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()
到此这篇关于pytorch实现图像识别(实战)的文章就介绍到这了,更多相关pytorch实现图像识别内容请搜索以前的文章或继续浏览下面的相关文章希望大家以后多多支持！
查看更多关于pytorch实现图像识别(实战)的详细内容...
声明：本文来自网络，不代表【好得很程序员自学网】立场，转载请注明出处：http://haodehen.cn/did99971