深度学习Day-20:DenseNet算法实战 乳腺癌识别

 🍨 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 | 接辅导、项目定制]

一、 基础配置

  • 语言环境:Python3.8
  • 编译器选择:Pycharm
  • 深度学习环境:
    • torch==1.12.1+cu113
    • torchvision==0.13.1+cu113

二、 前期准备 

1.设置GPU

import torch
import torch.nn as nn
from torchvision import transforms,datasets
import pathlib,warningswarnings.filterwarnings("ignore")device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

2. 导入数据

本项目所采用的数据集未收录于公开数据中,故需要自己在文件目录中导入相应数据集合,并设置对应文件目录,以供后续学习过程中使用。

运行下述代码:

data_dir = "./data/J3-data"
data_dir = pathlib.Path(data_dir)data_path = list(data_dir.glob('*'))
classNames = [str(path).split('\\')[2] for path in data_path]
print(classNames)

得到如下输出:

['0', '1']

接下来,我们通过transforms.Compose对整个数据集进行预处理:

train_transforms = transforms.Compose([transforms.Resize([224, 224]),      # 将输入图片resize成统一尺寸# transforms.RandomHorizontalFlip(), # 随机水平翻转transforms.ToTensor(),              # 将PIL Image或numpy.ndarray转换为tensor,并归一化到[0,1]之间transforms.Normalize(               # 标准化处理-->转换为标准正太分布(高斯分布),使模型更容易收敛mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225])      # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])total_dataset = datasets.ImageFolder(data_dir,transform=transforms)
print(total_dataset.class_to_idx)

得到如下输出:

{'0': 0, '1': 1}

3. 划分数据集

 此处数据集需要做按比例划分的操作:

train_size = int(0.8*len(total_dataset))
test_size = len(total_dataset) - train_size
train_dataset,test_dataset = torch.utils.data.random_split(total_dataset,[train_size,test_size])

接下来,根据划分得到的训练集和验证集对数据集进行包装:

batch_size = 32train_dl = torch.utils.data.DataLoader(train_dataset,batch_size = batch_size,shuffle = True,num_workers = 0)test_dl = torch.utils.data.DataLoader(test_dataset,batch_size = batch_size,shuffle = True,num_workers = 0)

并通过:

for X,y in test_dl:print('Shape of X:',X.shape)print('shape of y:',y.shape,y.dtype)break

输出测试数据集的数据分布情况:

Shape of X: torch.Size([32, 3, 224, 224])
shape of y: torch.Size([32]) torch.int64

4.搭建模型

首先,导入搭建模型所依赖的库用于后续模型的搭建过程:

import torch.nn.functional as F
from collections import OrderedDict

1.DenseLayer

class 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))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))self.drop_rate = drop_ratedef forward(self, x):new_feature = super(DenseLayer, self).forward(x)if self.drop_rate > 0:new_feature = F.dropout(new_feature, p=self.drop_rate, training=self.training)return torch.cat([x, new_feature], 1)

2.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)

3.Transition 

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))self.add_module('pool', nn.AvgPool2d(kernel_size=2, stride=2))

4.搭建DenseNet 

class 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__()self.features = nn.Sequential(OrderedDict([('conv0', nn.Conv2d(3, init_channel, kernel_size=7, stride=2, padding=3)),('norm0', nn.BatchNorm2d(init_channel)),('relu0', nn.ReLU(inplace=True)),('pool0', nn.MaxPool2d(kernel_size=3, stride=2, padding=1))]))num_features = init_channelfor i, num_layers in enumerate(block_config):block = DenseBlock(num_layers, num_features, bn_size=bn_size, growth_rate=growth_rate, drop_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)self.features.add_module('norm5', nn.BatchNorm2d(num_features))self.features.add_module('relu5', nn.ReLU(inplace=True))self.classifier = nn.Linear(num_features, num_classes)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

5.利用DenseNet搭建DenseNet121

densenet121 = DenseNet(init_channel=64,growth_rate=32,block_config=(6,12,24,16),num_classes=len(classNames))
model = densenet121.to(device)

2.查看模型信息

import torchsummary as summary
summary.summary(model, (3, 224, 224))

得到如下输出:

