mosaic数据增强

 

https://blog.csdn.net/weixin_44791964/article/details/105996954?utm_medium=distribute.pc_relevant.none-task-blog-title-8&spm=1001.2101.3001.4242

from PIL import Image, ImageDraw
import numpy as np
from matplotlib.colors import rgb_to_hsv, hsv_to_rgb
import math
def rand(a=0, b=1):
    return np.random.rand()*(b-a) + a

def merge_bboxes(bboxes, cutx, cuty):

    merge_bbox = []
    for i in range(len(bboxes)):
        for box in bboxes[i]:
            tmp_box = []
            x1,y1,x2,y2 = box[0], box[1], box[2], box[3]

            if i == 0:
                if y1 > cuty or x1 > cutx:
                    continue
                if y2 >= cuty and y1 <= cuty:
                    y2 = cuty
                    if y2-y1 < 5:
                        continue
                if x2 >= cutx and x1 <= cutx:
                    x2 = cutx
                    if x2-x1 < 5:
                        continue
                
            if i == 1:
                if y2 < cuty or x1 > cutx:
                    continue

                if y2 >= cuty and y1 <= cuty:
                    y1 = cuty
                    if y2-y1 < 5:
                        continue
                
                if x2 >= cutx and x1 <= cutx:
                    x2 = cutx
                    if x2-x1 < 5:
                        continue

            if i == 2:
                if y2 < cuty or x2 < cutx:
                    continue

                if y2 >= cuty and y1 <= cuty:
                    y1 = cuty
                    if y2-y1 < 5:
                        continue

                if x2 >= cutx and x1 <= cutx:
                    x1 = cutx
                    if x2-x1 < 5:
                        continue

            if i == 3:
                if y1 > cuty or x2 < cutx:
                    continue

                if y2 >= cuty and y1 <= cuty:
                    y2 = cuty
                    if y2-y1 < 5:
                        continue

                if x2 >= cutx and x1 <= cutx:
                    x1 = cutx
                    if x2-x1 < 5:
                        continue

            tmp_box.append(x1)
            tmp_box.append(y1)
            tmp_box.append(x2)
            tmp_box.append(y2)
            tmp_box.append(box[-1])
            merge_bbox.append(tmp_box)
    return merge_bbox

def get_random_data(annotation_line, input_shape, random=True, hue=.1, sat=1.5, val=1.5, proc_img=True):
    '''random preprocessing for real-time data augmentation'''
    h, w = input_shape
    min_offset_x = 0.4
    min_offset_y = 0.4
    scale_low = 1-min(min_offset_x,min_offset_y)
    scale_high = scale_low+0.2

    image_datas = [] 
    box_datas = []
    index = 0

    place_x = [0,0,int(w*min_offset_x),int(w*min_offset_x)]
    place_y = [0,int(h*min_offset_y),int(w*min_offset_y),0]
    for line in annotation_line:
        # 每一行进行分割
        line_content = line.split()
        # 打开图片
        image = Image.open(line_content[0])
        image = image.convert("RGB") 
        # 图片的大小
        iw, ih = image.size
        # 保存框的位置
        box = np.array([np.array(list(map(int,box.split(',')))) for box in line_content[1:]])
        
        # image.save(str(index)+".jpg")
        # 是否翻转图片
        flip = rand()<.5
        if flip and len(box)>0:
            image = image.transpose(Image.FLIP_LEFT_RIGHT)
            box[:, [0,2]] = iw - box[:, [2,0]]

        # 对输入进来的图片进行缩放
        new_ar = w/h
        scale = rand(scale_low, scale_high)
        if new_ar < 1:
            nh = int(scale*h)
            nw = int(nh*new_ar)
        else:
            nw = int(scale*w)
            nh = int(nw/new_ar)
        image = image.resize((nw,nh), Image.BICUBIC)

