深度学习Week21——学习DenseNet算法

文章目录
深度学习Week21——学习DenseNet算法
一、前言
二、我的环境
三、学习DenseNet算法
四、代码复现
4.1 配置数据集
4.2 构建模型
五、模型应用与评估
5.1 编写训练函数
5.2 编写测试函数
5.3 训练模型
5.4 结果可视化

一、前言

  • 🍨 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

由于进阶营的难度较大，一周的时间我们难以完成一期内容的深入学习与理解，为了更好的学习，我们本周只了解并研究 DenseNet与ResNet的区别，并学习pytorch代码。

二、我的环境

  • 电脑系统：Windows 10
  • 语言环境：Python 3.8.0
  • 编译器：Pycharm2023.2.3
    深度学习环境：Pytorch
    显卡及显存：RTX 3060 8G

三、学习DenseNet算法

通过阅读K同学啊的代码以及DenseNe论文原文，我学习到DenseNe相比于之前学过的内容t提出了一个更激进的密集连接机制：即互相连接所有的层，具体来说就是每个层都会接受其前面所有层作为其额外的输入。
图1为标准的神经网络传播过程，图2为ResNet网络的残差连接机制，作为对比，图3为DenseNet的密集连接机制。可以看到，ResNet是每个层与前面的某层（一般是2~4层）短路连接在一起，连接方式是通过元素相加。而在DenseNet中，每个层都会与前面所有层在channel维度上连接（concat）在一起（即元素叠加），并作为下一层的输入。
图1.标准的神经网络传播过程

在这里插入图片描述
图2. ResNet网络的短路连接机制（其中+代表的是元素级相加操作）
在这里插入图片描述
图3 DenseNet网络的密集连接机制（其中c代表的是channel级连接操作）
在这里插入图片描述
通俗点来说，假设在一个团队工作，每个人（网络层）都有自己的任务（特征提取）。

  • 在传统的网络中，成员A完成任务后，把结果交给成员B，B再交给C，以此类推。
  • 而在ResNet网络中，成员A完成任务后，不仅把结果交给B，还留了一条快速通道给D（跨过了B和C）。这样，如果B和C做得不好，D仍然能直接使用A的结果，确保信息不丢失。
  • 但是在DenseNet中，成员A不仅把结果交给B，还同时交给C、D、E等所有后续成员。这样，每个成员都可以直接利用前面所有成员的工作成果。

四、代码复现

4.1 配置数据集

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warningswarnings.filterwarnings("ignore")             #忽略警告信息device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

data_dir = "/home/mw/input/data7619//bird_photos/bird_photos"data_dir = pathlib.Path(data_dir)data_paths  = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[0] for path in data_paths]
print(classeNames)

['/home/mw/input/data7619/bird_photos/bird_photos/Bananaquit', '/home/mw/input/data7619/bird_photos/bird_photos/Black Throated Bushtiti', '/home/mw/input/data7619/bird_photos/bird_photos/Cockatoo', '/home/mw/input/data7619/bird_photos/bird_photos/Black Skimmer']

image_count = len(list(data_dir.glob('*/*')))
print("图片总数为：",image_count)


图片总数为： 565
数据增强
import torchvision.transforms as transforms
from torchvision import datasets# 这里我们运用上前面学习到的数据增强的方式
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.RandomVerticalFlip(),  # 随机垂直翻转transforms.RandomRotation(15),  # 随机旋转图片，范围为-15度到15度transforms.ToTensor(),  # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
])test_transform = 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转换为tensor，并归一化到[0,1]之间transforms.Normalize(  # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])total_data = datasets.ImageFolder("/home/mw/input/data7619//bird_photos/bird_photos", transform=train_transforms)
print(total_data.class_to_idx)