----------------------------------------------------------------Layer (type)               Output Shape         Param #
================================================================Conv2d-1         [-1, 64, 112, 112]           9,472BatchNorm2d-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]           8,320BatchNorm2d-8          [-1, 128, 56, 56]             256ReLU-9          [-1, 128, 56, 56]               0Conv2d-10           [-1, 32, 56, 56]          36,896BatchNorm2d-11           [-1, 96, 56, 56]             192ReLU-12           [-1, 96, 56, 56]               0Conv2d-13          [-1, 128, 56, 56]          12,416BatchNorm2d-14          [-1, 128, 56, 56]             256ReLU-15          [-1, 128, 56, 56]               0Conv2d-16           [-1, 32, 56, 56]          36,896BatchNorm2d-17          [-1, 128, 56, 56]             256ReLU-18          [-1, 128, 56, 56]               0Conv2d-19          [-1, 128, 56, 56]          16,512BatchNorm2d-20          [-1, 128, 56, 56]             256ReLU-21          [-1, 128, 56, 56]               0Conv2d-22           [-1, 32, 56, 56]          36,896BatchNorm2d-23          [-1, 160, 56, 56]             320ReLU-24          [-1, 160, 56, 56]               0Conv2d-25          [-1, 128, 56, 56]          20,608BatchNorm2d-26          [-1, 128, 56, 56]             256ReLU-27          [-1, 128, 56, 56]               0Conv2d-28           [-1, 32, 56, 56]          36,896BatchNorm2d-29          [-1, 192, 56, 56]             384ReLU-30          [-1, 192, 56, 56]               0Conv2d-31          [-1, 128, 56, 56]          24,704BatchNorm2d-32          [-1, 128, 56, 56]             256ReLU-33          [-1, 128, 56, 56]               0Conv2d-34           [-1, 32, 56, 56]          36,896BatchNorm2d-35          [-1, 224, 56, 56]             448ReLU-36          [-1, 224, 56, 56]               0Conv2d-37          [-1, 128, 56, 56]          28,800BatchNorm2d-38          [-1, 128, 56, 56]             256ReLU-39          [-1, 128, 56, 56]               0Conv2d-40           [-1, 32, 56, 56]          36,896BatchNorm2d-41          [-1, 256, 56, 56]             512ReLU-42          [-1, 256, 56, 56]               0Conv2d-43          [-1, 128, 56, 56]          32,896AvgPool2d-44          [-1, 128, 28, 28]               0BatchNorm2d-45          [-1, 128, 28, 28]             256ReLU-46          [-1, 128, 28, 28]               0Conv2d-47          [-1, 128, 28, 28]          16,512BatchNorm2d-48          [-1, 128, 28, 28]             256ReLU-49          [-1, 128, 28, 28]               0Conv2d-50           [-1, 32, 28, 28]          36,896BatchNorm2d-51          [-1, 160, 28, 28]             320ReLU-52          [-1, 160, 28, 28]               0Conv2d-53          [-1, 128, 28, 28]          20,608BatchNorm2d-54          [-1, 128, 28, 28]             256ReLU-55          [-1, 128, 28, 28]               0Conv2d-56           [-1, 32, 28, 28]          36,896BatchNorm2d-57          [-1, 192, 28, 28]             384ReLU-58          [-1, 192, 28, 28]               0Conv2d-59          [-1, 128, 28, 28]          24,704BatchNorm2d-60          [-1, 128, 28, 28]             256ReLU-61          [-1, 128, 28, 28]               0Conv2d-62           [-1, 32, 28, 28]          36,896BatchNorm2d-63          [-1, 224, 28, 28]             448ReLU-64          [-1, 224, 28, 28]               0Conv2d-65          [-1, 128, 28, 28]          28,800BatchNorm2d-66          [-1, 128, 28, 28]             256ReLU-67          [-1, 128, 28, 28]               0Conv2d-68           [-1, 32, 28, 28]          36,896BatchNorm2d-69          [-1, 256, 28, 28]             512ReLU-70          [-1, 256, 28, 28]               0Conv2d-71          [-1, 128, 28, 28]          32,896BatchNorm2d-72          [-1, 128, 28, 28]             256ReLU-73          [-1, 128, 28, 28]               0Conv2d-74           [-1, 32, 28, 28]          36,896BatchNorm2d-75          [-1, 288, 28, 28]             576ReLU-76          [-1, 288, 28, 28]               0Conv2d-77          [-1, 128, 28, 28]          36,992BatchNorm2d-78          [-1, 128, 28, 28]             256ReLU-79          [-1, 128, 28, 28]               0Conv2d-80           [-1, 32, 28, 28]          36,896BatchNorm2d-81          [-1, 320, 28, 28]             640ReLU-82          [-1, 320, 28, 28]               0Conv2d-83          [-1, 128, 28, 28]          41,088BatchNorm2d-84          [-1, 128, 28, 28]             256ReLU-85          [-1, 128, 28, 28]               0Conv2d-86           [-1, 32, 28, 28]          36,896BatchNorm2d-87          [-1, 352, 28, 28]             704ReLU-88          [-1, 352, 28, 28]               0Conv2d-89          [-1, 128, 28, 28]          45,184BatchNorm2d-90          [-1, 128, 28, 28]             256ReLU-91          [-1, 128, 28, 28]               0Conv2d-92           [-1, 32, 28, 28]          36,896BatchNorm2d-93          [-1, 384, 28, 28]             768ReLU-94          [-1, 384, 28, 28]               0Conv2d-95          [-1, 128, 28, 28]          49,280BatchNorm2d-96          [-1, 128, 28, 28]             256ReLU-97          [-1, 128, 28, 28]               0Conv2d-98           [-1, 32, 28, 28]          36,896BatchNorm2d-99          [-1, 416, 28, 28]             832ReLU-100          [-1, 416, 28, 28]               0Conv2d-101          [-1, 128, 28, 28]          53,376BatchNorm2d-102          [-1, 128, 28, 28]             256ReLU-103          [-1, 128, 28, 28]               0Conv2d-104           [-1, 32, 28, 28]          36,896BatchNorm2d-105          [-1, 448, 28, 28]             896ReLU-106          [-1, 448, 28, 28]               0Conv2d-107          [-1, 128, 28, 28]          57,472BatchNorm2d-108          [-1, 128, 28, 28]             256ReLU-109          [-1, 128, 28, 28]               0Conv2d-110           [-1, 32, 28, 28]          36,896BatchNorm2d-111          [-1, 480, 28, 28]             960ReLU-112          [-1, 480, 28, 28]               0Conv2d-113          [-1, 128, 28, 28]          61,568BatchNorm2d-114          [-1, 128, 28, 28]             256ReLU-115          [-1, 128, 28, 28]               0Conv2d-116           [-1, 32, 28, 28]          36,896BatchNorm2d-117          [-1, 512, 28, 28]           1,024ReLU-118          [-1, 512, 28, 28]               0Conv2d-119          [-1, 256, 28, 28]         131,328AvgPool2d-120          [-1, 256, 14, 14]               0BatchNorm2d-121          [-1, 256, 14, 14]             512ReLU-122          [-1, 256, 14, 14]               0Conv2d-123          [-1, 128, 14, 14]          32,896BatchNorm2d-124          [-1, 128, 14, 14]             256ReLU-125          [-1, 128, 14, 14]               0Conv2d-126           [-1, 32, 14, 14]          36,896BatchNorm2d-127          [-1, 288, 14, 14]             576ReLU-128          [-1, 288, 14, 14]               0Conv2d-129          [-1, 128, 14, 14]          36,992BatchNorm2d-130          [-1, 128, 14, 14]             256ReLU-131          [-1, 128, 14, 14]               0Conv2d-132           [-1, 32, 14, 14]          36,896BatchNorm2d-133          [-1, 320, 14, 14]             640ReLU-134          [-1, 320, 14, 14]               0Conv2d-135          [-1, 128, 14, 14]          41,088BatchNorm2d-136          [-1, 128, 14, 14]             256ReLU-137          [-1, 128, 14, 14]               0Conv2d-138           [-1, 32, 14, 14]          36,896BatchNorm2d-139          [-1, 352, 14, 14]             704ReLU-140          [-1, 352, 14, 14]               0Conv2d-141          [-1, 128, 14, 14]          45,184BatchNorm2d-142          [-1, 128, 14, 14]             256ReLU-143          [-1, 128, 14, 14]               0Conv2d-144           [-1, 32, 14, 14]          36,896BatchNorm2d-145          [-1, 384, 14, 14]             768ReLU-146          [-1, 384, 14, 14]               0Conv2d-147          [-1, 128, 14, 14]          49,280BatchNorm2d-148          [-1, 128, 14, 14]             256ReLU-149          [-1, 128, 14, 14]               0Conv2d-150           [-1, 32, 14, 14]          36,896BatchNorm2d-151          [-1, 416, 14, 14]             832ReLU-152          [-1, 416, 14, 14]               0Conv2d-153          [-1, 128, 14, 14]          53,376BatchNorm2d-154          [-1, 128, 14, 14]             256ReLU-155          [-1, 128, 14, 14]               0Conv2d-156           [-1, 32, 14, 14]          36,896BatchNorm2d-157          [-1, 448, 14, 14]             896ReLU-158          [-1, 448, 14, 14]               0Conv2d-159          [-1, 128, 14, 14]          57,472BatchNorm2d-160          [-1, 128, 14, 14]             256ReLU-161          [-1, 128, 14, 14]               0Conv2d-162           [-1, 32, 14, 14]          36,896BatchNorm2d-163          [-1, 480, 14, 14]             960ReLU-164          [-1, 480, 14, 14]               0Conv2d-165          [-1, 128, 14, 14]          61,568BatchNorm2d-166          [-1, 128, 14, 14]             256ReLU-167          [-1, 128, 14, 14]               0Conv2d-168           [-1, 32, 14, 14]          36,896BatchNorm2d-169          [-1, 512, 14, 14]           1,024ReLU-170          [-1, 512, 14, 14]               0Conv2d-171          [-1, 128, 14, 14]          65,664BatchNorm2d-172          [-1, 128, 14, 14]             256ReLU-173          [-1, 128, 14, 14]               0Conv2d-174           [-1, 32, 14, 14]          36,896BatchNorm2d-175          [-1, 544, 14, 14]           1,088ReLU-176          [-1, 544, 14, 14]               0Conv2d-177          [-1, 128, 14, 14]          69,760BatchNorm2d-178          [-1, 128, 14, 14]             256ReLU-179          [-1, 128, 14, 14]               0Conv2d-180           [-1, 32, 14, 14]          36,896BatchNorm2d-181          [-1, 576, 14, 14]           1,152ReLU-182          [-1, 576, 14, 14]               0Conv2d-183          [-1, 128, 14, 14]          73,856BatchNorm2d-184          [-1, 128, 14, 14]             256ReLU-185          [-1, 128, 14, 14]               0Conv2d-186           [-1, 32, 14, 14]          36,896BatchNorm2d-187          [-1, 608, 14, 14]           1,216ReLU-188          [-1, 608, 14, 