YoloV4当中的Mosaic数据增强代码实例分享

代码：https://github.com/bubbliiiing/yolo3-pytorch

对数据集转换成VOC格式，代码与上面可得。
yolo3整体的文件夹构架如下：

本文使用VOC格式进行训练。
训练前将标签文件放在VOCdevkit文件夹下的VOC2007文件夹下的Annotation中。

训练前将图片文件放在VOCdevkit文件夹下的VOC2007文件夹下的JPEGImages中。

在训练前利用voc2yolo3.py文件生成对应的txt。

再运行根目录下的voc_annotation.py，运行前需要将classes改成你自己的classes。
就会生成对应的2007_train.txt，每一行对应其图片位置及其真实框的位置。

在训练前需要修改model_data里面的voc_classes.txt文件，需要将classes改成你自己的classes。同时还需要修改utils/config.py文件，修改内部的Num_Classes变成所分的种类的数量。

增强代码如下：
普通增强：

from PIL import Image, ImageDraw
import numpy as np
from matplotlib.colors import rgb_to_hsv, hsv_to_rgb

def rand(a=0, b=1):
    return np.random.rand()*(b-a) + a

def get_random_data(annotation_line, input_shape, random=True, max_boxes=20, jitter=.5, hue=.1, sat=1.5, val=1.5, proc_img=True):
    '''random preprocessing for real-time data augmentation'''
    line = annotation_line.split()
    image = Image.open(line[0])
    iw, ih = image.size
    h, w = input_shape
    box = np.array([np.array(list(map(int,box.split(',')))) for box in line[1:]])

    # 对图像进行缩放并且进行长和宽的扭曲
    new_ar = w/h * rand(1-jitter,1+jitter)/rand(1-jitter,1+jitter)
    scale = rand(.25,2)
    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)

    # 将图像多余的部分加上灰条
    dx = int(rand(0, w-nw))
    dy = int(rand(0, h-nh))
    new_image = Image.new('RGB', (w,h), (128,128,128))
    new_image.paste(image, (dx, dy))
    image = new_image

    # 翻转图像
    flip = rand()<.5
    if flip: image = image.transpose(Image.FLIP_LEFT_RIGHT)

    # 色域扭曲
    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_data = hsv_to_rgb(x) # numpy array, 0 to 1

    # 将box进行调整
    box_data = np.zeros((max_boxes,5))
    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
        if flip: box[:, [0,2]] = w - box[:, [2,0]]
        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)] # discard invalid box
        if len(box)>max_boxes: box = box[:max_boxes]
        box_data[:len(box)] = box
    
    return image_data, box_data
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:]])

    return image, box


if __name__ == "__main__":
    with open("2007_train.txt") as f:
        lines = f.readlines()
    a = np.random.randint(0,len(lines))
    line = lines[a]

    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()
    
    image_data, box_data = get_random_data(line,[416,416])
    print(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()

    # img = Image.open(r"F:\Collection\yolo_Collection\keras-yolo3-master\Mobile-yolo3-master/VOCdevkit/VOC2007/JPEGImages/00000.jpg")

    # left, top, right, bottom = 527,377,555,404

    # draw = ImageDraw.Draw(img)

    # draw.rectangle([left, top, right, bottom])
    # img.show() 

YOLO v4 Mosaic数据增强方法：

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") 

本文地址：https://blog.csdn.net/qq_44787464/article/details/108261154