pytorch实现图像识别(实战)
作者:AI?AX?AT 时间:2022-10-03 01:19:03
1. 代码讲解
1.1 导库
import os.path
from os import listdir
import numpy as np
import pandas as pd
from PIL import Image
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.nn import AdaptiveAvgPool2d
from torch.utils.data.sampler import SubsetRandomSampler
from torch.utils.data import Dataset
import torchvision.transforms as transforms
from sklearn.model_selection import train_test_split
1.2 标准化、transform、设置GPU
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
normalize = transforms.Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]
)
transform = transforms.Compose([transforms.ToTensor(), normalize]) # 转换
1.3 预处理数据
class DogDataset(Dataset):
# 定义变量
def __init__(self, img_paths, img_labels, size_of_images):
self.img_paths = img_paths
self.img_labels = img_labels
self.size_of_images = size_of_images
# 多少长图片
def __len__(self):
return len(self.img_paths)
# 打开每组图片并处理每张图片
def __getitem__(self, index):
PIL_IMAGE = Image.open(self.img_paths[index]).resize(self.size_of_images)
TENSOR_IMAGE = transform(PIL_IMAGE)
label = self.img_labels[index]
return TENSOR_IMAGE, label
print(len(listdir(r'C:\Users\AIAXIT\Desktop\DeepLearningProject\Deep_Learning_Data\dog-breed-identification\train')))
print(len(pd.read_csv(r'C:\Users\AIAXIT\Desktop\DeepLearningProject\Deep_Learning_Data\dog-breed-identification\labels.csv')))
print(len(listdir(r'C:\Users\AIAXIT\Desktop\DeepLearningProject\Deep_Learning_Data\dog-breed-identification\test')))
train_paths = []
test_paths = []
labels = []
# 训练集图片路径
train_paths_lir = r'C:\Users\AIAXIT\Desktop\DeepLearningProject\Deep_Learning_Data\dog-breed-identification\train'
for path in listdir(train_paths_lir):
train_paths.append(os.path.join(train_paths_lir, path))
# 测试集图片路径
labels_data = pd.read_csv(r'C:\Users\AIAXIT\Desktop\DeepLearningProject\Deep_Learning_Data\dog-breed-identification\labels.csv')
labels_data = pd.DataFrame(labels_data)
# 把字符标签离散化,因为数据有120种狗,不离散化后面把数据给模型时会报错:字符标签过多。把字符标签从0-119编号
size_mapping = {}
value = 0
size_mapping = dict(labels_data['breed'].value_counts())
for kay in size_mapping:
size_mapping[kay] = value
value += 1
# print(size_mapping)
labels = labels_data['breed'].map(size_mapping)
labels = list(labels)
# print(labels)
print(len(labels))
# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(train_paths, labels, test_size=0.2)
train_set = DogDataset(X_train, y_train, (32, 32))
test_set = DogDataset(X_test, y_test, (32, 32))
train_loader = torch.utils.data.DataLoader(train_set, batch_size=64)
test_loader = torch.utils.data.DataLoader(test_set, batch_size=64)
1.4 建立模型
class LeNet(nn.Module):
def __init__(self):
super(LeNet, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(in_channels=3, out_channels=6, kernel_size=5),
nn.ReLU(),
nn.AvgPool2d(kernel_size=2, stride=2),
nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5),
nn.ReLU(),
nn.AvgPool2d(kernel_size=2, stride=2)
)
self.classifier = nn.Sequential(
nn.Linear(16 * 5 * 5, 120),
nn.ReLU(),
nn.Linear(120, 84),