14]               0Conv2d-189          [-1, 128, 14, 14]          77,952BatchNorm2d-190          [-1, 128, 14, 14]             256ReLU-191          [-1, 128, 14, 14]               0Conv2d-192           [-1, 32, 14, 14]          36,896BatchNorm2d-193          [-1, 640, 14, 14]           1,280ReLU-194          [-1, 640, 14, 14]               0Conv2d-195          [-1, 128, 14, 14]          82,048BatchNorm2d-196          [-1, 128, 14, 14]             256ReLU-197          [-1, 128, 14, 14]               0Conv2d-198           [-1, 32, 14, 14]          36,896BatchNorm2d-199          [-1, 672, 14, 14]           1,344ReLU-200          [-1, 672, 14, 14]               0Conv2d-201          [-1, 128, 14, 14]          86,144BatchNorm2d-202          [-1, 128, 14, 14]             256ReLU-203          [-1, 128, 14, 14]               0Conv2d-204           [-1, 32, 14, 14]          36,896BatchNorm2d-205          [-1, 704, 14, 14]           1,408ReLU-206          [-1, 704, 14, 14]               0Conv2d-207          [-1, 128, 14, 14]          90,240BatchNorm2d-208          [-1, 128, 14, 14]             256ReLU-209          [-1, 128, 14, 14]               0Conv2d-210           [-1, 32, 14, 14]          36,896BatchNorm2d-211          [-1, 736, 14, 14]           1,472ReLU-212          [-1, 736, 14, 14]               0Conv2d-213          [-1, 128, 14, 14]          94,336BatchNorm2d-214          [-1, 128, 14, 14]             256ReLU-215          [-1, 128, 14, 14]               0Conv2d-216           [-1, 32, 14, 14]          36,896BatchNorm2d-217          [-1, 768, 14, 14]           1,536ReLU-218          [-1, 768, 14, 14]               0Conv2d-219          [-1, 128, 14, 14]          98,432BatchNorm2d-220          [-1, 128, 14, 14]             256ReLU-221          [-1, 128, 14, 14]               0Conv2d-222           [-1, 32, 14, 14]          36,896BatchNorm2d-223          [-1, 800, 14, 14]           1,600ReLU-224          [-1, 800, 14, 14]               0Conv2d-225          [-1, 128, 14, 14]         102,528BatchNorm2d-226          [-1, 128, 14, 14]             256ReLU-227          [-1, 128, 14, 14]               0Conv2d-228           [-1, 32, 14, 14]          36,896BatchNorm2d-229          [-1, 832, 14, 14]           1,664ReLU-230          [-1, 832, 14, 14]               0Conv2d-231          [-1, 128, 14, 14]         106,624BatchNorm2d-232          [-1, 128, 14, 14]             256ReLU-233          [-1, 128, 14, 14]               0Conv2d-234           [-1, 32, 14, 14]          36,896BatchNorm2d-235          [-1, 864, 14, 14]           1,728ReLU-236          [-1, 864, 14, 14]               0Conv2d-237          [-1, 128, 14, 14]         110,720BatchNorm2d-238          [-1, 128, 14, 14]             256ReLU-239          [-1, 128, 14, 14]               0Conv2d-240           [-1, 32, 14, 14]          36,896BatchNorm2d-241          [-1, 896, 14, 14]           1,792ReLU-242          [-1, 896, 14, 14]               0Conv2d-243          [-1, 128, 14, 14]         114,816BatchNorm2d-244          [-1, 128, 14, 14]             256ReLU-245          [-1, 128, 14, 14]               0Conv2d-246           [-1, 32, 14, 14]          36,896BatchNorm2d-247          [-1, 928, 14, 14]           1,856ReLU-248          [-1, 928, 14, 14]               0Conv2d-249          [-1, 128, 14, 14]         118,912BatchNorm2d-250          [-1, 128, 14, 14]             256ReLU-251          [-1, 128, 14, 14]               0Conv2d-252           [-1, 32, 14, 14]          36,896BatchNorm2d-253          [-1, 960, 14, 14]           1,920ReLU-254          [-1, 960, 14, 14]               0Conv2d-255          [-1, 128, 14, 14]         123,008BatchNorm2d-256          [-1, 128, 14, 14]             256ReLU-257          [-1, 128, 14, 14]               0Conv2d-258           [-1, 32, 14, 14]          36,896BatchNorm2d-259          [-1, 992, 14, 14]           1,984ReLU-260          [-1, 992, 14, 14]               0Conv2d-261          [-1, 128, 14, 14]         127,104BatchNorm2d-262          [-1, 128, 14, 14]             256ReLU-263          [-1, 128, 14, 14]               0Conv2d-264           [-1, 32, 14, 14]          36,896BatchNorm2d-265         [-1, 1024, 14, 14]           2,048ReLU-266         [-1, 1024, 14, 14]               0Conv2d-267          [-1, 512, 14, 14]         524,800AvgPool2d-268            [-1, 512, 7, 7]               0BatchNorm2d-269            [-1, 512, 7, 7]           1,024ReLU-270            [-1, 512, 7, 7]               0Conv2d-271            [-1, 128, 7, 7]          65,664BatchNorm2d-272            [-1, 128, 7, 7]             256ReLU-273            [-1, 128, 7, 7]               0Conv2d-274             [-1, 32, 7, 7]          36,896BatchNorm2d-275            [-1, 544, 7, 7]           1,088ReLU-276            [-1, 544, 7, 7]               0Conv2d-277            [-1, 128, 7, 7]          69,760BatchNorm2d-278            [-1, 128, 7, 7]             256ReLU-279            [-1, 128, 7, 7]               0Conv2d-280             [-1, 32, 7, 7]          