目录

一、什么是数据增强

二、为什么要使用数据增强

三、数据增强的代码实现

一、什么是数据增强

在深度学习中，数据增强是通过一定的方式改变输入数据，以生成更多的训练样本，从而提高模型的泛化能力和效果。数据增强可以减少模型对某些特征的过度依赖，从而避免过拟合。

二、为什么要使用数据增强

在深度学习中，要求样本数量充足，样本数量越多，训练出来的模型效果越好，模型的泛化能力越强。但是实际中，样本数量不足或者样本质量不够好，这时就需要对样本做数据增强，来提高样本质量。

例如在图像分类任务中，对于输入的图像可以进行一些简单的平移、缩放、颜色变换等操作，这些操作不会改变图像的类别，但可以增加训练样本的数量。这些增强后的样本可以帮助模型更好地学习和理解图像的特征，提高模型的泛化能力和准确率。

三、数据增强的代码实现

未使用数据增强的代码及结果展示：

讯享网

import torch from torch.utils.data import Dataset, DataLoader import numpy as np from PIL import Image from torchvision import transforms data_transforms = { 'train': transforms.Compose([ transforms.Resize([256, 256]), transforms.ToTensor(), ]), 'valid': transforms.Compose([ transforms.Resize([256, 256]), transforms.ToTensor(), ]), } class food_dataset(Dataset): def __init__(self, file_path, transform=None): self.file_path = file_path self.imgs = [] self.labels = [] self.transform = transform with open(self.file_path) as f: samples = [x.strip().split(' ') for x in f.readlines()] for img_path, label in samples: self.imgs.append(img_path) self.labels.append(label) def __len__(self): return len(self.imgs) def __getitem__(self, idx): image = Image.open(self.imgs[idx]) if self.transform: image = self.transform(image) label = self.labels[idx] label = torch.from_numpy(np.array(label, dtype=np.int64)) return image, label training_data = food_dataset(file_path='.\\train.txt', transform=data_transforms['train']) test_data = food_dataset(file_path='.\\test.txt', transform=data_transforms['valid']) train_dataloader = DataLoader(training_data, batch_size=128, shuffle=True) test_dataloader = DataLoader(test_data, batch_size=128, shuffle=True) # from matplotlib import pyplot as plt # image, label = iter(train_dataloader).__next__() # sample = image[2] # sample = sample.permute((1, 2, 0)).numpy() # plt.imshow(sample) # plt.show() # print('Label is: {}'.format(label[2].numpy())) import torch device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu" print(f"Using {device} device") # device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # print(device) # import os # # os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID" # os.environ["CUDA_VISIBLE_DEVICES"] = '1' from torch import nn class CNN(nn.Module): def __init__(self): super(CNN, self).__init__() self.conv1 = nn.Sequential( nn.Conv2d( in_channels=3, out_channels=16, kernel_size=5, stride=1, padding=2, ), nn.ReLU(), nn.MaxPool2d(kernel_size=2), ) self.conv2 = nn.Sequential( nn.Conv2d(16, 32, 5, 1, 2), nn.ReLU(), nn.Conv2d(32, 32, 5, 1, 2), nn.ReLU(), nn.MaxPool2d(2), ) self.conv3 = nn.Sequential( nn.Conv2d(32, 64, 5, 1, 2), nn.ReLU(), ) self.out = nn.Linear(64 * 64 * 64, 20) def forward(self, x): x = self.conv1(x) x = self.conv2(x) x = self.conv3(x) x = x.view(x.size(0), -1) output = self.out(x) return output model = CNN().to(device) print(model) def train(dataloader, model, loss_fn, optimizer): model.train() batch_size_num = 1 for x, y in dataloader: x, y = x.to(device), y.to(device) pred = model.forward(x) loss = loss_fn(pred, y) optimizer.zero_grad() loss.backward() optimizer.step() loss = loss.item() if batch_size_num % 100 == 0: print(f"loss: {loss:>7f} [number:{batch_size_num}]") batch_size_num += 1 def test(dataloader, model, loss_fn): size = len(dataloader.dataset) num_batches = len(dataloader) model.eval() # test_loss, correct = 0, 0 with torch.no_grad(): for x, y in dataloader: x, y = x.to(device), y.to(device) pred = model.forward(x) test_loss += loss_fn(pred, y).item() correct += (pred.argmax(1) == y).type(torch.float).sum().item() a = (pred.argmax(1) == y) b = (pred.argmax(1) == y).type(torch.float) test_loss /= num_batches correct /= size print(f"Test result: \n Accuracy: {(100 * correct)}%, Avg loss: {test_loss}") acc_s.append(correct) loss_s.append(test_loss) loss_fn = nn.CrossEntropyLoss() optimizer = torch.optim.Adam(model.parameters(), lr=0.001) # train(train_dataloader, model, loss_fn, optimizer) # test(test_dataloader, model, loss_fn) epochs = 50 acc_s = [] loss_s = [] for t in range(epochs): print(f"Epoch {t + 1}\n-------------------------------") train(train_dataloader, model, loss_fn, optimizer) test(test_dataloader, model, loss_fn) # print("Done!") # test(test_dataloader, model, loss_fn) from matplotlib import pyplot as plt plt.subplot(1, 2, 1) plt.plot(range(0, epochs), acc_s) plt.xlabel("epoch") plt.ylabel('accuracy') plt.subplot(1, 2, 2) plt.plot(range(0, epochs), loss_s) plt.xlabel("epoch") plt.ylabel('loss') plt.show()

其结果展示为：

使用了数据增强即在这串代码里做出更改

讯享网data_transforms = { 'train': transforms.Compose([ transforms.Resize([256, 256]), transforms.ToTensor(), ]), 'valid': transforms.Compose([ transforms.Resize([256, 256]), transforms.ToTensor(), ]), } 

将其更改为：

data_transforms = { # 也可以使用PIL库，smote 人工拟合出来数据 'train': transforms.Compose([ transforms.Resize([300, 300]), # 是图像变换大小 transforms.RandomRotation(45), # 随机旋转，-45到45度之间随机选 transforms.CenterCrop(256), # 从中心开始裁剪[256,256] transforms.RandomHorizontalFlip(p=0.5), # 随机水平翻转 选择一个概率概率 transforms.RandomVerticalFlip(p=0.5), # 随机垂直翻转 transforms.ColorJitter(brightness=0.2, contrast=0.1, saturation=0.1, hue=0.1), # 参数1为亮度，参数2为对比度，参数3为饱和度，参数4为色相 transforms.RandomGrayscale(p=0.1), # 概率转换成灰度率，3通道就是R=G=B transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) # 标准化，均值，标准差 ]), 'valid': transforms.Compose([ transforms.Resize([256, 256]), transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]), }

更改完成后，结果展示为：

对比比较发现，不在产生梯度爆炸，且准确率更高。