nn.ReLU(),
nn.Linear(84, 120)
)
def forward(self, x):
batch_size = x.shape[0]
x = self.features(x)
x = x.view(batch_size, -1)
x = self.classifier(x)
return x
model = LeNet().to(device)
criterion = nn.CrossEntropyLoss().to(device)
optimizer = optim.Adam(model.parameters())
TRAIN_LOSS = [] # 损失
TRAIN_ACCURACY = [] # 准确率
1.5 训练模型
def train(epoch):
model.train()
epoch_loss = 0.0 # 损失
correct = 0 # 精确率
for batch_index, (Data, Label) in enumerate(train_loader):
# 扔到GPU中
Data = Data.to(device)
Label = Label.to(device)
output_train = model(Data)
# 计算损失
loss_train = criterion(output_train, Label)
epoch_loss = epoch_loss + loss_train.item()
# 计算精确率
pred = torch.max(output_train, 1)[1]
train_correct = (pred == Label).sum()
correct = correct + train_correct.item()
# 梯度归零、反向传播、更新参数
optimizer.zero_grad()
loss_train.backward()
optimizer.step()
print('Epoch: ', epoch, 'Train_loss: ', epoch_loss / len(train_set), 'Train correct: ', correct / len(train_set))
1.6 测试模型
和训练集差不多。
def test():
model.eval()
correct = 0.0
test_loss = 0.0
with torch.no_grad():
for Data, Label in test_loader:
Data = Data.to(device)
Label = Label.to(device)
test_output = model(Data)
loss = criterion(test_output, Label)
pred = torch.max(test_output, 1)[1]
test_correct = (pred == Label).sum()
correct = correct + test_correct.item()
test_loss = test_loss + loss.item()
print('Test_loss: ', test_loss / len(test_set), 'Test correct: ', correct / len(test_set))
1.7结果
epoch = 10
for n_epoch in range(epoch):
train(n_epoch)
test()
来源:https://blog.csdn.net/weixin_45758642/article/details/119764959
标签:pytorch,实现,图像,识别
![](/images/zang.png)
![](/images/jiucuo.png)
猜你喜欢
Python 恐龙跑跑小游戏实现流程
2021-10-23 19:42:59
![](https://img.aspxhome.com/file/2023/9/66889_0s.png)
asp.net中通过ALinq让Mysql操作变得如此简单
2024-01-21 06:53:41
![](https://img.aspxhome.com/file/2023/5/77195_0s.jpg)
JS正则(RegExp)判断文本框中是否包含特殊符号
2023-05-12 18:18:55
PHP+Ajax简单get验证操作示例
2024-05-13 09:24:27
![](https://img.aspxhome.com/file/2023/9/125809_0s.png)
vue项目持久化存储数据的实现代码
2024-04-27 15:59:48
Python中偏函数用法示例
2022-10-13 18:48:26
网站设计配色方案教程
2007-10-10 19:38:00
![](https://img.aspxhome.com/file/UploadPic/up/2007101019571461.jpg)
JavaScript ES6中const、let与var的对比详解
2024-05-22 10:37:36
八个有用的WordPress的SQL语句
2009-01-12 18:54:00
详解利用上下文管理器扩展Python计时器
2023-11-07 09:33:48
跟老齐学Python之复习if语句
2022-03-20 19:33:20
Python实现动态绘图的示例详解
2021-07-08 16:44:40
![](https://img.aspxhome.com/file/2023/5/93615_0s.gif)
MDB格式网站文件如何解压
2008-07-02 12:48:00
Python 使用 pip 安装 matplotlib 模块的方法
2021-08-22 02:42:52
![](https://img.aspxhome.com/file/2023/0/79430_0s.png)
css学习笔记: css新闻列表的特殊做法
2009-07-19 14:25:00
![](https://img.aspxhome.com/file/UploadPic/20097/19/11e89610908g215-71s.jpg)
Python聚类算法之DBSACN实例分析
2021-03-26 00:11:10
![](https://img.aspxhome.com/file/2023/7/120607_0s.png)
用CSS3和HTML5五步打造便签效果
2012-04-25 20:47:51
JavaScript 函数惰性载入的实现及其优点介绍
2024-04-16 09:25:37
python通过ElementTree操作XML
2021-01-09 09:12:20
使用python对泰坦尼克号幸存者进行数据分析与预测
2022-09-07 09:29:42
![](https://img.aspxhome.com/file/2023/6/131726_0s.png)