36,896BatchNorm2d-281            [-1, 576, 7, 7]           1,152ReLU-282            [-1, 576, 7, 7]               0Conv2d-283            [-1, 128, 7, 7]          73,856BatchNorm2d-284            [-1, 128, 7, 7]             256ReLU-285            [-1, 128, 7, 7]               0Conv2d-286             [-1, 32, 7, 7]          36,896BatchNorm2d-287            [-1, 608, 7, 7]           1,216ReLU-288            [-1, 608, 7, 7]               0Conv2d-289            [-1, 128, 7, 7]          77,952BatchNorm2d-290            [-1, 128, 7, 7]             256ReLU-291            [-1, 128, 7, 7]               0Conv2d-292             [-1, 32, 7, 7]          36,896BatchNorm2d-293            [-1, 640, 7, 7]           1,280ReLU-294            [-1, 640, 7, 7]               0Conv2d-295            [-1, 128, 7, 7]          82,048BatchNorm2d-296            [-1, 128, 7, 7]             256ReLU-297            [-1, 128, 7, 7]               0Conv2d-298             [-1, 32, 7, 7]          36,896BatchNorm2d-299            [-1, 672, 7, 7]           1,344ReLU-300            [-1, 672, 7, 7]               0Conv2d-301            [-1, 128, 7, 7]          86,144BatchNorm2d-302            [-1, 128, 7, 7]             256ReLU-303            [-1, 128, 7, 7]               0Conv2d-304             [-1, 32, 7, 7]          36,896BatchNorm2d-305            [-1, 704, 7, 7]           1,408ReLU-306            [-1, 704, 7, 7]               0Conv2d-307            [-1, 128, 7, 7]          90,240BatchNorm2d-308            [-1, 128, 7, 7]             256ReLU-309            [-1, 128, 7, 7]               0Conv2d-310             [-1, 32, 7, 7]          36,896BatchNorm2d-311            [-1, 736, 7, 7]           1,472ReLU-312            [-1, 736, 7, 7]               0Conv2d-313            [-1, 128, 7, 7]          94,336BatchNorm2d-314            [-1, 128, 7, 7]             256ReLU-315            [-1, 128, 7, 7]               0Conv2d-316             [-1, 32, 7, 7]          36,896BatchNorm2d-317            [-1, 768, 7, 7]           1,536ReLU-318            [-1, 768, 7, 7]               0Conv2d-319            [-1, 128, 7, 7]          98,432BatchNorm2d-320            [-1, 128, 7, 7]             256ReLU-321            [-1, 128, 7, 7]               0Conv2d-322             [-1, 32, 7, 7]          36,896BatchNorm2d-323            [-1, 800, 7, 7]           1,600ReLU-324            [-1, 800, 7, 7]               0Conv2d-325            [-1, 128, 7, 7]         102,528BatchNorm2d-326            [-1, 128, 7, 7]             256ReLU-327            [-1, 128, 7, 7]               0Conv2d-328             [-1, 32, 7, 7]          36,896BatchNorm2d-329            [-1, 832, 7, 7]           1,664ReLU-330            [-1, 832, 7, 7]               0Conv2d-331            [-1, 128, 7, 7]         106,624BatchNorm2d-332            [-1, 128, 7, 7]             256ReLU-333            [-1, 128, 7, 7]               0Conv2d-334             [-1, 32, 7, 7]          36,896BatchNorm2d-335            [-1, 864, 7, 7]           1,728ReLU-336            [-1, 864, 7, 7]               0Conv2d-337            [-1, 128, 7, 7]         110,720BatchNorm2d-338            [-1, 128, 7, 7]             256ReLU-339            [-1, 128, 7, 7]               0Conv2d-340             [-1, 32, 7, 7]          36,896BatchNorm2d-341            [-1, 896, 7, 7]           1,792ReLU-342            [-1, 896, 7, 7]               0Conv2d-343            [-1, 128, 7, 7]         114,816BatchNorm2d-344            [-1, 128, 7, 7]             256ReLU-345            [-1, 128, 7, 7]               0Conv2d-346             [-1, 32, 7, 7]          36,896BatchNorm2d-347            [-1, 928, 7, 7]           1,856ReLU-348            [-1, 928, 7, 7]               0Conv2d-349            [-1, 128, 7, 7]         118,912BatchNorm2d-350            [-1, 128, 7, 7]             256ReLU-351            [-1, 128, 7, 7]               0Conv2d-352             [-1, 32, 7, 7]          36,896BatchNorm2d-353            [-1, 960, 7, 7]           1,920ReLU-354            [-1, 960, 7, 7]               0Conv2d-355            [-1, 128, 7, 7]         123,008BatchNorm2d-356            [-1, 128, 7, 7]             256ReLU-357            [-1, 128, 7, 7]               0Conv2d-358             [-1, 32, 7, 7]          36,896BatchNorm2d-359            [-1, 992, 7, 7]           1,984ReLU-360            [-1, 992, 7, 7]               0Conv2d-361            [-1, 128, 7, 7]         127,104BatchNorm2d-362            [-1, 128, 7, 7]             256ReLU-363            [-1, 128, 7, 7]               0Conv2d-364             [-1, 32, 7, 7]          36,896BatchNorm2d-365           [-1, 1024, 7, 7]           2,048ReLU-366           [-1, 1024, 7, 7]               0Linear-367                    [-1, 2]           2,050
================================================================
Total params: 6,966,146
Trainable params: 6,966,146
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 294.57
Params size (MB): 26.57
Estimated Total Size (MB): 321.72
----------------------------------------------------------------

