BelgiumTS交通数据集分类-pytorch版

数据集下载地址:https://www.lanzouw.com/b01i4vc4b
密码:6y8b

注意：文件大小494M，有点大，百度云太慢不考虑，蓝奏云只能上传小于100M的，所以，将训练集拆分压缩了，使用时请将Training(0~30)和Training(31~61)合并到一个文件夹中

这个数据集有62个类别，可以做分类任务，数据量不是很多，所以我使用旋转、翻转对数据集进行增强。得到18300个图片。

类别：62类，训练集和测试集都有标签

训练集：4575张图片，下面的代码我通过旋转，翻转对数据增强得到18300张图片数据

测试集：2520张图片

完整代码在最下面：

下面数据处理和训练过程的代码：

定义数据增强的transform，如果你不想增强数据，只用data_transforms即可

# 定义图片增强要用的transformsimport torchvision.datasets as datasets
import torchvision.transforms as transformsfrom torch import nn
import torch
import torch.nn.functional as F
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')# data augmentation for training and test time
# Resize all images to 32 * 32 and normalize them to mean = 0 and standard-deviation = 1 based on statistics collected from the training setdata_transforms = transforms.Compose([transforms.Resize((32, 32)),transforms.ToTensor(),transforms.Normalize((0.3337, 0.3064, 0.3171), ( 0.2672, 0.2564, 0.2629))
])# Resize, normalize and rotate image
data_rotate = transforms.Compose([transforms.Resize((32, 32)),transforms.RandomRotation(15),transforms.ToTensor(),transforms.Normalize((0.3337, 0.3064, 0.3171), ( 0.2672, 0.2564, 0.2629))
])# Resize, normalize and flip image horizontally and vertically
data_hvflip = transforms.Compose([transforms.Resize((32, 32)),transforms.RandomHorizontalFlip(1),transforms.RandomVerticalFlip(1),transforms.ToTensor(),transforms.Normalize((0.3337, 0.3064, 0.3171), ( 0.2672, 0.2564, 0.2629))
])# Resize, normalize and shear image
data_shear = transforms.Compose([transforms.Resize((32, 32)),transforms.RandomAffine(degrees = 15,shear=2),transforms.ToTensor(),transforms.Normalize((0.3337, 0.3064, 0.3171), ( 0.2672, 0.2564, 0.2629))
])

加载数据集, 制作train_dataset时，我使用了三个上面的三个增强数据的transforms，你也可以只用第一个，或则使用其中几个

train_dir = './data/TSC/Training/'
test_dir = './data/TSC/Testing/'train_dataset = torch.utils.data.ConcatDataset([#数据增强，图片旋转剪切datasets.ImageFolder(train_dir,transform=data_transforms),datasets.ImageFolder(train_dir,transform=data_rotate),datasets.ImageFolder(train_dir,transform=data_hvflip),datasets.ImageFolder(train_dir,transform=data_shear)])test_dataset = datasets.ImageFolder(test_dir,transform=data_transforms)train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True, num_workers=1)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=True, num_workers=1)

定义模型：

class CNN_TSC(nn.Module):def __init__(self):super(CNN_TSC, self).__init__()self.conv1 = nn.Conv2d(3, 6, 5)self.pool = nn.MaxPool2d(2, 2)self.conv2 = nn.Conv2d(6, 16, 5)self.fc1 = nn.Linear(16 * 5 * 5, 120)self.fc2 = nn.Linear(120, 84)self.fc3 = nn.Linear(84, 62)def forward(self, x):x = self.pool(F.relu(self.conv1(x)))x = self.pool(F.relu(self.conv2(x)))x = x.view(-1, 16 * 5 * 5)x = F.relu(self.fc1(x))x = F.relu(self.fc2(x))output = self.fc3(x)return outputnet= CNN_TSC().to(device)
#定义损失函数和优化器
loss = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(net.parameters(), lr=0.001)

训练和预测：

#训练
def train():net.train()for data, label in train_loader:data, label = data.to(device), label.to(device)net.zero_grad()output = net(data)l = loss(output, label)l.backward()optimizer.step()
#测试
def test(epoch):net.eval()batch_loss, correct, total = 0,0 ,0for data, label in test_loader:data, label = data.to(device), label.to(device)output = net(data)batch_loss +=loss(output, label)predict_label = torch.argmax(output, dim=1)correct += torch.sum(predict_label==label)total +=len(label)print('epoch:%d loss: %.4f  accuracy:%.2f%%' %(epoch, batch_loss/len(test_loader), 100*correct/total))print('training on %s'%(device))
for epoch in range(10):train()test(epoch)

