深度学习-数据增强策略

数据增强策略:
	1 在线模式--训练中
		随机裁剪(完全随机,四个角+中心)  crop
		def random_crop(img, scale=[0.8, 1.0], ratio=[3. / 4., 4. / 3.], resize_w=100, resize_h=100):
			"""
			随机裁剪
			:param img:
			:param scale: 缩放
			:param ratio:
			:param resize_w:
			:param resize_h:
			:return:
			"""
			aspect_ratio = math.sqrt(np.random.uniform(*ratio))
			w = 1. * aspect_ratio
			h = 1. / aspect_ratio
			src_h, src_w = img.shape[:2]

			bound = min((float(src_w) / src_h) / (w ** 2),
						(float(src_h) / src_w) / (h ** 2))
			scale_max = min(scale[1], bound)
			scale_min = min(scale[0], bound)

			target_area = src_h * src_w * np.random.uniform(scale_min,
															scale_max)
			target_size = math.sqrt(target_area)
			w = int(target_size * w)
			h = int(target_size * h)

			i = np.random.randint(0, src_w - w + 1)
			j = np.random.randint(0, src_h - h + 1)

			img = img[j:j + h, i:i + w]
			img = cv2.resize(img, (resize_w, resize_h))
			return img


		def rule_crop(img, box_ratio=(3. / 4, 3. / 4), location_type='LT', resize_w=100, resize_h=100):
			"""
			按照一定规则进行裁剪, 直接在原图尺寸上操作,不对原图进行
			:param img:
			:param box_ratio: 剪切的 比例:  (宽度上的比例, 高度上的比例)
			:param location_type: 具体在=哪个位置: 以下其中一个:
					LR : 左上角
					RT : 右上角
					LB : 左下角
					RB : 右下角
					CC : 中心
			:param resize_w: 输出图的width
			:param resize_h: 输出图的height
			:return:
			"""
			assert location_type in ('LT', 'RT', 'LB', 'RB', 'CC'), 'must have a location .'
			is_gray = False
			if len(img.shape) == 3:
				h, w, c = img.shape
			elif len(img.shape) == 2:
				h, w = img.shape
				is_gray = True

			crop_w, crop_h = int(w * box_ratio[0]), int(h * box_ratio[1])
			crop_img = np.zeros([10, 10])
			if location_type == 'LT':
				crop_img = img[:crop_h, :crop_w, :] if not is_gray else img[:crop_h, :crop_w]
			elif location_type == 'RT':
				crop_img = img[:crop_h:, w - crop_w:, :] if not is_gray else img[:crop_h:, w - crop_w:]
			elif location_type == 'LB':
				crop_img = img[h - crop_h:, :crop_w, :] if not is_gray else img[h - crop_h:, :crop_w]
			elif location_type == 'RB':
				crop_img = img[h - crop_h:, w - crop_w:, :] if not is_gray else img[h - crop_h:, w - crop_w:]
			elif location_type == 'CC':
				start_h = (h - crop_h) // 2
				start_w = (w - crop_w) // 2
				crop_img = img[start_h:start_h + crop_h, start_w:start_w + crop_w, :] if not is_gray else img[
																										  start_h:start_h + crop_h,
																										  start_w:start_w + crop_w]

			resize = cv2.resize(crop_img, (resize_w, resize_h))
			return resize
		水平翻转  flip
		def random_flip(img, mode=1):
			"""
			随机翻转
			:param img:
			:param model: 1=水平翻转 / 0=垂直 / -1=水平垂直
			:return:
			"""
			assert mode in (0, 1, -1), "mode is not right"
			flip = np.random.choice(2) * 2 - 1  # -1 / 1
			if mode == 1:
				img = img[:, ::flip, :]
			elif mode == 0:
				img = img[::flip, :, :]
			elif mode == -1:
				img = img[::flip, ::flip, :]

			return img


		def flip(img, mode=1):
			"""
			翻转
			:param img:
			:param mode: 1=水平翻转 / 0=垂直 / -1=水平垂直
			:return:
			"""
			assert mode in (0, 1, -1), "mode is not right"
			return cv2.flip(img, flipCode=mode)
	2 离线模式
		2.1 随机扰动
			噪声(高斯、自定义)  noise
            def random_noise(img, rand_range=(3, 20)):
                """
                随机噪声
                :param img:
                :param rand_range: (min, max)
                :return:
                """
                img = np.asarray(img, np.float)
                sigma = random.randint(*rand_range)
                nosie = np.random.normal(0, sigma, size=img.shape)
                img += nosie
                img = np.uint8(np.clip(img, 0, 255))
                return img

			滤波(高斯、平滑、均值、中值、最大最小值、双边、引导、运动)
			# 各种滤波原理介绍:https://blog.csdn.net/hellocsz/article/details/80727972
            def gaussianBlue(img, ks=(7, 7), stdev=1.5):
                """
                高斯模糊, 可以对图像进行平滑处理,去除尖锐噪声
                :param img:
                :param ks:  卷积核
                :param stdev: 标准差
                :return:
                """
                return cv2.GaussianBlur(img, (7, 7), 1.5)

		2.2 转换
			旋转  rorate
            def rotate(img, angle, scale=1.0):
                """
                旋转
                :param img:
                :param angle: 旋转角度, >0 表示逆时针,
                :param scale:
                :return:
                """
                height, width = img.shape[:2]  # 获取图像的高和宽
                center = (width / 2, height / 2)  # 取图像的中点

