第J3-1周：DenseNet算法 实现乳腺癌识别（pytorch）
>- **🍨 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]**
🏡 我的环境：
- 语言环境：Python3.8
- 编译器：Jupyter Notebook
- 深度学习环境：Pytorch
-
- torch==2.3.1+cu118
-
- torchvision==0.18.1+cu118
DenseNet算法已在前面的 第J3周：DenseNet算法实战与解析（pytorch版）和 第J3周：DenseNet算法实战与解析（TensorFlow版）中进行了介绍，本文不在一一赘述，仅就本项目的内容进行简单叙述。
一、前言
今天，我们将一起探索一下深度学习在医学领域的应用。乳腺癌是女性最常见的癌症形式，浸润性导管癌（IDC）是最常见的乳腺癌形式。准确识别和分类乳腺癌亚型是一项重要的临床任务，利用深度学习方法识别可以有效节省时间并减少错误。我们的数据集是由多张以40倍扫描的乳腺癌（BCa）标本的完整载玻片图像组成。
二、 前期准备
1. 设置GPU
如果设备上支持GPU就使用GPU,否则使用CPU
import warnings
warnings.filterwarnings("ignore")import torch
device=torch.device("cuda" if torch.cuda.is_available() else "CPU")
device运行结果：
device(type='cuda')2. 导入数据
并查看数据集中图片数量
import pathlibdata_dir=r'D:\THE MNIST DATABASE\J-series\J3-data'
data_dir=pathlib.Path(data_dir)image_count=len(list(data_dir.glob('*/*')))
print("图片总数为：",image_count)运行结果：
图片总数为： 134033. 查看数据集分类
data_paths=list(data_dir.glob('*'))
classNames=[str(path).split("\\")[4] for path in data_paths]
classNames运行结果：
['正常细胞', '癌细胞']4. 随机查看图片
随机抽取数据集中的10张图片进行查看
import PIL,random
import matplotlib.pyplot as plt
from PIL import Image
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data_paths2=list(data_dir.glob('*/*'))
plt.figure(figsize=(10,4))
for i in range(10):plt.subplot(2,5,i+1)#plt.suptitle("OreoCC的案例",fontsize=15)plt.axis("off")image=random.choice(data_paths2) #随机选择一个图片plt.title(image.parts[-2]) #通过glob对象取出他的文件夹名称，即分类名plt.imshow(Image.open(str(image))) #显示图片运行结果：
5. 图片预处理
import torchvision.transforms as transforms
from torchvision import transforms,datasetstrain_transforms=transforms.Compose([transforms.Resize([224,224]), #将图片统一尺寸transforms.RandomHorizontalFlip(), #将图片随机水平翻转transforms.RandomRotation(0.2), #将图片按照0.2的弧度值随机旋转transforms.ToTensor(), #将图片转换为tensortransforms.Normalize( #标准化处理-->转换为正态分布，使模型更容易收敛mean=[0.485,0.456,0.406],std=[0.229,0.224,0.225])
])total_data=datasets.ImageFolder(r'D:\THE MNIST DATABASE\J-series\J3-data',transform=train_transforms
)
total_data运行结果：
Dataset ImageFolderNumber of datapoints: 13403Root location: D:\THE MNIST DATABASE\J-series\J3-dataStandardTransform
Transform: Compose(Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=True)RandomHorizontalFlip(p=0.5)RandomRotation(degrees=[-0.2, 0.2], interpolation=nearest, expand=False, fill=0)ToTensor()Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]))将数据集分类情况进行映射输出：
total_data.class_to_idx运行结果：
{'正常细胞': 0, '癌细胞': 1}6. 划分数据集
train_size=int(0.8*len(total_data))
test_size=len(total_data)-train_sizetrain_dataset,test_dataset=torch.utils.data.random_split(total_data,[train_size,test_size]
)
train_dataset,test_dataset运行结果：
(<torch.utils.data.dataset.Subset at 0x256e37f7990>,<torch.utils.data.dataset.Subset at 0x256e37f78d0>)查看训练集和测试集的数据数量：
train_size,test_size运行结果：
(10722, 2681)7. 加载数据集
batch_size=16
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
)查看测试集的情况：
for x,y in train_dl:print("Shape of x [N,C,H,W]:",x.shape)print("Shape of y:",y.shape,y.dtype)break运行结果：
Shape of x [N,C,H,W]: torch.Size([16, 3, 224, 224])
Shape of y: torch.Size([16]) torch.int64三、使用Pytorch实现DenseNet121
1. 搭建模型
import torch.nn as nn