三、 训练模型 

1. 编写训练函数

def train(dataloader,model,optimizer,loss_fn):size = len(dataloader.dataset)num_batches = len(dataloader)train_acc,train_loss = 0,0for X,y in dataloader:X,y = X.to(device),y.to(device)pred = model(X)loss = loss_fn(pred,y)optimizer.zero_grad()loss.backward()optimizer.step()train_loss += loss.item()train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss /= num_batchestrain_acc /= sizereturn train_acc,train_loss

2. 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

def test(dataloader, model, loss_fn):size = len(dataloader.dataset)  # 测试集的大小num_batches = len(dataloader)  # 批次数目, (size/batch_size,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

3.正式训练

import copyoptimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
loss_fn = nn.CrossEntropyLoss()  # 创建损失函数epochs = 10train_loss=[]
train_acc=[]
test_loss=[]
test_acc=[]
best_acc = 0for epoch in range(epochs):model.train()epoch_train_acc,epoch_train_loss = train(train_dl,model,opt,loss_fn)model.eval()epoch_test_acc,epoch_test_loss = test(test_dl,model,loss_fn)if epoch_test_acc > best_acc:best_acc = epoch_test_accbest_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)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 = '/best_model.pth'  # 保存的参数文件名
torch.save(best_model.state_dict(), PATH)print('Done')

得到如下输出:

