数据增强作为前处理的关键步骤,在整个计算机视觉中有着具足轻重的地位;
数据增强往往是决定数据集质量的关键,主要用于数据增广,在基于深度学习的任务中,数据的多样性和数量往往能够决定模型的上限;
本次记录主要是对数据增强中一些方法的源码实现;
首先如果是使用Pytorch框架,其内部的torchvision已经包装好了数据增强的很多方法;
from torchvision import transforms
data_aug = transforms.Compose[
transforms.Resize(size=240),
transforms.RandomHorizontalFlip(0.5),
transforms.ToTensor()
]
接下来自己实现一些主要的方法;
常见的数据增强方法有:Compose、RandomHflip、RandomVflip、Reszie、RandomCrop、Normalize、Rotate、RandomRotate
作用:对多个方法的排序整合,并且依次调用;
# 排序(compose)
class Compose(object):
def __init__(self, transforms):
self.transforms = transforms
def __call__(self, img):
for t in self.transforms:
img = t(img) # 通过循环不断调用列表中的方法
return img
作用:随机水平翻转;
# 随机水平翻转(random h flip)
class RandomHflip(object):
def __call__(self, image):
if random.randint(2):
return cv2.flip(image, 1)
else:
return image
通过随机数0或1,实现对图像可能反转或不翻转;
作用:随机垂直翻转
class RandomVflip(object):
def __call__(self, image):
if random.randint(2):
return cv2.flip(image, 0)
else:
return image
作用:随机裁剪;
# 缩放(scale)
def scale_down(src_size, size):
w, h = size
sw, sh = src_size
if sh < h:
w, h = float(w * sh) / h, sh
if sw < w:
w, h = sw, float(h * sw) / w
return int(w), int(h)
# 固定裁剪(fixed crop)
def fixed_crop(src, x0, y0, w, h, size=None):
out = src[y0:y0 + h, x0:x0 + w]
if size is not None and (w, h) != size:
out = cv2.resize(out, (size[0], size[1]), interpolation=cv2.INTER_CUBIC)
return out
# 随机裁剪(random crop)
class RandomCrop(object):
def __init__(self, size):
self.size = size
def __call__(self, image):
h, w, _ = image.shape
new_w, new_h = scale_down((w, h), self.size)
if w == new_w:
x0 = 0
else:
x0 = random.randint(0, w - new_w)
if h == new_h:
y0 = 0
else:
y0 = random.randint(0, h - new_h)
out = fixed_crop(image, x0, y0, new_w, new_h, self.size)
return out
作用:对图像数据进行正则化,也就是减均值除方差的作用;
# 正则化(normalize)
class Normalize(object):
def __init__(self,mean, std):
'''
:param mean: RGB order
:param std: RGB order
'''
self.mean = np.array(mean).reshape(3,1,1)
self.std = np.array(std).reshape(3,1,1)
def __call__(self, image):
'''
:param image: (H,W,3) RGB
:return:
'''
return (image.transpose((2, 0, 1)) / 255. - self.mean) / self.std
作用:对图像进行旋转;
# 旋转(rotate)
def rotate_nobound(image, angle, center=None, scale=1.):
(h, w) = image.shape[:2]
# if the center is None, initialize it as the center of the image
if center is None:
center = (w // 2, h // 2) # perform the rotation
M = cv2.getRotationMatrix2D(center, angle, scale) # 这里是实现得到旋转矩阵
rotated = cv2.warpAffine(image, M, (w, h)) # 通过矩阵进行仿射变换
return rotated
作用:随机旋转,广泛适用于图像增强;
# 随机旋转(random rotate)
class FixRandomRotate(object):
# 这里的随机旋转是指在0、90、180、270四个角度下的
def __init__(self, angles=[0,90,180,270], bound=False):
self.angles = angles
self.bound = bound
def __call__(self,img):
do_rotate = random.randint(0, 4)
angle=self.angles[do_rotate]
if self.bound:
img = rotate_bound(img, angle)
else:
img = rotate_nobound(img, angle)
return img