import torch.nn.functional as Fclass DenseLayer(nn.Sequential):def __init__(self,in_channel,growth_rate,bn_size,drop_rate):super(DenseLayer,self).__init__()self.add_module('norm1',nn.BatchNorm2d(in_channel))self.add_module('relu1',nn.ReLU(inplace=True))self.add_module('conv1',nn.Conv2d(in_channel,bn_size*growth_rate,kernel_size=1,stride=1,bias=False))self.add_module('norm2',nn.BatchNorm2d(bn_size*growth_rate))self.add_module('relu2',nn.ReLU(inplace=True))self.add_module('conv2',nn.Conv2d(bn_size*growth_rate,growth_rate,kernel_size=3,stride=1,padding=1,bias=False))self.drop_rate=drop_ratedef forward(self,x):new_feature=super(DenseLayer,self).forward(x)if self.drop_rate>0:new_feature=F.drop_rate(new_feature,p=self.drop_rate,training=self.training)return torch.cat([x,new_feature],1)据此，实现DenseBlock模块，内部是密集连接方式（输入特征数线性增长）：
"""DenseBlock"""
class DenseBlock(nn.Sequential):def __init__(self,num_layers,in_channel,bn_size,growth_rate,drop_rate):super(DenseBlock,self).__init__()for i in range(num_layers):layer=DenseLayer(in_channel+i*growth_rate,growth_rate,bn_size,drop_rate)self.add_module('denselayer%d'%(i+1),layer)此外，我们实现Transition层，它主要是一个卷积层和一个池化层：
"""Transition layer between two adjacent DenseBlock"""
class Transition(nn.Sequential):def __init__(self,in_channel,out_channel):super(Transition,self).__init__()self.add_module('norm',nn.BatchNorm2d(in_channel))self.add_module('relu',nn.ReLU(inplace=True))self.add_module('conv',nn.Conv2d(in_channel,out_channel,kernel_size=1,stride=1,bias=False))self.add_module('pool',nn.AvgPool2d(2,stride=2))最后我们实现DenseNet网络：
from collections import OrderedDictclass DenseNet(nn.Module):def __init__(self,growth_rate=32,block_config=(6,12,24,16),init_channel=64,bn_size=4,compression_rate=0.5,drop_rate=0,num_classes=1000):super(DenseNet,self).__init__()#first Conv2dself.features=nn.Sequential(OrderedDict([('conv0',nn.Conv2d(3,init_channel,kernel_size=7,stride=2,padding=3,bias=False)),('norm0',nn.BatchNorm2d(init_channel)),('relu0',nn.ReLU(inplace=True)),('pool0',nn.MaxPool2d(3,stride=2,padding=1))]))#DenseBlocknum_features=init_channelfor i,num_layers in enumerate(block_config):block=DenseBlock(num_layers,num_features,bn_size,growth_rate,drop_rate)self.features.add_module('denseblock%d' % (i+1),block)num_features+=num_layers*growth_rateif i!=len(block_config)-1: transition=Transition(num_features,int(num_features*compression_rate))self.features.add_module('transition%d' % (i+1),transition)num_features=int(num_features*compression_rate)#final BN+ReLUself.features.add_module('norm5',nn.BatchNorm2d(num_features))self.features.add_module('relu5',nn.ReLU(inplace=True))#分类层self.classifier=nn.Linear(num_features,num_classes)#参数初始化for m in self.modules():if isinstance(m,nn.Conv2d):nn.init.kaiming_normal_(m.weight)elif isinstance(m,nn.BatchNorm2d):nn.init.constant_(m.bias,0)nn.init.constant_(m.weight,1)elif isinstance(m,nn.Linear):nn.init.constant_(m.bias,0)def forward(self,x):x=self.features(x)x=F.avg_pool2d(x,7,stride=1).view(x.size(0),-1)x=self.classifier(x)return x选择不同的网络参数，就可以实现不同深度的DenseNet，这里实现DenseNet-121网络
DenseNet121=DenseNet(init_channel=64,growth_rate=32,block_config=(6,12,24,16),num_classes=len(classNames))model=DenseNet121.to(device)
model运行结果：
DenseNet((features): Sequential((conv0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)(norm0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu0): ReLU(inplace=True)(pool0): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)(denseblock1): DenseBlock((denselayer1): DenseLayer((norm1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer2): DenseLayer((norm1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(96, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer3): DenseLayer((norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer4): DenseLayer((norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer5): DenseLayer((norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer6): DenseLayer((norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)))(transition1): Transition((norm): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(pool): AvgPool2d(kernel_size=2, stride=2, padding=0))(denseblock2): DenseBlock((denselayer1): DenseLayer((norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer2): DenseLayer((norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer3): DenseLayer((norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer4): DenseLayer((norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer5): DenseLayer((norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer6): DenseLayer((norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer7): DenseLayer((norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer8): DenseLayer((norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer9): DenseLayer((norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer10): DenseLayer((norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer11): DenseLayer((norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer12): DenseLayer((norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)))(transition2): Transition((norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(pool): AvgPool2d(kernel_size=2, stride=2, padding=0))(denseblock3): DenseBlock((denselayer1): DenseLayer((norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer2): DenseLayer((norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer3): DenseLayer((norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer4): DenseLayer((norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer5): DenseLayer((norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer6): DenseLayer((norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer7): DenseLayer((norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer8): DenseLayer((norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer9): DenseLayer((norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer10): DenseLayer((norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer11): DenseLayer((norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer12): DenseLayer((norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer13): DenseLayer((norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer14): DenseLayer((norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer15): DenseLayer((norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer16): DenseLayer((norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer17): DenseLayer((norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer18): DenseLayer((norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer19): DenseLayer((norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer20): DenseLayer((norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer21): DenseLayer((norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer22): DenseLayer((norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer23): DenseLayer((norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer24): DenseLayer((norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)))(transition3): Transition((norm): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(pool): AvgPool2d(kernel_size=2, stride=2, padding=0))(denseblock4): DenseBlock((denselayer1): DenseLayer((norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer2): DenseLayer((norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer3): DenseLayer((norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer4): DenseLayer((norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer5): DenseLayer((norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer6): DenseLayer((norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer7): DenseLayer((norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer8): DenseLayer((norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer9): DenseLayer((norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer10): DenseLayer((norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer11): DenseLayer((norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer12): DenseLayer((norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer13): DenseLayer((norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer14): DenseLayer((norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer15): DenseLayer((norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False))(denselayer16): DenseLayer((norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu1): ReLU(inplace=True)(conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu2): ReLU(inplace=True)(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)))(norm5): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu5): ReLU(inplace=True))(classifier): Linear(in_features=1024, out_features=2, bias=True)
)2. 查看模型详情
#打印网络结构
import torchsummary as summary
summary.summary(model,(3,224,224))运行结果：
----------------------------------------------------------------Layer (type) Output Shape Param #
================================================================Conv2d-1 [-1, 64, 112, 112] 9,408BatchNorm2d-2 [-1, 64, 112, 112] 128ReLU-3 [-1, 64, 112, 112] 0MaxPool2d-4 [-1, 64, 56, 56] 0BatchNorm2d-5 [-1, 64, 56, 56] 128ReLU-6 [-1, 64, 56, 56] 0Conv2d-7 [-1, 128, 56, 56] 8,192BatchNorm2d-8 [-1, 128, 56, 56] 256ReLU-9 [-1, 128, 56, 56] 0Conv2d-10 [-1, 32, 56, 56] 36,864BatchNorm2d-11 [-1, 96, 56, 56] 192ReLU-12 [-1, 96, 56, 56] 0Conv2d-13 [-1, 128, 56, 56] 12,288BatchNorm2d-14 [-1, 128, 56, 56] 256ReLU-15 [-1, 128, 56, 56] 0Conv2d-16 [-1, 32, 56, 56] 36,864BatchNorm2d-17 [-1, 128, 56, 56] 256ReLU-18 [-1, 128, 56, 56] 0Conv2d-19 [-1, 128, 56, 56] 16,384BatchNorm2d-20 [-1, 128, 56, 56] 256ReLU-21 [-1, 128, 56, 56] 0Conv2d-22 [-1, 32, 56, 56] 36,864BatchNorm2d-23 [-1, 160, 56, 56] 320ReLU-24 [-1, 160, 56, 56] 0Conv2d-25 [-1, 128, 56, 56] 20,480BatchNorm2d-26 [-1, 128, 56, 56] 256ReLU-27 [-1, 128, 56, 56] 0Conv2d-28 [-1, 32, 56, 56] 36,864BatchNorm2d-29 [-1, 192, 56, 56] 384ReLU-30 [-1, 192, 56, 56] 0Conv2d-31 [-1, 128, 56, 56] 24,576BatchNorm2d-32 [-1, 128, 56, 56] 256ReLU-33 [-1, 128, 56, 56] 0Conv2d-34 [-1, 32, 56, 56] 36,864BatchNorm2d-35 [-1, 224, 56, 56] 448ReLU-36 [-1, 224, 56, 56] 0Conv2d-37 [-1, 128, 56, 56] 28,672BatchNorm2d-38 [-1, 128, 56, 56] 256ReLU-39 [-1, 128, 56, 56] 0Conv2d-40 [-1, 32, 56, 56] 36,864BatchNorm2d-41 [-1, 256, 56, 56] 512ReLU-42 [-1, 256, 56, 56] 0Conv2d-43 [-1, 128, 56, 56] 32,768AvgPool2d-44 [-1, 128, 28, 28] 0BatchNorm2d-45 [-1, 128, 28, 28] 256ReLU-46 [-1, 128, 28, 28] 0Conv2d-47 [-1, 128, 28, 28] 16,384BatchNorm2d-48 [-1, 128, 28, 28] 256ReLU-49 [-1, 128, 28, 28] 0Conv2d-50 [-1, 32, 28, 28] 36,864BatchNorm2d-51 [-1, 160, 28, 28] 320ReLU-52 [-1, 160, 28, 28] 0Conv2d-53 [-1, 128, 28, 28] 20,480BatchNorm2d-54 [-1, 128, 28, 28] 