{'Bananaquit': 0, 'Black Skimmer': 1, 'Black Throated Bushtiti': 2, 'Cockatoo': 3}
划分训练集、测试集
# 按比例将数据集分割为训练集和测试集
train_size = int(0.8 * len(total_data))  # 计算训练集的大小，占总数据集的80%
test_size = len(total_data) - train_size  # 计算测试集的大小，占总数据集的20%
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])  # 随机分割数据集# 定义批量大小
batch_size = 16# 创建训练集的数据加载器
train_dl = torch.utils.data.DataLoader(train_dataset,  # 训练集数据batch_size=batch_size,  # 每个批次的大小为32shuffle=True,  # 打乱数据num_workers=0  # 使用的工作线程数
)# 创建测试集的数据加载器
test_dl = torch.utils.data.DataLoader(test_dataset,  batch_size=batch_size,  shuffle=True,  num_workers=0  
)for X, y in test_dl:print("Shape of X [N, C, H, W]: ", X.shape) print("Shape of y: ", y.shape, y.dtype)  break  

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

4.2 构建模型

首先我们实现DenseLayer，实现高效的特征传递和重用

class _DenseLayer(nn.Sequential):"""Basic unit of DenseBlock (using bottleneck layer) """def __init__(self, num_input_features, growth_rate, bn_size, drop_rate):super(_DenseLayer, self).__init__()self.add_module("norm1", nn.BatchNorm2d(num_input_features))self.add_module("relu1", nn.ReLU(inplace=True))self.add_module("conv1", nn.Conv2d(num_input_features, 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_features = super(_DenseLayer, self).forward(x)if self.drop_rate > 0:new_features = F.dropout(new_features, p=self.drop_rate, training=self.training)return torch.cat([x, new_features], 1)

据此，实现DenseBlock模块，有多个DenseLayer，内部是密集连接方式（输入特征数线性增长）：

class _DenseBlock(nn.Sequential):"""DenseBlock"""def __init__(self, num_layers, num_input_features, bn_size, growth_rate, drop_rate):super(_DenseBlock, self).__init__()for i in range(num_layers):layer = _DenseLayer(num_input_features+i*growth_rate, growth_rate, bn_size,drop_rate)self.add_module("denselayer%d" % (i+1,), layer)

然后，我们实现Transition层，它主要是一个卷积层和一个池化层：

class _Transition(nn.Sequential):"""Transition layer between two adjacent DenseBlock"""def __init__(self, num_input_feature, num_output_features):super(_Transition, self).__init__()self.add_module("norm", nn.BatchNorm2d(num_input_feature))self.add_module("relu", nn.ReLU(inplace=True))self.add_module("conv", nn.Conv2d(num_input_feature, num_output_features,kernel_size=1, stride=1, bias=False))self.add_module("pool", nn.AvgPool2d(2, stride=2))

接下来我们实现DenseNet网络：

class DenseNet(nn.Module):"DenseNet-BC model"def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64,bn_size=4, compression_rate=0.5, drop_rate=0, num_classes=1000):""":param growth_rate: (int) number of filters used in DenseLayer, `k` in the paper:param block_config: (list of 4 ints) number of layers in each DenseBlock:param num_init_features: (int) number of filters in the first Conv2d:param bn_size: (int) the factor using in the bottleneck layer:param compression_rate: (float) the compression rate used in Transition Layer:param drop_rate: (float) the drop rate after each DenseLayer:param num_classes: (int) number of classes for classification"""super(DenseNet, self).__init__()# first Conv2dself.features = nn.Sequential(OrderedDict([("conv0", nn.Conv2d(3, num_init_features, kernel_size=7, stride=2, padding=3, bias=False)),("norm0", nn.BatchNorm2d(num_init_features)),("relu0", nn.ReLU(inplace=True)),("pool0", nn.MaxPool2d(3, stride=2, padding=1))]))# DenseBlocknum_features = num_init_featuresfor 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))# classification layerself.classifier = nn.Linear(num_features, num_classes)# params initializationfor 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):features = self.features(x)out = F.avg_pool2d(features, 7, stride=1).view(features.size(0), -1)out = self.classifier(out)return out

