yolov3 kmeans
yolov3在做boundingbox预测的时候,用到了anchor boxes.
.cfg文件内的配置如下:
[yolo]
mask = 3,4,5
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319在用我们自己的数据做训练的时候,要先修改anchors,匹配我们自己的数据.anchors大小通过聚类得到.
通俗地说,聚类就是把挨得近的数据点划分到一起.
kmeans算法的思想很简单
- 随便指定k个cluster
- 把点划分到与之最近的一个cluster
- 上面得到的cluster肯定是不好的,因为一开始的cluster是乱选的嘛
- 更新每个cluster为当前cluster的点的均值.(这时候cluster肯定变准了,为什么呢?比如当前这个cluster里有3个点,2个点靠的很近,还有1个点离得稍微远点,那取均值的话,那相当于靠的很近的2个点有更多投票权,新算出来的cluster的中心会更加靠近这两个点.你要是非要抬杠:那万一一开始我随机指定的cluster中心点就特别准呢,重新取均值反而把中心点弄的不准了?事实上这是kmeans的一个缺陷:比较依赖初始的k个cluster的位置.选择不恰当的k值可能会导致糟糕的聚类结果。这也是为什么要进行特征检查来决定数据集的聚类数目了。)
- 重新执行上述过程
- 把点划分到与之最近的一个cluster
- 更新每个cluster为当前cluster的点的均值
- 不断重复上述过程,直至cluster中心变化很小
Created on Feb 20, 2017
@author: jumabek
'''
from os import listdir
from os.path import isfile, join
import argparse
#import cv2
import numpy as np
import sys
import os
import shutil
import random
import math
width_in_cfg_file = 416.
height_in_cfg_file = 416.
def IOU(x,centroids):
similarities = []
k = len(centroids)
for centroid in centroids:
c_w,c_h = centroid
w,h = x
if c_w>=w and c_h>=h:
similarity = w*h/(c_w*c_h)
elif c_w>=w and c_h<=h:
similarity = w*c_h/(w*h + (c_w-w)*c_h)
elif c_w<=w and c_h>=h:
similarity = c_w*h/(w*h + c_w*(c_h-h))
else: #means both w,h are bigger than c_w and c_h respectively
similarity = (c_w*c_h)/(w*h)
similarities.append(similarity) # will become (k,) shape
return np.array(similarities)
def avg_IOU(X,centroids):
n,d = X.shape
sum = 0.
for i in range(X.shape[0]):
#note IOU() will return array which contains IoU for each centroid and X[i] // slightly ineffective, but I am too lazy
sum+= max(IOU(X[i],centroids))
return sum/n
def write_anchors_to_file(centroids,X,anchor_file):
f = open(anchor_file,'w')
anchors = centroids.copy()
print(anchors.shape)
for i in range(anchors.shape[0]):
anchors[i][0]*=width_in_cfg_file/32.
anchors[i][1]*=height_in_cfg_file/32.
widths = anchors[:,0]
sorted_indices = np.argsort(widths)
print('Anchors = ', anchors[sorted_indices])
for i in sorted_indices[:-1]:
f.write('%0.2f,%0.2f, '%(anchors[i,0],anchors[i,1]))
#there should not be comma after last anchor, that's why
f.write('%0.2f,%0.2f\n'%(anchors[sorted_indices[-1:],0],anchors[sorted_indices[-1:],1]))
f.write('%f\n'%(avg_IOU(X,centroids)))
print()
def kmeans(X,centroids,eps,anchor_file):
N = X.shape[0]
iterations = 0
k,dim = centroids.shape
prev_assignments = np.ones(N)*(-1)
iter = 0
old_D = np.zeros((N,k))
while True:
D = []
iter+=1
for i in range(N):
d = 1 - IOU(X[i],centroids)
D.append(d)
D = np.array(D) # D.shape = (N,k)
print("iter {}: dists = {}".format(iter,np.sum(np.abs(old_D-D))))
#assign samples to centroids
assignments = np.argmin(D,axis=1)
if (assignments == prev_assignments).all() :
print("Centroids = ",centroids)
write_anchors_to_file(centroids,X,anchor_file)
return
#calculate new centroids
centroid_sums=np.zeros((k,dim),np.float)
for i in range(N):
centroid_sums[assignments[i]]+=X[i]
for j in range(k):
centroids[j] = centroid_sums[j]/(np.sum(assignments==j))
prev_assignments = assignments.copy()
old_D = D.copy()
def main(argv):
parser = argparse.ArgumentParser()
parser.add_argument('-filelist', default = '\\path\\to\\voc\\filelist\\train.txt',
help='path to filelist\n' )
parser.add_argument('-output_dir', default = 'generated_anchors/anchors', type = str,
help='Output anchor directory\n' )
parser.add_argument('-num_clusters', default = 0, type = int,
help='number of clusters\n' )
args = parser.parse_args()
if not os.path.exists(args.output_dir):
os.mkdir(args.output_dir)
f = open(args.filelist)
lines = [line.rstrip('\n') for line in f.readlines()]
annotation_dims = []
size = np.zeros((1,1,3))
for line in lines:
#line = line.replace('images','labels')
#line = line.replace('img1','labels')
line = line.replace('JPEGImages','labels')
line = line.replace('.jpg','.txt')
line = line.replace('.png','.txt')
print(line)
f2 = open(line)
for line in f2.readlines():
line = line.rstrip('\n')
w,h = line.split(' ')[3:]
#print(w,h)
annotation_dims.append(tuple(map(float,(w,h))))
annotation_dims = np.array(annotation_dims)
eps = 0.005
if args.num_clusters == 0:
for num_clusters in range(1,11): #we make 1 through 10 clusters
anchor_file = join( args.output_dir,'anchors%d.txt'%(num_clusters))
indices = [ random.randrange(annotation_dims.shape[0]) for i in range(num_clusters)]
centroids = annotation_dims[indices]
kmeans(annotation_dims,centroids,eps,anchor_file)
print('centroids.shape', centroids.shape)
else:
anchor_file = join( args.output_dir,'anchors%d.txt'%(args.num_clusters))
indices = [ random.randrange(annotation_dims.shape[0]) for i in range(args.num_clusters)]
centroids = annotation_dims[indices]
kmeans(annotation_dims,centroids,eps,anchor_file)
print('centroids.shape', centroids.shape)
if __name__=="__main__":
main(sys.argv)用法:python3 gen_anchors.py -filelist ./park_train.txt park_train.txt描述了训练图片路径.