256ReLU-55 [-1, 128, 28, 28] 0Conv2d-56 [-1, 32, 28, 28] 36,864BatchNorm2d-57 [-1, 192, 28, 28] 384ReLU-58 [-1, 192, 28, 28] 0Conv2d-59 [-1, 128, 28, 28] 24,576BatchNorm2d-60 [-1, 128, 28, 28] 256ReLU-61 [-1, 128, 28, 28] 0Conv2d-62 [-1, 32, 28, 28] 36,864BatchNorm2d-63 [-1, 224, 28, 28] 448ReLU-64 [-1, 224, 28, 28] 0Conv2d-65 [-1, 128, 28, 28] 28,672BatchNorm2d-66 [-1, 128, 28, 28] 256ReLU-67 [-1, 128, 28, 28] 0Conv2d-68 [-1, 32, 28, 28] 36,864BatchNorm2d-69 [-1, 256, 28, 28] 512ReLU-70 [-1, 256, 28, 28] 0Conv2d-71 [-1, 128, 28, 28] 32,768BatchNorm2d-72 [-1, 128, 28, 28] 256ReLU-73 [-1, 128, 28, 28] 0Conv2d-74 [-1, 32, 28, 28] 36,864BatchNorm2d-75 [-1, 288, 28, 28] 576ReLU-76 [-1, 288, 28, 28] 0Conv2d-77 [-1, 128, 28, 28] 36,864BatchNorm2d-78 [-1, 128, 28, 28] 256ReLU-79 [-1, 128, 28, 28] 0Conv2d-80 [-1, 32, 28, 28] 36,864BatchNorm2d-81 [-1, 320, 28, 28] 640ReLU-82 [-1, 320, 28, 28] 0Conv2d-83 [-1, 128, 28, 28] 40,960BatchNorm2d-84 [-1, 128, 28, 28] 256ReLU-85 [-1, 128, 28, 28] 0Conv2d-86 [-1, 32, 28, 28] 36,864BatchNorm2d-87 [-1, 352, 28, 28] 704ReLU-88 [-1, 352, 28, 28] 0Conv2d-89 [-1, 128, 28, 28] 45,056BatchNorm2d-90 [-1, 128, 28, 28] 256ReLU-91 [-1, 128, 28, 28] 0Conv2d-92 [-1, 32, 28, 28] 36,864BatchNorm2d-93 [-1, 384, 28, 28] 768ReLU-94 [-1, 384, 28, 28] 0Conv2d-95 [-1, 128, 28, 28] 49,152BatchNorm2d-96 [-1, 128, 28, 28] 256ReLU-97 [-1, 128, 28, 28] 0Conv2d-98 [-1, 32, 28, 28] 36,864BatchNorm2d-99 [-1, 416, 28, 28] 832ReLU-100 [-1, 416, 28, 28] 0Conv2d-101 [-1, 128, 28, 28] 53,248BatchNorm2d-102 [-1, 128, 28, 28] 256ReLU-103 [-1, 128, 28, 28] 0Conv2d-104 [-1, 32, 28, 28] 36,864BatchNorm2d-105 [-1, 448, 28, 28] 896ReLU-106 [-1, 448, 28, 28] 0Conv2d-107 [-1, 128, 28, 28] 57,344BatchNorm2d-108 [-1, 128, 28, 28] 256ReLU-109 [-1, 128, 28, 28] 0Conv2d-110 [-1, 32, 28, 28] 36,864BatchNorm2d-111 [-1, 480, 28, 28] 960ReLU-112 [-1, 480, 28, 28] 0Conv2d-113 [-1, 128, 28, 28] 61,440BatchNorm2d-114 [-1, 128, 28, 28] 256ReLU-115 [-1, 128, 28, 28] 0Conv2d-116 [-1, 32, 28, 28] 36,864BatchNorm2d-117 [-1, 512, 28, 28] 1,024ReLU-118 [-1, 512, 28, 28] 0Conv2d-119 [-1, 256, 28, 28] 131,072AvgPool2d-120 [-1, 256, 14, 14] 0BatchNorm2d-121 [-1, 256, 14, 14] 512ReLU-122 [-1, 256, 14, 14] 0Conv2d-123 [-1, 128, 14, 14] 32,768BatchNorm2d-124 [-1, 128, 14, 14] 256ReLU-125 [-1, 128, 14, 14] 0Conv2d-126 [-1, 32, 14, 14] 36,864BatchNorm2d-127 [-1, 288, 14, 14] 576ReLU-128 [-1, 288, 14, 14] 0Conv2d-129 [-1, 128, 14, 14] 36,864BatchNorm2d-130 [-1, 128, 14, 14] 256ReLU-131 [-1, 128, 14, 14] 0Conv2d-132 [-1, 32, 14, 14] 36,864BatchNorm2d-133 [-1, 320, 14, 14] 640ReLU-134 [-1, 320, 14, 14] 0Conv2d-135 [-1, 128, 14, 14] 40,960BatchNorm2d-136 [-1, 128, 14, 14] 256ReLU-137 [-1, 128, 14, 14] 0Conv2d-138 [-1, 32, 14, 14] 36,864BatchNorm2d-139 [-1, 352, 14, 14] 704ReLU-140 [-1, 352, 14, 14] 0Conv2d-141 [-1, 128, 14, 14] 45,056BatchNorm2d-142 [-1, 128, 14, 14] 256ReLU-143 [-1, 128, 14, 14] 0Conv2d-144 [-1, 32, 14, 14] 36,864BatchNorm2d-145 [-1, 384, 14, 14] 768ReLU-146 [-1, 384, 14, 14] 0Conv2d-147 [-1, 128, 14, 14] 49,152BatchNorm2d-148 [-1, 128, 14, 14] 256ReLU-149 [-1, 128, 14, 14] 0Conv2d-150 [-1, 32, 14, 14] 36,864BatchNorm2d-151 [-1, 416, 14, 14] 832ReLU-152 [-1, 416, 14, 14] 0Conv2d-153 [-1, 128, 14, 14] 53,248BatchNorm2d-154 [-1, 128, 14, 14] 256ReLU-155 [-1, 128, 14, 14] 0Conv2d-156 [-1, 32, 14, 14] 36,864BatchNorm2d-157 [-1, 448, 14, 14] 896ReLU-158 [-1, 448, 14, 14] 0Conv2d-159 [-1, 128, 14, 14] 57,344BatchNorm2d-160 [-1, 128, 