6.268, Test_acc:69.5%, Test_loss:6.218
Epoch: 3, Train_acc:68.3%, Train_loss:6.227, Test_acc:70.4%, Test_loss:6.198
Epoch: 4, Train_acc:71.4%, Train_loss:6.200, Test_acc:74.6%, Test_loss:6.164
Epoch: 5, Train_acc:72.4%, Train_loss:6.186, Test_acc:72.3%, Test_loss:6.186
Epoch: 6, Train_acc:70.6%, Train_loss:6.206, Test_acc:75.3%, Test_loss:6.146
Epoch: 7, Train_acc:64.4%, Train_loss:6.268, Test_acc:60.4%, Test_loss:6.312
Epoch: 8, Train_acc:67.6%, Train_loss:6.236, Test_acc:76.0%, Test_loss:6.147
Epoch: 9, Train_acc:67.2%, Train_loss:6.237, Test_acc:68.1%, Test_loss:6.223
Epoch:10, Train_acc:67.3%, Train_loss:6.237, Test_acc:76.7%, Test_loss:6.150
Done

四、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()

总结：

本周主要学习了Inception V1，通过理论学习了解了模型相关的运算以及推导，并通过实践更加深入地了解了模型的结构。