实现DenseNet-121网络，而且Pytorch提供了预训练好的网络参数：

def densenet121(pretrained=False, **kwargs):"""DenseNet121"""model = DenseNet(num_init_features=64, growth_rate=32, block_config=(6, 12, 24, 16),**kwargs)if pretrained:# '.'s are no longer allowed in module names, but pervious _DenseLayer# has keys 'norm.1', 'relu.1', 'conv.1', 'norm.2', 'relu.2', 'conv.2'.# They are also in the checkpoints in model_urls. This pattern is used# to find such keys.pattern = re.compile(r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$')state_dict = model_zoo.load_url(model_urls['densenet121'])for key in list(state_dict.keys()):res = pattern.match(key)if res:new_key = res.group(1) + res.group(2)state_dict[new_key] = state_dict[key]del state_dict[key]model.load_state_dict(state_dict)return model

from collections import OrderedDict
model = densenet121(num_classes=1000).to(device)
print(model)

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=1000, bias=True)
)

五 、模型应用与评估

5.1 编写训练函数

def train(dataloader, model, loss_fn, optimizer):model.train()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)loss = loss_fn(pred, y)# 反向传播optimizer.zero_grad()loss.backward()optimizer.step()train_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc  /= len(dataloader.dataset)train_loss /= len(dataloader)return train_acc, train_loss

5.2 编写测试函数

def test(dataloader, model, loss_fn):model.eval()test_loss, test_acc = 0, 0with torch.no_grad():for X, y in dataloader:X, y = X.to(device), y.to(device)pred = model(X)loss = loss_fn(pred, y)test_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()test_loss += loss.item()test_acc  /= len(dataloader.dataset)test_loss /= len(dataloader)return test_acc, test_loss

5.3 训练模型

# 定义损失函数和优化器
loss_fn = nn.CrossEntropyLoss()
learn_rate = 1e-4
opt = optim.Adam(model.parameters(), lr=learn_rate)epochs = 30
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0# 开始训练
for epoch in range(epochs):model.train()epoch_train_acc, epoch_train_loss = train(train_dl, model, opt, loss_fn, device)# 清理缓存以释放显存torch.cuda.empty_cache()model.eval()epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn, device)if epoch_test_acc > best_acc:best_acc = epoch_test_accbest_model = 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))
print('Done')

