浅谈yolov4中的数据增强
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")