14, 14] 256ReLU-161 [-1, 128, 14, 14] 0Conv2d-162 [-1, 32, 14, 14] 36,864BatchNorm2d-163 [-1, 480, 14, 14] 960ReLU-164 [-1, 480, 14, 14] 0Conv2d-165 [-1, 128, 14, 14] 61,440BatchNorm2d-166 [-1, 128, 14, 14] 256ReLU-167 [-1, 128, 14, 14] 0Conv2d-168 [-1, 32, 14, 14] 36,864BatchNorm2d-169 [-1, 512, 14, 14] 1,024ReLU-170 [-1, 512, 14, 14] 0Conv2d-171 [-1, 128, 14, 14] 65,536BatchNorm2d-172 [-1, 128, 14, 14] 256ReLU-173 [-1, 128, 14, 14] 0Conv2d-174 [-1, 32, 14, 14] 36,864BatchNorm2d-175 [-1, 544, 14, 14] 1,088ReLU-176 [-1, 544, 14, 14] 0Conv2d-177 [-1, 128, 14, 14] 69,632BatchNorm2d-178 [-1, 128, 14, 14] 256ReLU-179 [-1, 128, 14, 14] 0Conv2d-180 [-1, 32, 14, 14] 36,864BatchNorm2d-181 [-1, 576, 14, 14] 1,152ReLU-182 [-1, 576, 14, 14] 0Conv2d-183 [-1, 128, 14, 14] 73,728BatchNorm2d-184 [-1, 128, 14, 14] 256ReLU-185 [-1, 128, 14, 14] 0Conv2d-186 [-1, 32, 14, 14] 36,864BatchNorm2d-187 [-1, 608, 14, 14] 1,216ReLU-188 [-1, 608, 14, 14] 0Conv2d-189 [-1, 128, 14, 14] 77,824BatchNorm2d-190 [-1, 128, 14, 14] 256ReLU-191 [-1, 128, 14, 14] 0Conv2d-192 [-1, 32, 14, 14] 36,864BatchNorm2d-193 [-1, 640, 14, 14] 1,280ReLU-194 [-1, 640, 14, 14] 0Conv2d-195 [-1, 128, 14, 14] 81,920BatchNorm2d-196 [-1, 128, 14, 14] 256ReLU-197 [-1, 128, 14, 14] 0Conv2d-198 [-1, 32, 14, 14] 36,864BatchNorm2d-199 [-1, 672, 14, 14] 1,344ReLU-200 [-1, 672, 14, 14] 0Conv2d-201 [-1, 128, 14, 14] 86,016BatchNorm2d-202 [-1, 128, 14, 14] 256ReLU-203 [-1, 128, 14, 14] 0Conv2d-204 [-1, 32, 14, 14] 36,864BatchNorm2d-205 [-1, 704, 14, 14] 1,408ReLU-206 [-1, 704, 14, 14] 0Conv2d-207 [-1, 128, 14, 14] 90,112BatchNorm2d-208 [-1, 128, 14, 14] 256ReLU-209 [-1, 128, 14, 14] 0Conv2d-210 [-1, 32, 14, 14] 36,864BatchNorm2d-211 [-1, 736, 14, 14] 1,472ReLU-212 [-1, 736, 14, 14] 0Conv2d-213 [-1, 128, 14, 14] 94,208BatchNorm2d-214 [-1, 128, 14, 14] 256ReLU-215 [-1, 128, 14, 14] 0Conv2d-216 [-1, 32, 14, 14] 36,864BatchNorm2d-217 [-1, 768, 14, 14] 1,536ReLU-218 [-1, 768, 14, 14] 0Conv2d-219 [-1, 128, 14, 14] 98,304BatchNorm2d-220 [-1, 128, 14, 14] 256ReLU-221 [-1, 128, 14, 14] 0Conv2d-222 [-1, 32, 14, 14] 36,864BatchNorm2d-223 [-1, 800, 14, 14] 1,600ReLU-224 [-1, 800, 14, 14] 0Conv2d-225 [-1, 128, 14, 14] 102,400BatchNorm2d-226 [-1, 128, 14, 14] 256ReLU-227 [-1, 128, 14, 14] 0Conv2d-228 [-1, 32, 14, 14] 36,864BatchNorm2d-229 [-1, 832, 14, 14] 1,664ReLU-230 [-1, 832, 14, 14] 0Conv2d-231 [-1, 128, 14, 14] 106,496BatchNorm2d-232 [-1, 128, 14, 14] 256ReLU-233 [-1, 128, 14, 14] 0Conv2d-234 [-1, 32, 14, 14] 36,864BatchNorm2d-235 [-1, 864, 14, 14] 1,728ReLU-236 [-1, 864, 14, 14] 0Conv2d-237 [-1, 128, 14, 14] 110,592BatchNorm2d-238 [-1, 128, 14, 14] 256ReLU-239 [-1, 128, 14, 14] 0Conv2d-240 [-1, 32, 14, 14] 36,864BatchNorm2d-241 [-1, 896, 14, 14] 1,792ReLU-242 [-1, 896, 14, 14] 0Conv2d-243 [-1, 128, 14, 14] 114,688BatchNorm2d-244 [-1, 128, 14, 14] 256ReLU-245 [-1, 128, 14, 14] 0Conv2d-246 [-1, 32, 14, 14] 36,864BatchNorm2d-247 [-1, 928, 14, 14] 1,856ReLU-248 [-1, 928, 14, 14] 0Conv2d-249 [-1, 128, 14, 14] 118,784BatchNorm2d-250 [-1, 128, 14, 14] 256ReLU-251 [-1, 128, 14, 14] 0Conv2d-252 [-1, 32, 14, 14] 36,864BatchNorm2d-253 [-1, 960, 14, 14] 1,920ReLU-254 [-1, 960, 14, 14] 0Conv2d-255 [-1, 128, 14, 14] 122,880BatchNorm2d-256 [-1, 128, 14, 14] 256ReLU-257 [-1, 128, 14, 14] 0Conv2d-258 [-1, 32, 14, 14] 36,864BatchNorm2d-259 [-1, 992, 14, 14] 1,984ReLU-260 [-1, 992, 14, 14] 0Conv2d-261 [-1, 128, 14, 14] 126,976BatchNorm2d-262 [-1, 128, 14, 14] 256ReLU-263 [-1, 128, 14, 14] 