传统数据增强

import torchvision.transforms as T
import matplotlib.pyplot as plt
import PIL.Image as Image
import numpy as np


plt.figure(figsize=(10, 10), dpi=100)
orig_img = Image.open("C:/Users/ZMZ/Desktop/cat.jpeg")


#图像大小的调整
resized_imgs = [T.Resize(size=size)(orig_img) for size in [128,256]]
# plt.figure('resize:128*128')
ax1 = plt.subplot(131)
ax1.set_title('original')
ax1.imshow(orig_img)

ax2 = plt.subplot(132)
ax2.set_title('resize:128*128')
ax2.imshow(resized_imgs[0])

ax3 = plt.subplot(133)
ax3.set_title('resize:256*256')
ax3.imshow(resized_imgs[1])

plt.savefig('image_resize.svg', dpi=200,bbox_inches='tight')


# 灰度变换
gray_img = T.Grayscale()(orig_img)
# plt.figure('resize:128*128')
ax1 = plt.subplot(121)
ax1.set_title('original')
ax1.imshow(orig_img)

ax2 = plt.subplot(122)
ax2.set_title('gray')
ax2.imshow(gray_img,cmap='gray')
plt.savefig('image_gray.svg', dpi=200,bbox_inches='tight')

# 标准化
normalized_img = T.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))(T.ToTensor()(orig_img))
normalized_img = [T.ToPILImage()(normalized_img)]
# plt.figure('resize:128*128')
ax1 = plt.subplot(121)
ax1.set_title('original')
ax1.imshow(orig_img)

ax2 = plt.subplot(122)
ax2.set_title('normalize')
ax2.imshow(normalized_img[0])
plt.savefig('image_normalize.svg', dpi=200,bbox_inches='tight')

# 随机旋转
rotated_imgs = [T.RandomRotation(degrees=90)(orig_img)]
print(rotated_imgs)
plt.figure('resize:128*128')
ax1 = plt.subplot(121)
ax1.set_title('original')
ax1.imshow(orig_img)

ax2 = plt.subplot(122)
ax2.set_title('90°')
ax2.imshow(np.array(rotated_imgs[0]))
plt.savefig('image_rotation.svg', dpi=200,bbox_inches='tight')

# 中心剪切
center_crops = [T.CenterCrop(size=size)(orig_img) for size in (128,64)]

plt.figure('resize:128*128')
ax1 = plt.subplot(131)
ax1.set_title('original')
ax1.imshow(orig_img)

ax2 = plt.subplot(132)
ax2.set_title('128*128°')
ax2.imshow(np.array(center_crops[0]))

ax3 = plt.subplot(133)
ax3.set_title('64*64')
ax3.imshow(np.array(center_crops[1]))
plt.savefig('image_center_crop.svg', dpi=200,bbox_inches='tight')

# 随机裁剪
random_crops = [T.RandomCrop(size=size)(orig_img) for size in (400,300)]

plt.figure('resize:128*128')
ax1 = plt.subplot(131)
ax1.set_title('original')
ax1.imshow(orig_img)

ax2 = plt.subplot(132)
ax2.set_title('400*400')
ax2.imshow(np.array(random_crops[0]))

ax3 = plt.subplot(133)
ax3.set_title('300*300')
ax3.imshow(np.array(random_crops[1]))
plt.savefig('image_random_crop.svg', dpi=200,bbox_inches='tight')

# 高斯模糊
blurred_imgs = [T.GaussianBlur(kernel_size=(3, 3), sigma=sigma)(orig_img) for sigma in (3,7)]

plt.figure('resize:128*128')
ax1 = plt.subplot(131)
ax1.set_title('original')
ax1.imshow(orig_img)

ax2 = plt.subplot(132)
ax2.set_title('sigma=3')
ax2.imshow(np.array(blurred_imgs[0]))

ax3 = plt.subplot(133)
ax3.set_title('sigma=7')
ax3.imshow(np.array(blurred_imgs[1]))

plt.axis('off')
plt.savefig('image_blur.svg', dpi=200,bbox_inches='tight')