        # 进行色域变换
        hue = rand(-hue, hue)
        sat = rand(1, sat) if rand()<.5 else 1/rand(1, sat)
        val = rand(1, val) if rand()<.5 else 1/rand(1, val)
        x = rgb_to_hsv(np.array(image)/255.)
        x[..., 0] += hue
        x[..., 0][x[..., 0]>1] -= 1
        x[..., 0][x[..., 0]<0] += 1
        x[..., 1] *= sat
        x[..., 2] *= val
        x[x>1] = 1
        x[x<0] = 0
        image = hsv_to_rgb(x)

        image = Image.fromarray((image*255).astype(np.uint8))
        # 将图片进行放置，分别对应四张分割图片的位置
        dx = place_x[index]
        dy = place_y[index]
        new_image = Image.new('RGB', (w,h), (128,128,128))
        new_image.paste(image, (dx, dy))
        image_data = np.array(new_image)/255

        # Image.fromarray((image_data*255).astype(np.uint8)).save(str(index)+"distort.jpg")
        
        index = index + 1
        box_data = []
        # 对box进行重新处理
        if len(box)>0:
            np.random.shuffle(box)
            box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
            box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
            box[:, 0:2][box[:, 0:2]<0] = 0
            box[:, 2][box[:, 2]>w] = w
            box[:, 3][box[:, 3]>h] = h
            box_w = box[:, 2] - box[:, 0]
            box_h = box[:, 3] - box[:, 1]
            box = box[np.logical_and(box_w>1, box_h>1)]
            box_data = np.zeros((len(box),5))
            box_data[:len(box)] = box
        
        image_datas.append(image_data)
        box_datas.append(box_data)

        img = Image.fromarray((image_data*255).astype(np.uint8))
        for j in range(len(box_data)):
            thickness = 3
            left, top, right, bottom  = box_data[j][0:4]
            draw = ImageDraw.Draw(img)
            for i in range(thickness):
                draw.rectangle([left + i, top + i, right - i, bottom - i],outline=(255,255,255))
        img.show()

    
    # 将图片分割，放在一起
    cutx = np.random.randint(int(w*min_offset_x), int(w*(1 - min_offset_x)))
    cuty = np.random.randint(int(h*min_offset_y), int(h*(1 - min_offset_y)))

    new_image = np.zeros([h,w,3])
    new_image[:cuty, :cutx, :] = image_datas[0][:cuty, :cutx, :]
    new_image[cuty:, :cutx, :] = image_datas[1][cuty:, :cutx, :]
    new_image[cuty:, cutx:, :] = image_datas[2][cuty:, cutx:, :]
    new_image[:cuty, cutx:, :] = image_datas[3][:cuty, cutx:, :]

    # 对框进行进一步的处理
    new_boxes = merge_bboxes(box_datas, cutx, cuty)

    return new_image, new_boxes

def normal_(annotation_line, input_shape):
    '''random preprocessing for real-time data augmentation'''
    line = annotation_line.split()
    image = Image.open(line[0])
    box = np.array([np.array(list(map(int,box.split(',')))) for box in line[1:]])
 
    iw, ih = image.size
    image = image.transpose(Image.FLIP_LEFT_RIGHT)
    box[:, [0,2]] = iw - box[:, [2,0]]

    return image, box

if __name__ == "__main__":
    with open("2007_train.txt") as f:
        lines = f.readlines()
    a = np.random.randint(0,len(lines))
    # index = 0
    # line_all = lines[a:a+4]
    # for line in line_all:
    #     image_data, box_data = normal_(line,[416,416])
    #     img = image_data
    #     for j in range(len(box_data)):
    #         thickness = 3
    #         left, top, right, bottom  = box_data[j][0:4]
    #         draw = ImageDraw.Draw(img)
    #         for i in range(thickness):
    #             draw.rectangle([left + i, top + i, right - i, bottom - i],outline=(255,255,255))
    #     img.show()
    #     # img.save(str(index)+"box.jpg")
    #     index = index+1
        
    line = lines[a:a+4]
    image_data, box_data = get_random_data(line,[416,416])
    img = Image.fromarray((image_data*255).astype(np.uint8))
    for j in range(len(box_data)):
        thickness = 3
        left, top, right, bottom  = box_data[j][0:4]
        draw = ImageDraw.Draw(img)
        for i in range(thickness):
            draw.rectangle([left + i, top + i, right - i, bottom - i],outline=(255,255,255))
    img.show()
    # img.save("box_all.jpg")