作用:实现缩放;
# 大小重置(resize)
class Resize(object):
def __init__(self, size, inter=cv2.INTER_CUBIC):
self.size = size
self.inter = inter
def __call__(self, image):
return cv2.resize(image, (self.size[0], self.size[0]), interpolation=self.inter)
其他一些数据增强的方法大部分是特殊的裁剪;
1、中心裁剪
# 中心裁剪(center crop)
def center_crop(src, size):
h, w = src.shape[0:2]
new_w, new_h = scale_down((w, h), size)
x0 = int((w - new_w) / 2)
y0 = int((h - new_h) / 2)
out = fixed_crop(src, x0, y0, new_w, new_h, size)
return out
2、随机亮度增强
# 随机亮度增强(random brightness)
class RandomBrightness(object):
def __init__(self, delta=10):
assert delta >= 0
assert delta <= 255
self.delta = delta
def __call__(self, image):
if random.randint(2):
delta = random.uniform(-self.delta, self.delta)
image = (image + delta).clip(0.0, 255.0)
# print('RandomBrightness,delta ',delta)
return image
3、随机对比度增强
# 随机对比度增强(random contrast)
class RandomContrast(object):
def __init__(self, lower=0.9, upper=1.05):
self.lower = lower
self.upper = upper
assert self.upper >= self.lower, "contrast upper must be >= lower."
assert self.lower >= 0, "contrast lower must be non-negative."
# expects float image
def __call__(self, image):
if random.randint(2):
alpha = random.uniform(self.lower, self.upper)
# print('contrast:', alpha)
image = (image * alpha).clip(0.0,255.0)
return image
4、随机饱和度增强
# 随机饱和度增强(random saturation)
class RandomSaturation(object):
def __init__(self, lower=0.8, upper=1.2):
self.lower = lower
self.upper = upper
assert self.upper >= self.lower, "contrast upper must be >= lower."
assert self.lower >= 0, "contrast lower must be non-negative."
def __call__(self, image):
if random.randint(2):
alpha = random.uniform(self.lower, self.upper)
image[:, :, 1] *= alpha
# print('RandomSaturation,alpha',alpha)
return image
4、边界扩充
# 边界扩充(expand border)
class ExpandBorder(object):
def __init__(self, mode='constant', value=255, size=(336,336), resize=False):
self.mode = mode
self.value = value
self.resize = resize
self.size = size
def __call__(self, image):
h, w, _ = image.shape
if h > w:
pad1 = (h-w)//2
pad2 = h - w - pad1
if self.mode == 'constant':
image = np.pad(image, ((0, 0), (pad1, pad2), (0, 0)),
self.mode, constant_values=self.value)
else:
image = np.pad(image,((0,0), (pad1, pad2),(0,0)), self.mode)
elif h < w:
pad1 = (w-h)//2
pad2 = w-h - pad1
if self.mode == 'constant':
image = np.pad(image, ((pad1, pad2),(0, 0), (0, 0)),
self.mode,constant_values=self.value)
else:
image = np.pad(image, ((pad1, pad2), (0, 0), (0, 0)),self.mode)
if self.resize:
image = cv2.resize(image, (self.size[0], self.size[0]),interpolation=cv2.INTER_LINEAR)
return image
当然还有很多其他数据增强的方式,在这里就不继续做说明了;
除了可以使用Pytorch中自带的数据增强包之外,也可以使用imgaug这个包(一个基于数据处理的包、包含大量的数据处理方法,并且代码完全开源)
代码地址:https://github.com/aleju/imgaug
说明文档:https://imgaug.readthedocs.io/en/latest/index.html
强烈建议大家看看这个说明文档,其中的很多数据处理方法可以快速的应用到实际项目中,也可以加深对图像处理的理解;