0Conv2d-264 [-1, 32, 14, 14] 36,864BatchNorm2d-265 [-1, 1024, 14, 14] 2,048ReLU-266 [-1, 1024, 14, 14] 0Conv2d-267 [-1, 512, 14, 14] 524,288AvgPool2d-268 [-1, 512, 7, 7] 0BatchNorm2d-269 [-1, 512, 7, 7] 1,024ReLU-270 [-1, 512, 7, 7] 0Conv2d-271 [-1, 128, 7, 7] 65,536BatchNorm2d-272 [-1, 128, 7, 7] 256ReLU-273 [-1, 128, 7, 7] 0Conv2d-274 [-1, 32, 7, 7] 36,864BatchNorm2d-275 [-1, 544, 7, 7] 1,088ReLU-276 [-1, 544, 7, 7] 0Conv2d-277 [-1, 128, 7, 7] 69,632BatchNorm2d-278 [-1, 128, 7, 7] 256ReLU-279 [-1, 128, 7, 7] 0Conv2d-280 [-1, 32, 7, 7] 36,864BatchNorm2d-281 [-1, 576, 7, 7] 1,152ReLU-282 [-1, 576, 7, 7] 0Conv2d-283 [-1, 128, 7, 7] 73,728BatchNorm2d-284 [-1, 128, 7, 7] 256ReLU-285 [-1, 128, 7, 7] 0Conv2d-286 [-1, 32, 7, 7] 36,864BatchNorm2d-287 [-1, 608, 7, 7] 1,216ReLU-288 [-1, 608, 7, 7] 0Conv2d-289 [-1, 128, 7, 7] 77,824BatchNorm2d-290 [-1, 128, 7, 7] 256ReLU-291 [-1, 128, 7, 7] 0Conv2d-292 [-1, 32, 7, 7] 36,864BatchNorm2d-293 [-1, 640, 7, 7] 1,280ReLU-294 [-1, 640, 7, 7] 0Conv2d-295 [-1, 128, 7, 7] 81,920BatchNorm2d-296 [-1, 128, 7, 7] 256ReLU-297 [-1, 128, 7, 7] 0Conv2d-298 [-1, 32, 7, 7] 36,864BatchNorm2d-299 [-1, 672, 7, 7] 1,344ReLU-300 [-1, 672, 7, 7] 0Conv2d-301 [-1, 128, 7, 7] 86,016BatchNorm2d-302 [-1, 128, 7, 7] 256ReLU-303 [-1, 128, 7, 7] 0Conv2d-304 [-1, 32, 7, 7] 36,864BatchNorm2d-305 [-1, 704, 7, 7] 1,408ReLU-306 [-1, 704, 7, 7] 0Conv2d-307 [-1, 128, 7, 7] 90,112BatchNorm2d-308 [-1, 128, 7, 7] 256ReLU-309 [-1, 128, 7, 7] 0Conv2d-310 [-1, 32, 7, 7] 36,864BatchNorm2d-311 [-1, 736, 7, 7] 1,472ReLU-312 [-1, 736, 7, 7] 0Conv2d-313 [-1, 128, 7, 7] 94,208BatchNorm2d-314 [-1, 128, 7, 7] 256ReLU-315 [-1, 128, 7, 7] 0Conv2d-316 [-1, 32, 7, 7] 36,864BatchNorm2d-317 [-1, 768, 7, 7] 1,536ReLU-318 [-1, 768, 7, 7] 0Conv2d-319 [-1, 128, 7, 7] 98,304BatchNorm2d-320 [-1, 128, 7, 7] 256ReLU-321 [-1, 128, 7, 7] 0Conv2d-322 [-1, 32, 7, 7] 36,864BatchNorm2d-323 [-1, 800, 7, 7] 1,600ReLU-324 [-1, 800, 7, 7] 0Conv2d-325 [-1, 128, 7, 7] 102,400BatchNorm2d-326 [-1, 128, 7, 7] 256ReLU-327 [-1, 128, 7, 7] 0Conv2d-328 [-1, 32, 7, 7] 36,864BatchNorm2d-329 [-1, 832, 7, 7] 1,664ReLU-330 [-1, 832, 7, 7] 0Conv2d-331 [-1, 128, 7, 7] 106,496BatchNorm2d-332 [-1, 128, 7, 7] 256ReLU-333 [-1, 128, 7, 7] 0Conv2d-334 [-1, 32, 7, 7] 36,864BatchNorm2d-335 [-1, 864, 7, 7] 1,728ReLU-336 [-1, 864, 7, 7] 0Conv2d-337 [-1, 128, 7, 7] 110,592BatchNorm2d-338 [-1, 128, 7, 7] 256ReLU-339 [-1, 128, 7, 7] 0Conv2d-340 [-1, 32, 7, 7] 36,864BatchNorm2d-341 [-1, 896, 7, 7] 1,792ReLU-342 [-1, 896, 7, 7] 0Conv2d-343 [-1, 128, 7, 7] 114,688BatchNorm2d-344 [-1, 128, 7, 7] 256ReLU-345 [-1, 128, 7, 7] 0Conv2d-346 [-1, 32, 7, 7] 36,864BatchNorm2d-347 [-1, 928, 7, 7] 1,856ReLU-348 [-1, 928, 7, 7] 0Conv2d-349 [-1, 128, 7, 7] 118,784BatchNorm2d-350 [-1, 128, 7, 7] 256ReLU-351 [-1, 128, 7, 7] 0Conv2d-352 [-1, 32, 7, 7] 36,864BatchNorm2d-353 [-1, 960, 7, 7] 1,920ReLU-354 [-1, 960, 7, 7] 0Conv2d-355 [-1, 128, 7, 7] 122,880BatchNorm2d-356 [-1, 128, 7, 7] 256ReLU-357 [-1, 128, 7, 7] 0Conv2d-358 [-1, 32, 7, 7] 36,864BatchNorm2d-359 [-1, 992, 7, 7] 1,984ReLU-360 [-1, 992, 7, 7] 0Conv2d-361 [-1, 128, 7, 7] 126,976BatchNorm2d-362 [-1, 128, 7, 7] 256ReLU-363 [-1, 128, 7, 7] 0Conv2d-364 [-1, 32, 7, 7] 36,864BatchNorm2d-365 [-1, 1024, 7, 7] 2,048ReLU-366 [-1, 1024, 7, 7] 0Linear-367 [-1, 2] 2,050
================================================================
Total params: 6,955,906
Trainable params: 6,955,906
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 294.57