Epoch: 1, Train_acc:52.2%, Train_loss:5.147, Test_acc:58.4%, Test_loss:3.211, Lr:1.00E-04
Epoch: 2, Train_acc:69.2%, Train_loss:2.282, Test_acc:80.5%, Test_loss:1.687, Lr:1.00E-04
Epoch: 3, Train_acc:77.2%, Train_loss:1.095, Test_acc:77.9%, Test_loss:0.827, Lr:1.00E-04
Epoch: 4, Train_acc:83.2%, Train_loss:0.728, Test_acc:84.1%, Test_loss:0.599, Lr:1.00E-04
Epoch: 5, Train_acc:82.3%, Train_loss:0.583, Test_acc:88.5%, Test_loss:0.442, Lr:1.00E-04
Epoch: 6, Train_acc:85.4%, Train_loss:0.486, Test_acc:80.5%, Test_loss:0.461, Lr:1.00E-04
Epoch: 7, Train_acc:86.9%, Train_loss:0.492, Test_acc:87.6%, Test_loss:0.399, Lr:1.00E-04
Epoch: 8, Train_acc:86.9%, Train_loss:0.432, Test_acc:90.3%, Test_loss:0.298, Lr:1.00E-04
Epoch: 9, Train_acc:87.4%, Train_loss:0.384, Test_acc:89.4%, Test_loss:0.346, Lr:1.00E-04
Epoch:10, Train_acc:89.4%, Train_loss:0.336, Test_acc:89.4%, Test_loss:0.284, Lr:1.00E-04
Epoch:11, Train_acc:90.0%, Train_loss:0.361, Test_acc:87.6%, Test_loss:0.277, Lr:1.00E-04
Epoch:12, Train_acc:90.0%, Train_loss:0.298, Test_acc:88.5%, Test_loss:0.395, Lr:1.00E-04
Epoch:13, Train_acc:93.8%, Train_loss:0.209, Test_acc:85.8%, Test_loss:0.540, Lr:1.00E-04
Epoch:14, Train_acc:93.1%, Train_loss:0.212, Test_acc:89.4%, Test_loss:0.266, Lr:1.00E-04
Epoch:15, Train_acc:93.1%, Train_loss:0.243, Test_acc:91.2%, Test_loss:0.185, Lr:1.00E-04
Epoch:16, Train_acc:93.8%, Train_loss:0.224, Test_acc:89.4%, Test_loss:0.450, Lr:1.00E-04
Epoch:17, Train_acc:91.4%, Train_loss:0.232, Test_acc:92.0%, Test_loss:0.275, Lr:1.00E-04
Epoch:18, Train_acc:91.4%, Train_loss:0.320, Test_acc:92.0%, Test_loss:0.193, Lr:1.00E-04
Epoch:19, Train_acc:92.5%, Train_loss:0.289, Test_acc:92.9%, Test_loss:0.242, Lr:1.00E-04
Epoch:20, Train_acc:96.7%, Train_loss:0.148, Test_acc:92.0%, Test_loss:0.232, Lr:1.00E-04
Epoch:21, Train_acc:97.1%, Train_loss:0.145, Test_acc:92.9%, Test_loss:0.202, Lr:1.00E-04
Epoch:22, Train_acc:90.9%, Train_loss:0.274, Test_acc:87.6%, Test_loss:0.265, Lr:1.00E-04
Epoch:23, Train_acc:94.5%, Train_loss:0.168, Test_acc:93.8%, Test_loss:0.211, Lr:1.00E-04
Epoch:24, Train_acc:95.4%, Train_loss:0.162, Test_acc:92.0%, Test_loss:0.203, Lr:1.00E-04
Epoch:25, Train_acc:95.8%, Train_loss:0.150, Test_acc:86.7%, Test_loss:0.365, Lr:1.00E-04
Epoch:26, Train_acc:95.6%, Train_loss:0.149, Test_acc:93.8%, Test_loss:0.226, Lr:1.00E-04
Epoch:27, Train_acc:92.3%, Train_loss:0.211, Test_acc:87.6%, Test_loss:0.379, Lr:1.00E-04
Epoch:28, Train_acc:97.1%, Train_loss:0.133, Test_acc:92.0%, Test_loss:0.191, Lr:1.00E-04
Epoch:29, Train_acc:95.8%, Train_loss:0.129, Test_acc:92.0%, Test_loss:0.250, Lr:1.00E-04
Epoch:30, Train_acc:98.7%, Train_loss:0.084, Test_acc:91.2%, Test_loss:0.184, Lr:1.00E-04
Done

5.4 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()

在这里插入图片描述

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.rhkb.cn/news/386320.html

如若内容造成侵权/违法违规/事实不符，请联系长河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

第一个设计模式——单例模式

第一个设计模式——单例模式

目录 一、特点： 二、实现单例模式步骤 三、饿汉式 四、懒汉式 五、双重检查锁 六、静态内部类 七、枚举 八、可能被反序列化和反射破坏什么意思？ 九、如何解决呢？ 一、特点： 唯一性，单例模式确保程序中只有一…
阅读更多...
Qt自定义带前后缀图标的PushButton

Qt自定义带前后缀图标的PushButton

写在前面 Qt提供QPushButton不满足带前后缀图标的需求，因此考虑自定义实现带前后缀图标的PushButton，方便后续快速使用。 效果如下： 同时可设置前后缀图标和文本之间间隙： 代码实现 通过前文介绍的Qt样式表底层实现 可以得…
阅读更多...
HiveSQL中last_value和first_value函数的应用