Epoch: 1, Train_acc:84.3%, Train_loss:0.359, Test_acc:86.7%, Test_loss:0.317, Lr:1.00E-04
Epoch: 2, Train_acc:87.6%, Train_loss:0.292, Test_acc:89.0%, Test_loss:0.270, Lr:1.00E-04
Epoch: 3, Train_acc:89.2%, Train_loss:0.260, Test_acc:89.8%, Test_loss:0.264, Lr:1.00E-04
Epoch: 4, Train_acc:90.2%, Train_loss:0.239, Test_acc:89.7%, Test_loss:0.259, Lr:1.00E-04
Epoch: 5, Train_acc:91.0%, Train_loss:0.222, Test_acc:90.3%, Test_loss:0.228, Lr:1.00E-04
Epoch: 6, Train_acc:91.1%, Train_loss:0.218, Test_acc:90.9%, Test_loss:0.236, Lr:1.00E-04
Epoch: 7, Train_acc:91.7%, Train_loss:0.201, Test_acc:82.4%, Test_loss:0.462, Lr:1.00E-04
Epoch: 8, Train_acc:92.5%, Train_loss:0.184, Test_acc:90.2%, Test_loss:0.264, Lr:1.00E-04
Epoch: 9, Train_acc:93.3%, Train_loss:0.172, Test_acc:90.2%, Test_loss:0.272, Lr:1.00E-04
Epoch:10, Train_acc:93.2%, Train_loss:0.171, Test_acc:90.7%, Test_loss:0.229, Lr:1.00E-04
DoneProcess finished with exit code 0

四、 结果可视化

1. Loss&Accuracy

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()

得到的可视化结果:

五、个人理解

本文为实战帖,具体代码细节及网络理解在之前的文章中已有涉及,这里不再做细节阐述。

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如若转载,请注明出处:http://www.mzph.cn/news/853730.shtml

如若内容造成侵权/违法违规/事实不符,请联系多彩编程网进行投诉反馈email:809451989@qq.com,一经查实,立即删除!

相关文章

在表格中渲染轮播图的方法;

效果图:代码: shop()function shop() {// render()$.ajax({url: "http://jingxun.zhbbll.asia/pc/Commodity/shop_list", //要请求的后端地址type: "GET", //数据发送的方式(POST或者GET)dataType: JSON,headers: {token: token,id…

双Token方案实现Token自动续期(基于springboot+vue前后端分离项目)

文章目录 前言一、双Token方案介绍1. 令牌类型与功能2.双Token方案的优点3.实现流程 二、具体实现1.后端实现1.1 jwt工具类1.2 响应工具类1.3 实体类1.4 过滤器1.5 controller1.6 启动类 2、前端实现2.1 登录页面2.2 index页面2.3 请求拦截器和响应拦截器 效果展示 前言 更多j…

【星座运势】本周财运分析,巨蟹座财富潜力大开!

大家好!今天我们来谈谈巨蟹座本周的财富运势。经过调查和数据分析,我发现巨蟹座这周的财运潜力很大!接下来,我将用通俗易懂的语言,通过代码说明,向大家展示巨蟹座的财富运势。 首先,我们需要通…

人工智能对零售业的影响

机器人、人工智能相关领域 news/events (专栏目录) 本文目录 一、人工智能如何改变零售格局二、利用人工智能实现购物体验自动化三、利用人工智能改善库存管理四、通过人工智能解决方案增强客户服务五、利用人工智能分析消费者行为六、利用 AI 打造个性化…

【javaEE-有关CPU进程和线程实现的并发编程及二者的区别】

🔥🔥🔥有关进程并发编程开发的成本问题 这次之前其实我们所有的写的程序都是使用单核心来运行的,但是一般我们的计算机都有很多核心,如果我们编程的时候,只使用一个核心的话,其实这是一个非常大…

使用源代码编译方式升级内核【笔记】

为什么要升级内核 升级内核有多个重要的原因,主要包括以下几点: 安全性:随着技术的发展,旧版本的内核可能会存在安全漏洞。黑客或恶意用户可能会利用这些漏洞进行攻击。升级内核可以修复这些已知的安全漏洞,从而提高系统的安全性。性能优化:新版本的内核通常会包含对性能…

打造成功的人力RPO项目:赢得市场赚取利润

人力资源外包(RPO)项目是当今企业在招聘和人才管理方面越来越倾向的选择。想要通过人力RPO项目赚钱,以下是一些关键的策略和步骤,帮助您进入这个市场并取得成功。 1. 建立专业的人力RPO服务 首先,要想在人力RPO项目中赚钱,必须建立…

9. 文本三剑客之awk

文章目录 9.1 什么是awk9.2 awk命令格式9.3 awk执行流程9.4 行与列9.4.1 取行9.4.2 取列 9.1 什么是awk 虽然sed编辑器是非常方便自动修改文本文件的工具,但其也有自身的限制。通常你需要一个用来处理文件中的数据的更高级工具,它能提供一个类编程环境来…

