浅谈yolov4中的一部分数据增强

前言

在接下来的几天，我将解读yolov4，yolo系列一直是很火的目标检测算法。我特别喜欢yolov4。而今天我们来谈下数据增强。

数据增强

计算机视觉中的图像增强，是人为的为视觉不变性（语义不变）引入了先验知识。数据增强也基本上成了提高模型性能的最简单、直接的方法了。首先增强的样本和原来的样本是由强相关性的（裁剪、翻转、旋转、缩放、扭曲等几何变换，还有像素扰动、添加噪声、光照调节、对比度调节、样本加和或插值、分割补丁等），通过某些简单的操作，提高了最终性能。

数据增强步骤

1.对图片进行水平翻转

水平翻转目标框坐标

# 图片的大小
   iw, ih = image.size
  image = image.transpose(Image.FLIP_LEFT_RIGHT)
            # print(box[:, [0, 2]] ,box[:, [2, 0]])
            box[:, [0, 2]] = iw - box[:, [2, 0]]
            image.show()

2.对图片进行缩放

代码：

 # 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)
            # image.show()
        else:
            nw = int(scale * w)
            nh = int(nw / new_ar)

        image = image.resize((nw, nh), Image.BICUBIC)
        image.show()

3.对图片HSV色域变换

HSV模型，是针对用户观感的一种颜色模型，侧重于色彩表示，什么颜色、深浅如何、明暗如何。

H是色彩，S是深浅， S = 0时，只有灰度，V是明暗，表示色彩的明亮程度
代码：

 # 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))
        image.show()

4. Mosaic数据增强

Yolov4的mosaic数据增强参考了CutMix数据增强方式，理论上具有一定的相似性！CutMix数据增强方式利用两张图片进行拼接。如下第4张图。

但是mosaic利用了四张图片，根据论文所说其拥有一个巨大的优点是丰富检测物体的背景！且在BN计算的时候一下子会计算四张图片的数据！

annotations需要对框的坐标在合成图中进行调整，超出边界的需要裁剪，效果图如下

     # 将图片进行放置，分别对应四张分割图片的位置
        dx = place_x[index]
        # print(dx)
        dy = place_y[index]
        # print(dy)
        new_image = Image.new('RGB', (w, h), (128, 128, 128))
        new_image.paste(image, (dx, dy))
        image_data = np.array(new_image) / 255
        # new_image.show()
        # 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]
            #>>> np.logical_and([True, False], [False, False])
            #array([False, False], dtype=bool)
            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
    # print(int(w * min_offset_x))
    # print( int(w * (1 - min_offset_x)))
    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:, :]
    img = Image.fromarray((new_image * 255).astype(np.uint8))
    img.show()
    # 对框进行进一步的处理
    new_boxes = merge_bboxes(box_datas, cutx, cuty)
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

5. 总代码

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")
        image.show()
        # 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
        # image.show()
        if flip and len(box) > 0:
            # image.show()
            image = image.transpose(Image.FLIP_LEFT_RIGHT)
            # print(box[:, [0, 2]] ,box[:, [2, 0]])
            box[:, [0, 2]] = iw - box[:, [2, 0]]
            # image.show()
        # 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)
            # image.show()
        else:
            nw = int(scale * w)
            nh = int(nw / new_ar)

        image = image.resize((nw, nh), Image.BICUBIC)
        # image.show()

        # 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))
        image.show()
        # 将图片进行放置，分别对应四张分割图片的位置
        dx = place_x[index]
        # print(dx)
        dy = place_y[index]
        # print(dy)
        new_image = Image.new('RGB', (w, h), (128, 128, 128))
        new_image.paste(image, (dx, dy))
        image_data = np.array(new_image) / 255
        # new_image.show()
        # 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]
            #>>> np.logical_and([True, False], [False, False])
            #array([False, False], dtype=bool)
            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
    # print(int(w * min_offset_x))
    # print( int(w * (1 - min_offset_x)))
    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:, :]
    img = Image.fromarray((new_image * 255).astype(np.uint8))
    img.show()
    # 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))
    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")