科大讯飞：

https://blog.csdn.net/Guo_Python/article/details/107386365?utm_medium=distribute.pc_relevant.none-task-blog-OPENSEARCH-4.channel_param&depth_1-utm_source=distribute.pc_relevant.none-task-blog-OPENSEARCH-4.channel_param

from PIL import Image, ImageDraw

https://blog.csdn.net/qq_35275007/article/details/107696246?utm_medium=distribute.pc_relevant.none-task-blog-title-6&spm=1001.2101.3001.4242

https://blog.csdn.net/weixin_45192980/article/details/107888746?utm_medium=distribute.pc_relevant.none-task-blog-OPENSEARCH-6.channel_param&depth_1-utm_source=distribute.pc_relevant.none-task-blog-OPENSEARCH-6.channel_param

https://blog.csdn.net/weixin_45192980/article/details/107888746?utm_medium=distribute.pc_relevant.none-task-blog-title-3&spm=1001.2101.3001.4242

 

c++opencv：

https://blog.csdn.net/sinat_41852207/article/details/105871882?utm_medium=distribute.pc_relevant.none-task-blog-title-9&spm=1001.2101.3001.4242

yolov5的，pytorch：jacke121-yolov5-master0725

import math
import random

import cv2
import numpy as np

def load_image(self, index):
    # loads 1 image from dataset, returns img, original hw, resized hw
    img = self.imgs[index]
    if img is None:  # not cached
        path = self.img_files[index]
        img = cv2.imread(path)  # BGR
        assert img is not None, 'Image Not Found ' + path
        h0, w0 = img.shape[:2]  # orig hw
        r = self.img_size / max(h0, w0)  # resize image to img_size
        if r != 1:  # always resize down, only resize up if training with augmentation
            interp = cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR
            img = cv2.resize(img, (int(w0 * r), int(h0 * r)), interpolation=interp)
        return img, (h0, w0), img.shape[:2]  # img, hw_original, hw_resized
    else:
        return self.imgs[index], self.img_hw0[index], self.img_hw[index]  # img, hw_original, hw_resized

def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.2):  # box1(4,n), box2(4,n)
    # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
    w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
    w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
    ar = np.maximum(w2 / (h2 + 1e-16), h2 / (w2 + 1e-16))  # aspect ratio
    return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + 1e-16) > area_thr) & (ar < ar_thr)  # candidates


def random_affine(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10, border=(0, 0)):
    # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
    # https://medium.com/uruvideo/dataset-augmentation-with-random-homographies-a8f4b44830d4
    # targets = [cls, xyxy]

    height = img.shape[0] + border[0] * 2  # shape(h,w,c)
    width = img.shape[1] + border[1] * 2

    # Rotation and Scale
    R = np.eye(3)
    a = random.uniform(-degrees, degrees)
    # a += random.choice([-180, -90, 0, 90])  # add 90deg rotations to small rotations
    s = random.uniform(1 - scale, 1 + scale)
    # s = 2 ** random.uniform(-scale, scale)
    R[:2] = cv2.getRotationMatrix2D(angle=a, center=(img.shape[1] / 2, img.shape[0] / 2), scale=s)

    # Translation
    T = np.eye(3)
    T[0, 2] = random.uniform(-translate, translate) * img.shape[1] + border[1]  # x translation (pixels)
    T[1, 2] = random.uniform(-translate, translate) * img.shape[0] + border[0]  # y translation (pixels)