【CT】LeetCode手撕—20. 有效的括号

题目 原题连接&#xff1a;20. 有效的括号 1- 思路 模式识别 模式1&#xff1a;括号左右匹配 ——> 借助栈来实现 ——> Deque<Character> deque new LinkedList<>()模式2&#xff1a;顺序匹配 ——> 用 if 判断 具体思路 1.遇到左括号 直接入栈相应…

FPGA IO_BANK、IO_STANDARD

描述 Xilinx 7系列FPGA和UltraScale体系结构提供了高性能&#xff08;HP&#xff09;和 高范围&#xff08;HR&#xff09;I/O组。I/O库是I/O块&#xff08;IOB&#xff09;的集合&#xff0c;具有可配置的 SelectIO驱动程序和接收器&#xff0c;支持多种标准接口 单端和差分。…

JS中的延时操作setTimeout()和setInterval()

JS中&#xff0c;给我们提供两种延时操作的内置方法setTimeout()和setInterval()。setTimeout和setInterval方法都是挂载在javascript的window对象下&#xff0c;通过两个参数控制&#xff0c;第一个参数控制运行的表达式或方法&#xff0c;第二个参数表示延时的时间&#xff0…

【电路笔记】-共基极放大器

共基极放大器 文章目录 共基极放大器1、概述2、等效电路3、电流增益4、输入阻抗5、输出阻抗6、电压增益7、示例:电压、电流和功率增益8、总结1、概述 在本文中,我们将介绍双极晶体管放大器的最后一种拓扑,称为共基极放大器 (CBA)。 下面的图 1 显示了 CBA 的电气图,此处没…

vite-plugin-pwa 离线安装Vite应用

渐进式Web应用&#xff08;PWA&#xff09;通过结合 Web 和移动应用的特点&#xff0c;为用户带来更加流畅和快速的体验。且PWA支持离线访问能力&#xff08;访问静态资源本地缓存&#xff09;&#xff0c;极大提高了用户交互的流畅性&#xff0c;降低非必要的网络依赖。尤其适…

卡尔曼滤波源码注释和调用示例

卡尔曼滤波源码注释和调用示例 flyfish Python版本代码地址 C版代码地址 主要用于分析代码&#xff0c;增加了中文注释 import numpy as np import scipy.linalg""" 0.95分位数的卡方分布表&#xff0c;N自由度&#xff08;包含N1到9的值&#xff09;。 取自…

【JS重点15】原型对象概述

目录 一&#xff1a;构造函数缺陷 二&#xff1a;原型 1 原型是是什么 2 原型对象的作用 3 原型对象this指向问题 4 利用原型对象添加方法 给JS内置构造函数Array添加最大值方法 给JS内置构造函数Array添加求和方法 三&#xff1a;Constructor属性 四&#xff1a;如何…

情绪管理:大我则定,小我则乱(王阳明)

学了很多知识&#xff0c;却还是感物易动&#xff1f;如何让心回归中正&#xff1f;王阳明一言以蔽之&#xff1a; —— 大我&#xff0c;大我则定&#xff0c;小我则乱 保持心静的方法&#xff1a;有大爱&#xff0c;为大局着想

全球“抱团”美股,美股“抱团”AI

内容提要 过去一个月内&#xff0c;全球约有300亿美元新资金流入股票基金&#xff0c;其中高达94%投向了美国资产&#xff1b;一季度&#xff0c;海外投资者购入了1870亿美元美国公司债券&#xff0c;同比增长61%。 文章正文 尽管美国面临债务问题和大选带来的政治分歧&#…

单链表——AcWing.826单链表

单链表 定义 单链表是一种常见的数据结构&#xff0c;它由一系列节点组成&#xff0c;每个节点包含一个数据元素和一个指向下一个节点的指针。 运用情况 用于实现动态的数据存储和管理&#xff0c;例如实现栈、队列等其他数据结构。在需要频繁进行插入和删除操作时非常有用…

pdf文件怎么改变大小?在线快速压缩pdf的方法

pdf作为一种常用的文件格式&#xff0c;使用这种文件类型的好处在于不仅拥有更好的兼容性&#xff0c;还可以设置密码来保证安全性&#xff0c;防止未授权用户查看内容&#xff0c;所以现在导出文件展示都会采用这种格式的来做内容展示。当遇到pdf文件过大问题时&#xff0c;想…

Python虚拟环境的配置

前言&#xff1a; 本人一度被Python的虚拟环境的配置所困扰&#xff0c;前段时间抽空学习了一下&#xff0c;现在总结一下方法&#xff0c;供大家参考。 先使用winr打开命令行窗口。 展示所有虚拟环境 conda env list 创建虚拟环境 例如我们创建一个叫做py_sk的虚拟环境 …