mixup 数据增强

将2张图像按照一定比例进行混合，常用于图像分类。

 原图如下：

 mixup后：

 按照0.5的比例进行混合。

代码如下：

import cv2

image1 = cv2.imread('hongxiancai125.jpg')
image1 = cv2.resize(image1,(600,600))
image2 = cv2.imread('huluobo1.jpg')
image2 = cv2.resize(image2,(600,600))
new_image = image1*0.5 + image2*0.5

cv2.imwrite('mixup.jpg', new_image)

 随机比例alpha：

import numpy as np

# alpha为混合的比例
lam = np.random.beta(alpha, alpha)

使用到分类中：

alpha = 1.0  # 默认设置为1
criterion = nn.CrossEntropyLoss()
for (inputs, labels) in train_loader:
    lam = np.random.beta(alpha, alpha)
    index = torch.randperm(inputs.size(0))
    images_a, images_b = inputs, inputs[index]
    labels_a, labels_b = labels, labels[index]
    mixed_images = lam * images_a + (1 - lam) * images_b
    outputs = model(mixed_images)
    _, preds = torch.max(outputs, 1)
    loss = lam * criterion(outputs, labels_a) + (1 - lam) * criterion(outputs, labels_b)