Params size (MB): 26.53
Estimated Total Size (MB): 321.68
----------------------------------------------------------------三、训练模型
1. 编写训练函数
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，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losstrain_acc+=(pred.argmax(1)==y).type(torch.float).sum().item()train_loss+=loss.item()train_acc/=sizetrain_loss/=num_batchesreturn train_acc,train_loss2. 编写测试函数
测试函数和训练函数大致相同，但是由于不进行梯度下降对网络权重进行更新，所以不需要传入优化器
#测试函数
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_loss3. 正式训练
import copy
opt=torch.optim.Adam(model.parameters(),lr=1e-7) #创建优化器，并设置学习率
loss_fn=nn.CrossEntropyLoss() #创建损失函数epochs=20train_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):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)#保存最佳模型到J3_modelif epoch_test_acc>best_acc:best_acc=epoch_test_accJ3_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)#获取当前学习率lr=opt.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'D:\THE MNIST DATABASE\J-series\J3_1_model.pth'
torch.save(model.state_dict(),PATH)
print("Done")运行结果：
Epoch: 1,Train_acc:50.9%,Train_loss:0.726,Test_acc:54.9%,Test_loss:0.699,Lr:1.00E-07
Epoch: 2,Train_acc:55.9%,Train_loss:0.686,Test_acc:63.8%,Test_loss:0.655,Lr:1.00E-07
Epoch: 3,Train_acc:62.2%,Train_loss:0.651,Test_acc:69.9%,Test_loss:0.613,Lr:1.00E-07
Epoch: 4,Train_acc:65.8%,Train_loss:0.621,Test_acc:72.2%,Test_loss:0.580,Lr:1.00E-07
Epoch: 5,Train_acc:68.4%,Train_loss:0.596,Test_acc:74.0%,Test_loss:0.557,Lr:1.00E-07
Epoch: 6,Train_acc:71.7%,Train_loss:0.573,Test_acc:78.0%,Test_loss:0.532,Lr:1.00E-07
Epoch: 7,Train_acc:74.5%,Train_loss:0.552,Test_acc:80.3%,Test_loss:0.512,Lr:1.00E-07
Epoch: 8,Train_acc:76.6%,Train_loss:0.535,Test_acc:80.9%,Test_loss:0.501,Lr:1.00E-07
Epoch: 9,Train_acc:78.2%,Train_loss:0.519,Test_acc:82.1%,Test_loss:0.472,Lr:1.00E-07
Epoch:10,Train_acc:79.3%,Train_loss:0.506,Test_acc:81.8%,Test_loss:0.477,Lr:1.00E-07
Epoch:11,Train_acc:79.6%,Train_loss:0.493,Test_acc:82.5%,Test_loss:0.453,Lr:1.00E-07
Epoch:12,Train_acc:80.2%,Train_loss:0.482,Test_acc:82.3%,Test_loss:0.443,Lr:1.00E-07
Epoch:13,Train_acc:80.8%,Train_loss:0.470,Test_acc:82.5%,Test_loss:0.425,Lr:1.00E-07
Epoch:14,Train_acc:80.7%,Train_loss:0.461,Test_acc:82.6%,Test_loss:0.428,Lr:1.00E-07
Epoch:15,Train_acc:80.9%,Train_loss:0.457,Test_acc:82.8%,Test_loss:0.418,Lr:1.00E-07
Epoch:16,Train_acc:81.2%,Train_loss:0.445,Test_acc:82.6%,Test_loss:0.413,Lr:1.00E-07
Epoch:17,Train_acc:81.6%,Train_loss:0.441,Test_acc:82.7%,Test_loss:0.401,Lr:1.00E-07
Epoch:18,Train_acc:81.2%,Train_loss:0.434,Test_acc:83.0%,Test_loss:0.396,Lr:1.00E-07
Epoch:19,Train_acc:81.5%,Train_loss:0.427,Test_acc:82.9%,Test_loss:0.396,Lr:1.00E-07
Epoch:20,Train_acc:81.7%,Train_loss:0.425,Test_acc:83.2%,Test_loss:0.394,Lr:1.00E-07
Done八、 结果可视化
1. Loss与Accuracy图
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'] #正常显示中文标签
plt.rcParams['axes.unicode_minus']=False #正常显示负号
plt.rcParams['figure.dpi']=300 #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()运行结果：
2. 指定图片进行预测
from PIL import Imageclasses=list(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}')预测图片：
#预测训练集中的某张照片
predict_one_image(image_path=r'D:\THE MNIST DATABASE\J-series\J3-data\癌细胞\8863_idx5_x1101_y1551_class1.png',model=model,transform=train_transforms,classes=classes)运行结果：
预测结果是：癌细胞
九、心得体会
在本次项目训练中，着实耗费了我很久的时间，因为模型结果过拟合现象十分严重，且因为数据集较大，每次跑模型的时间较长，我整日都在不断地调整batch_size、lr和weight_decay，最终，我删除了weight_decay，因为它的存在老是使得结果波动较大，得到了稍微平滑好一点的结果，具体原因不得而知。