                M = cv2.getRotationMatrix2D(center, angle, scale)  # 获得图像绕着某一点的旋转矩阵
                # cv2.warpAffine()的第二个参数是变换矩阵,第三个参数是输出图像的大小
                rotated = cv2.warpAffine(img, M, (height, width))
                return rotated


            def random_rotate(img, angle_range=(-10, 10)):
                """
                随机旋转
                :param img:
                :param angle_range:  旋转角度范围 (min,max)   >0 表示逆时针,
                :return:
                """
                height, width = img.shape[:2]  # 获取图像的高和宽
                center = (width / 2, height / 2)  # 取图像的中点
                angle = random.randrange(*angle_range, 1)
                M = cv2.getRotationMatrix2D(center, angle, 1.0)  # 获得图像绕着某一点的旋转矩阵
                # cv2.warpAffine()的第二个参数是变换矩阵,第三个参数是输出图像的大小
                rotated = cv2.warpAffine(img, M, (height, width))
                return rotated
			偏移  shift
            def shift(img, x_offset, y_offset):
                """
                偏移,向右 向下
                :param img:
                :param x_offset:  >0表示向右偏移px, <0表示向左
                :param y_offset:  >0表示向下偏移px, <0表示向上
                :return:
                """
                h, w, _ = img.shape
                M = np.array([[1, 0, x_offset], [0, 1, y_offset]], dtype=np.float)
                return cv2.warpAffine(img, M, (w, h))
			扭曲  skew
            ...
			缩放  scale
            def resize_img(img, resize_w, resize_h):
                height, width = img.shape[:2]  # 获取图片的高和宽
                return cv2.resize(img, (resize_w, resize_h), interpolation=cv2.INTER_CUBIC)
			RGB/BGR->HSV
            def rgb2hsv_py(r, g, b):
                # from https://blog.csdn.net/weixin_43360384/article/details/84871521
                r, g, b = r/255.0, g/255.0, b/255.0
                mx = max(r, g, b)
                mn = min(r, g, b)
                m = mx-mn
                if mx == mn:
                    h = 0
                elif mx == r:
                    if g >= b:
                        h = ((g-b)/m)*60
                    else:
                        h = ((g-b)/m)*60 + 360
                elif mx == g:
                    h = ((b-r)/m)*60 + 120
                elif mx == b:
                    h = ((r-g)/m)*60 + 240
                if mx == 0:
                    s = 0
                else:
                    s = m/mx
                v = mx
                return h, s, v
            def rgb2hsv_cv(img):
                # from https://blog.csdn.net/qq_38332453/article/details/89258058
                h = img.shape[0]
                w = img.shape[1]
                H = np.zeros((h,w),np.float32)
                S = np.zeros((h, w), np.float32)
                V = np.zeros((h, w), np.float32)
                r,g,b = cv2.split(img)
                r, g, b = r/255.0, g/255.0, b/255.0
                for i in range(0, h):
                    for j in range(0, w):
                        mx = max((b[i, j], g[i, j], r[i, j]))
                        mn = min((b[i, j], g[i, j], r[i, j]))
                        V[i, j] = mx
                        if V[i, j] == 0:
                            S[i, j] = 0
                        else:
                            S[i, j] = (V[i, j] - mn) / V[i, j]
                        if mx == mn:
                            H[i, j] = 0
                        elif V[i, j] == r[i, j]:
                            if g[i, j] >= b[i, j]:
                                H[i, j] = (60 * ((g[i, j]) - b[i, j]) / (V[i, j] - mn))
                            else:
                                H[i, j] = (60 * ((g[i, j]) - b[i, j]) / (V[i, j] - mn))+360
                        elif V[i, j] == g[i, j]:
                            H[i, j] = 60 * ((b[i, j]) - r[i, j]) / (V[i, j] - mn) + 120
                        elif V[i, j] == b[i, j]:
                            H[i, j] = 60 * ((r[i, j]) - g[i, j]) / (V[i, j] - mn) + 240
                        H[i,j] = H[i,j] / 2
                return H, S, V
            图片叠加与融合
            def addWeight(src1, alpha, src2, beta, gamma):
                """
                g (x) = (1 − α)f0 (x) + αf1 (x)   #a→(0,1)不同的a值可以实现不同的效果
                dst = src1 * alpha + src2 * beta + gamma
                :param src1: img1
                :param alpha:
                :param src2: img2
                :param beta:
                :param gamma:
                :return:
                """
                assert src1.shap == src2.shape
                return cv2.addWeighted(src1, alpha, src2, beta, gamma)
			颜色抖动(亮度\色度\饱和度\对比度)  color jitter
            def adjust_contrast_bright(img, contrast=1.2, brightness=100):
                """
                调整亮度与对比度
                dst = img * contrast + brightness
                :param img:
                :param contrast: 对比度   越大越亮
                :param brightness: 亮度  0~100
                :return:
                """
                # 像素值会超过0-255, 因此需要截断
                return np.uint8(np.clip((contrast * img + brightness), 0, 255))
            def pytorch_color_jitter(img):
                return torchvision.transforms.ColorJitter(brightness=0, contrast=0, saturation=0, hue=0)
			3D几何变换
			
			

  

上一篇:java-调整RenderedImage的大小


下一篇:C++ std::deque 基本用法