# 亮度、对比度和饱和度调节
colorjitter_img = [T.ColorJitter(brightness=(2,2), contrast=(0.5,0.5), saturation=(0.5,0.5))(orig_img)]

plt.figure('resize:128*128')
ax1 = plt.subplot(121)
ax1.set_title('original')
ax1.imshow(orig_img)
ax2 = plt.subplot(122)
ax2.set_title('colorjitter_img')
ax2.imshow(np.array(colorjitter_img[0]))
plt.savefig('image_colorjitter.svg', dpi=200,bbox_inches='tight')


# 水平翻转
HorizontalFlip_img = [T.RandomHorizontalFlip(p=1)(orig_img)]

plt.figure('resize:128*128')
ax1 = plt.subplot(121)
ax1.set_title('original')
ax1.imshow(orig_img)

ax2 = plt.subplot(122)
ax2.set_title('horizontal_flip_img')
ax2.imshow(np.array(HorizontalFlip_img[0]))
plt.savefig('image_horizontal_flip.svg', dpi=200,bbox_inches='tight')

# 垂直翻转
VerticalFlip_img = [T.RandomVerticalFlip(p=1)(orig_img)]

plt.figure('resize:128*128')
ax1 = plt.subplot(121)
ax1.set_title('original')
ax1.imshow(orig_img)

ax2 = plt.subplot(122)
ax2.set_title('VerticalFlip')
ax2.imshow(np.array(VerticalFlip_img[0]))
plt.savefig('image_vertical_flip.svg', dpi=200,bbox_inches='tight')

# 高斯噪声
def add_noise(inputs, noise_factor=0.3):
    noisy = inputs + torch.randn_like(inputs) * noise_factor
    noisy = torch.clip(noisy, 0., 1.)
    return noisy


noise_imgs = [add_noise(T.ToTensor()(orig_img), noise_factor) for noise_factor in (0.3, 0.6)]
noise_imgs = [T.ToPILImage()(noise_img) for noise_img in noise_imgs]

plt.figure('resize:128*128')
ax1 = plt.subplot(131)
ax1.set_title('original')
ax1.imshow(orig_img)

ax2 = plt.subplot(132)
ax2.set_title('noise_factor=0.3')
ax2.imshow(np.array(noise_imgs[0]))

ax3 = plt.subplot(133)
ax3.set_title('noise_factor=0.6')
ax3.imshow(np.array(noise_imgs[1]))
plt.savefig('image_noise.svg', dpi=200,bbox_inches='tight')

# 随即块
def add_random_boxes(img,n_k,size=64):
    h,w = size,size
    img = np.asarray(img).copy()
    img_size = img.shape[1]
    boxes = []
    for k in range(n_k):
        y,x = np.random.randint(0,img_size-w,(2,))
        img[y:y+h,x:x+w] = 0
        boxes.append((x,y,h,w))
    img = Image.fromarray(img.astype('uint8'), 'RGB')
    return img

blocks_imgs = [add_random_boxes(orig_img,n_k=10)]

plt.figure('resize:128*128')
ax1 = plt.subplot(131)
ax1.set_title('original')
ax1.imshow(orig_img)
# ax1.axis('off')
ax2 = plt.subplot(132)
ax2.set_title('10 black boxes')
ax2.imshow(np.array(blocks_imgs[0]))
# ax2.axis('off')
plt.savefig('image_random_box.svg', dpi=200,bbox_inches='tight')

# 中心块
def add_central_region(img, size=32):
    h, w = size, size
    img = np.asarray(img).copy()
    img_size = img.shape[1]
    img[int(img_size / 2 - h):int(img_size / 2 + h), int(img_size / 2 - w):int(img_size / 2 + w)] = 0
    img = Image.fromarray(img.astype('uint8'), 'RGB')
    return img


central_imgs = [add_central_region(orig_img, size=128)]


plt.figure('resize:128*128')
ax1 = plt.subplot(131)
ax1.set_title('original')
ax1.imshow(orig_img)

ax2 = plt.subplot(132)
ax2.set_title('center box')
ax2.imshow(np.array(central_imgs[0]))

plt.savefig('image_center_box.svg', dpi=200,bbox_inches='tight')

参考：

https://mp.weixin.qq.com/s/EMJHdDK5asJJp2yELVBygQ