HiveSQL中last_value和first_value函数的应用

概述 今天做一个数据分析，其中有一列数据有些有数据有些没数据，因此我们需要把每数据的进行补充进来因此我们需要使用last_value 函数和over 结合使用，但是遇到一个比较奇葩的问题不能按照预期进行处理。 新说原因： 由于我们要处…
阅读更多...
vue3-环境变量-JavaScript-axio-基础使用-lzstring-字符串压缩-python

vue3-环境变量-JavaScript-axio-基础使用-lzstring-字符串压缩-python

文章目录 1.Vue3环境变量1.1.简介1.2.全局变量的引用1.3.package.json文件 2.axio2.1.promise2.2.安装2.3.配置2.3.1.全局 axios 默认值2.3.2.响应信息格式 2.4.Axios的拦截器2.4.1.请求拦截器2.4.2.响应拦截器2.4.3.移除拦截器2.4.4.自定义实例添加拦截器 3.lz-string3.1.java…
阅读更多...
java项目数据库 mysql 迁移到 达梦

java项目数据库 mysql 迁移到 达梦

目录 一、下载安装达梦数据库 1、下载 2、解压 3、安装 二、迁移 三、更改SpringBoot 的 yml文件 1、达梦创建用户 2、修改yml 一、下载安装达梦数据库 1、下载 下载地址 https://eco.dameng.com/download/ 点击下载 开发版 (X86平台) , 然后选择操作系统并点击立…
阅读更多...
“科技创新‘圳’在变革”2025深圳电子展

“科技创新‘圳’在变革”2025深圳电子展

电子产业作为现代社会的核心驱动力之一，正以前所未有的速度发展。在这样的背景下，深圳作为中国的经济特区和创新高地，又一次迎来了备受瞩目的盛会——2025深圳电子展览会。本次展览会定于2025年4月9日至11日，在深圳会展中心&#…
阅读更多...
剪画小程序：手机提取人声和伴奏

剪画小程序：手机提取人声和伴奏

在音乐的海洋中，我们常常渴望更纯粹地感受歌手的嗓音魅力。 如今，有了 剪画，人声分离不再是难题！ 想象一下，当您沉浸在一首动人的歌曲中，却希望更清晰地捕捉到歌手声音中的每一个微妙情感。 无论是经典老…
阅读更多...
算能端侧 AI 盒子 Stable Diffusion 一秒一张图：AirBox BM1684X

算能端侧 AI 盒子 Stable Diffusion 一秒一张图：AirBox BM1684X

本篇文章聊聊基于 端侧 AI 计算设备，20~30 瓦功耗运行大模型的算能 AirBox。 写在前面 去年的双十二的时候，在群里看到了一张照片，“手掌大小的 NUC”，但是能够跑大模型。 这个草就种下了。 今年 7 月初的时候，在上…
阅读更多...
学习008-02-04-09 Assign a Standard Image（分配标准图像）

学习008-02-04-09 Assign a Standard Image（分配标准图像）

Assign a Standard Image（分配标准图像） This lesson explains how to associate an entity class with a standard image from the DevExpress.Images assembly. This image illustrates the entity class in the following sections of the UI: 本课介…
阅读更多...
C# 知识点总结

C# 知识点总结

入门 C#程序在.NET上运行，.NET framework包含两个部分： ①：.NET framework类库 ②：公共语言运行库CLR（.NET虚拟机） CLS（公共语言规范） CTS（通用类型系统） .N…
阅读更多...
ubuntu20.04安装nginx，mysql8，php7.4详细教程，包成功

ubuntu20.04安装nginx，mysql8，php7.4详细教程，包成功

目录 1.更新索引 2.安装 Nginx 1.安装 Nginx： 2.启动 Nginx 服务并设置为开机自启： 3.开放防火墙的 80 端口： 4.检查 Nginx 是否正常运行： 3.安装 MySQL 8.0 1.首先，安装 MySQL 的仓库： 安装过程中你会看…
阅读更多...
RewardBench：Evaluating Reward Models for Language Modeling

