运行平台：pycharm

在对数据集进行训练的过程中，为了使网络模型具有更好的鲁棒性，通常我们需要对数据集进行数据增强处理，常见的处理方法有添加噪声、旋转、改变亮度等，如图1，2所示。

图1.原图（coco2017数据集）

图2.数据增强后效果（例）

数据增强代码：

import cv2
import numpy as np
import os.path
import copydef SaltAndPepper(src,percetage):SP_NoiseImg=src.copy()SP_NoiseNum=int(percetage*src.shape[0]*src.shape[1])for i in range(SP_NoiseNum):randR=np.random.randint(0,src.shape[0]-1)randG=np.random.randint(0,src.shape[1]-1)randB=np.random.randint(0,3)if np.random.randint(0,1)==0:SP_NoiseImg[randR,randG,randB]=0else:SP_NoiseImg[randR,randG,randB]=255return SP_NoiseImgdef addGaussianNoise(image,percetage):G_Noiseimg = image.copy()w = image.shape[1]h = image.shape[0]G_NoiseNum=int(percetage*image.shape[0]*image.shape[1])for i in range(G_NoiseNum):temp_x = np.random.randint(0,h)temp_y = np.random.randint(0,w)G_Noiseimg[temp_x][temp_y][np.random.randint(3)] = np.random.randn(1)[0]return G_Noiseimgdef darker(image,percetage=0.9):image_copy = image.copy()w = image.shape[1]h = image.shape[0]#get darkerfor xi in range(0,w):for xj in range(0,h):image_copy[xj,xi,0] = int(image[xj,xi,0]*percetage)image_copy[xj,xi,1] = int(image[xj,xi,1]*percetage)image_copy[xj,xi,2] = int(image[xj,xi,2]*percetage)return image_copydef brighter(image, percetage=1.5):image_copy = image.copy()w = image.shape[1]h = image.shape[0]#get brighterfor xi in range(0,w):for xj in range(0,h):image_copy[xj,xi,0] = np.clip(int(image[xj,xi,0]*percetage),a_max=255,a_min=0)image_copy[xj,xi,1] = np.clip(int(image[xj,xi,1]*percetage),a_max=255,a_min=0)image_copy[xj,xi,2] = np.clip(int(image[xj,xi,2]*percetage),a_max=255,a_min=0)return image_copydef rotate(image, angle, center=None, scale=1.0):(h, w) = image.shape[:2]# If no rotation center is specified, the center of the image is set as the rotation centerif center is None:center = (w / 2, h / 2)m = cv2.getRotationMatrix2D(center, angle, scale)rotated = cv2.warpAffine(image, m, (w, h))return rotateddef flip(image):flipped_image = np.fliplr(image)return flipped_imagefile_dir = "img/"
for img_name in os.listdir(file_dir):img_path = file_dir + img_nameimg = cv2.imread(img_path)rotated_90 = rotate(img, 90)cv2.imwrite(file_dir + img_name[0:-4] + '_r90.jpg', rotated_90)rotated_180 = rotate(img, 180)cv2.imwrite(file_dir + img_name[0:-4] + '_r180.jpg', rotated_180)for img_name in os.listdir(file_dir):img_path = file_dir + img_nameimg = cv2.imread(img_path)flipped_img = flip(img)cv2.imwrite(file_dir +img_name[0:-4] + '_fli.jpg', flipped_img)img_salt = SaltAndPepper(img, 0.3)cv2.imwrite(file_dir + img_name[0:7] + '_salt.jpg', img_salt)img_gauss = addGaussianNoise(img, 0.3)cv2.imwrite(file_dir + img_name[0:-4] + '_noise.jpg',img_gauss)img_darker = darker(img)cv2.imwrite(file_dir + img_name[0:-4] + '_darker.jpg', img_darker)img_brighter = brighter(img)cv2.imwrite(file_dir + img_name[0:-4] + '_brighter.jpg', img_brighter)blur = cv2.GaussianBlur(img, (7, 7), 1.5)cv2.imwrite(file_dir + img_name[0:-4] + '_blur.jpg',blur)