实验结果：

完整的代码：

import torchvision.datasets as datasets
import torchvision.transforms as transformsfrom torch import nn
import torch
import torch.nn.functional as F
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')# data augmentation for training and test time
# Resize all images to 32 * 32 and normalize them to mean = 0 and standard-deviation = 1 based on statistics collected from the training setdata_transforms = transforms.Compose([transforms.Resize((32, 32)),transforms.ToTensor(),transforms.Normalize((0.3337, 0.3064, 0.3171), ( 0.2672, 0.2564, 0.2629))
])# Resize, normalize and rotate image
data_rotate = transforms.Compose([transforms.Resize((32, 32)),transforms.RandomRotation(15),transforms.ToTensor(),transforms.Normalize((0.3337, 0.3064, 0.3171), ( 0.2672, 0.2564, 0.2629))
])# Resize, normalize and flip image horizontally and vertically
data_hvflip = transforms.Compose([transforms.Resize((32, 32)),transforms.RandomHorizontalFlip(1),transforms.RandomVerticalFlip(1),transforms.ToTensor(),transforms.Normalize((0.3337, 0.3064, 0.3171), ( 0.2672, 0.2564, 0.2629))
])# Resize, normalize and shear image
data_shear = transforms.Compose([transforms.Resize((32, 32)),transforms.RandomAffine(degrees = 15,shear=2),transforms.ToTensor(),transforms.Normalize((0.3337, 0.3064, 0.3171), ( 0.2672, 0.2564, 0.2629))
])#请修改这个目录为你的数据集目录
train_dir = './data/TSC/Training/'
test_dir = './data/TSC/Testing/'train_dataset = torch.utils.data.ConcatDataset([#数据增强，图片旋转剪切datasets.ImageFolder(train_dir,transform=data_transforms),datasets.ImageFolder(train_dir,transform=data_rotate),datasets.ImageFolder(train_dir,transform=data_hvflip),datasets.ImageFolder(train_dir,transform=data_shear)])test_dataset = datasets.ImageFolder(test_dir,transform=data_transforms)train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True, num_workers=1)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=True, num_workers=1)class CNN_TSC(nn.Module):def __init__(self):super(CNN_TSC, self).__init__()self.conv1 = nn.Conv2d(3, 6, 5)self.pool = nn.MaxPool2d(2, 2)self.conv2 = nn.Conv2d(6, 16, 5)self.fc1 = nn.Linear(16 * 5 * 5, 120)self.fc2 = nn.Linear(120, 84)self.fc3 = nn.Linear(84, 62)def forward(self, x):x = self.pool(F.relu(self.conv1(x)))x = self.pool(F.relu(self.conv2(x)))x = x.view(-1, 16 * 5 * 5)x = F.relu(self.fc1(x))x = F.relu(self.fc2(x))output = self.fc3(x)return outputnet= CNN_TSC().to(device)
#定义损失函数和优化器
loss = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(net.parameters(), lr=0.001)#训练
def train():net.train()for data, label in train_loader:data, label = data.to(device), label.to(device)net.zero_grad()output = net(data)l = loss(output, label)l.backward()optimizer.step()
#测试
def test(epoch):net.eval()batch_loss, correct, total = 0,0 ,0for data, label in test_loader:data, label = data.to(device), label.to(device)output = net(data)batch_loss +=loss(output, label)predict_label = torch.argmax(output, dim=1)correct += torch.sum(predict_label==label)total +=len(label)print('epoch:%d loss: %.4f  accuracy:%.2f%%' %(epoch, batch_loss/len(test_loader), 100*correct/total))print('training on %s'%(device))
for epoch in range(10):train()test(epoch)

BelgiumTS交通数据集分类-pytorch版相关推荐

卷积神经网络（VGG-11）识别Fashion-MNIST数据集（Pytorch版）
卷积神经网络(VGG-11)识别Fashion-MNIST数据集(Pytorch版) 1. 前言 1.1 案例介绍 1.2 环境配置 1.3 模块导入 2. 图像数据准备 2.1 训练验证集的准备 2 ...
TensorFlow实战（四）——交通标志牌（BelgiumTS交通数据集）的识别（一）
前言: 本系列将学习基于TensorFlow,利用比利时交通标志数据集--BelgiumTS交通信号数据集(包含62种交通信号),进行训练简单的卷积神经网络完成识别.本文将介绍如何下载BelgiumT ...
【NLP】文本分类TorchText实战-AG_NEWS 新闻主题分类任务（PyTorch版）
AG_NEWS 新闻主题分类任务(PyTorch版) 前言 1. 使用 N 元组加载数据 2. 安装 Torch-GPU&TorchText 3. 访问原始数据集迭代器 4. 准备数据处理管道 ...
使用pytorch版faster-rcnn训练自己数据集
使用pytorch版faster-rcnn训练自己数据集引言 faster-rcnn pytorch代码下载训练自己数据集接下来工作参考文献引言最近在复现目标检测代码(师兄强烈推荐FPN, ...
WIN10 +pytorch版yolov3训练自己数据集
pytorch版yolov3训练自己数据集目录 1. 环境搭建 2. 数据集构建 3. 训练模型 4. 测试模型 5. 评估模型 6. 可视化 7. 高级进阶-网络结构更改 1. 环境搭建将git ...
【深度学习笔记】自建交通标志分类数据集转换为MNIST数据格式
文章目录前言一.自建交通标志分类数据集并做预处理 1.RGB图像转灰度图像 2.灰度图像缩放为28*28尺寸二.转换为MNIST数据格式 1.转换代码如下 2.转换过程打印如下 3.最终转换结果 ...
Pytorch采用AlexNet实现猫狗数据集分类（训练与预测）
Pytorch采用AlexNet实现猫狗数据集分类(训练与预测) 介绍 AlexNet网络模型猫狗数据集 AlexNet网络训练训练全代码预测预测图片介绍 AlexNet模型是CNN网络中经 ...
深度学习笔记（2）——pytorch实现MNIST数据集分类（FNN、CNN、RNN、LSTM、GRU）
文章目录 0 前言 1 数据预处理 2 FNN(前馈神经网络) 3 CNN(卷积神经网络) 4 RNN(循环神经网络) 5 LSTM(长短期记忆网络) 6 GRU(门控循环单元) 7 完整代码 0 前 ...
Step by Step演示如何训练Pytorch版的EfficientDet
向AI转型的程序员都关注了这个号???????????? 机器学习AI算法工程公众号:datayx Paper:https://arxiv.org/abs/1911.09070 Base Git ...