RewardBench：Evaluating Reward Models for Language Modeling

Leaderboard： https://hf.co/spaces/allenai/reward-bench Code： https://github.com/allenai/reward-bench Dataset： https://hf.co/datasets/allenai/reward-bench 在人类偏好的强化学习（RLHF）过程中，奖励…
阅读更多...
【Vulnhub系列】Vulnhub_Seattle_003靶场渗透（原创）

【Vulnhub系列】Vulnhub_Seattle_003靶场渗透（原创）

【Vulnhub系列靶场】Vulnhub_Seattle_003靶场渗透 原文转载已经过授权 原文链接：Lusen的小窝 - 学无止尽，不进则退 (lusensec.github.io) 一、环境准备 1、从百度网盘下载对应靶机的.ova镜像 2、在VM中选择【打开】该.ova 3、选择存储路径&#xff0…
阅读更多...
【AI大模型】-- 应用部署

【AI大模型】-- 应用部署

一、GPU价格参考 有些在京东就能买到：https://item.jd.com/10065826100148.html美国商务部限制 GPU 对华出口的算力不超过 4800 TOPS 和带宽不超过 600 GB/s，导致最强的 H100 和 A100 禁售。英伟达随后推出针对中国市场的 A800 和 H800。 H100 与 A100&…
阅读更多...
CATIA V5R21安装包下载及图文安装教程

CATIA V5R21安装包下载及图文安装教程

大家好，今天给大家分享下catia安装教程 注意安装前请退出杀毒软件，防止误报影响安装进程 下载链接：百度网盘 请输入提取码 提取码：ypc6 01 在电脑D盘新建文件夹命名为CATIA,将下载的软件压缩包放置在该文件夹。 鼠标右击【C…
阅读更多...
淘宝测试环境治理实践

淘宝测试环境治理实践

去年之前，阿里巴巴的淘天集团测试环境是以领域方式运作：不局限测试环境治理本身，从测试模式方法论及用好测试环境思路引领集团测试环境治理。领域运作最难的是“统一思想”。业务进一步细分调整后，测试环境治理策略理应由业务方自…
阅读更多...
【MetaGPT系列】【MetaGPT完全实践宝典——多智能体实践】

【MetaGPT系列】【MetaGPT完全实践宝典——多智能体实践】

目录 前言一、智能体1-1、Agent概述1-2、Agent与ChatGPT的区别 二、多智能体框架MetaGPT2-1、安装&配置2-2、使用已有的Agent（ProductManager）2-3、多智能体系统介绍2-4、多智能体案例分析2-4-1、构建智能体团队2-4-2、动作/行为 定义2-4-3、角色/智…
阅读更多...
若能重回白宫，特朗普称将把比特币列为美国战略储备资产！

若能重回白宫，特朗普称将把比特币列为美国战略储备资产！

KlipC报道：当地时间7月29日，美国前总统特朗普参加比特币2024大会，并在会上宣布称，如果重返白宫，他将把比特币列为美国战略储备资产。讲话期间，比特币价格一度上涨到6.9万美元大关。 特朗普表示&#xff1a…
阅读更多...
Photos框架 - 自定义媒体选择器（UI预览）

Photos框架 - 自定义媒体选择器（UI预览）

引言 在前面的博客中我们已经介绍了使用媒体资源数据的获取，以及自定义的媒体资源选择列表页。在一个功能完整的媒体选择器中，预览自然是必不可少的，本篇博客我们就来实现一个资源的预览功能，并且实现列表和预览的数据联动效果。…
阅读更多...
前端基于 axios 实现批量任务调度管理器 demo

前端基于 axios 实现批量任务调度管理器 demo

一、背景介绍 这是一个基于 axios 实现的批量任务调度管理器的 demo。它使用了axios、promise 等多种技术和原理来实现批量处理多个异步请求，并确保所有请求都能正确处理并报告其状态。 假设有一个场景：有一个任务列表，有单个任务的处理功能…
阅读更多...
最新文章
推荐文章

Copyright @ 2022~2023