    # Shear
    S = np.eye(3)
    S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # x shear (deg)
    S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # y shear (deg)

    # Combined rotation matrix
    M = S @ T @ R  # ORDER IS IMPORTANT HERE!!
    if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any():  # image changed
        img = cv2.warpAffine(img, M[:2], dsize=(width, height), flags=cv2.INTER_LINEAR, borderValue=(114, 114, 114))

    # Transform label coordinates
    n = len(targets)
    if n:
        # warp points
        xy = np.ones((n * 4, 3))
        xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2)  # x1y1, x2y2, x1y2, x2y1
        xy = (xy @ M.T)[:, :2].reshape(n, 8)

        # create new boxes
        x = xy[:, [0, 2, 4, 6]]
        y = xy[:, [1, 3, 5, 7]]
        xy = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T

        # # apply angle-based reduction of bounding boxes
        # radians = a * math.pi / 180
        # reduction = max(abs(math.sin(radians)), abs(math.cos(radians))) ** 0.5
        # x = (xy[:, 2] + xy[:, 0]) / 2
        # y = (xy[:, 3] + xy[:, 1]) / 2
        # w = (xy[:, 2] - xy[:, 0]) * reduction
        # h = (xy[:, 3] - xy[:, 1]) * reduction
        # xy = np.concatenate((x - w / 2, y - h / 2, x + w / 2, y + h / 2)).reshape(4, n).T

        # clip boxes
        xy[:, [0, 2]] = xy[:, [0, 2]].clip(0, width)
        xy[:, [1, 3]] = xy[:, [1, 3]].clip(0, height)

        # filter candidates
        i = box_candidates(box1=targets[:, 1:5].T * s, box2=xy.T)
        targets = targets[i]
        targets[:, 1:5] = xy[i]

    return img, targets


def load_mosaic(self, index):
    # loads images in a mosaic

    labels4 = []
    s = self.img_size
    yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border]  # mosaic center x, y
    indices = [index] + [random.randint(0, len(self.labels) - 1) for _ in range(3)]  # 3 additional image indices
    for i, index in enumerate(indices):
        # Load image
        img, _, (h, w) = load_image(self, index)

        # place img in img4
        if i == 0:  # top left
            img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
            x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)
            x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)
        elif i == 1:  # top right
            x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
            x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
        elif i == 2:  # bottom left
            x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
            x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, max(xc, w), min(y2a - y1a, h)
        elif i == 3:  # bottom right
            x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
            x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)

        img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
        padw = x1a - x1b
        padh = y1a - y1b

        # Labels
        x = self.labels[index]
        labels = x.copy()
        if x.size > 0:  # Normalized xywh to pixel xyxy format
            labels[:, 1] = w * (x[:, 1] - x[:, 3] / 2) + padw
            labels[:, 2] = h * (x[:, 2] - x[:, 4] / 2) + padh
            labels[:, 3] = w * (x[:, 1] + x[:, 3] / 2) + padw
            labels[:, 4] = h * (x[:, 2] + x[:, 4] / 2) + padh
        labels4.append(labels)

    # Concat/clip labels
    if len(labels4):
        labels4 = np.concatenate(labels4, 0)
        # np.clip(labels4[:, 1:] - s / 2, 0, s, out=labels4[:, 1:])  # use with center crop
        np.clip(labels4[:, 1:], 0, 2 * s, out=labels4[:, 1:])  # use with random_affine

        # Replicate
        # img4, labels4 = replicate(img4, labels4)

    # Augment
    # img4 = img4[s // 2: int(s * 1.5), s // 2:int(s * 1.5)]  # center crop (WARNING, requires box pruning)
    img4, labels4 = random_affine(img4, labels4,
                                  degrees=self.hyp['degrees'],
                                  translate=self.hyp['translate'],
                                  scale=self.hyp['scale'],
                                  shear=self.hyp['shear'],
                                  border=self.mosaic_border)  # border to remove

    return img4, labels4