yolov3在作boundingbox预测的时候,用到了anchor boxes.这个anchors的含义即最有可能的object的width,height.事先经过聚类获得.好比某一个像素单元,我想对这个像素单元预测出一个object,围绕这个像素单元,能够预测出无数种object的形状,并非随便预测的,要参考anchor box的大小,即从已标注的数据中经过聚类统计到的最有可能的object的形状.html
.cfg文件内的配置以下:python
[yolo] mask = 3,4,5 anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
在用咱们本身的数据作训练的时候,要先修改anchors,匹配咱们本身的数据.anchors大小经过聚类获得.git
通俗地说,聚类就是把挨得近的数据点划分到一块儿.
kmeans算法的思想很简单github
<object-class> <x_center> <y_center> <width> <height> Where: <object-class> - integer object number from 0 to (classes-1) <x_center> <y_center> <width> <height> - float values relative to width and height of image, it can be equal from (0.0 to 1.0] > for example: <x> = <absolute_x> / <image_width> or <height> = <absolute_height> / <image_height> atention: <x_center> <y_center> - are center of rectangle (are not top-left corner)
举例:
1 0.716797 0.395833 0.216406 0.147222
全部的值都是比例.(中心点x,中心点y,目标宽,目标高)算法
通常来讲,计算样本点到质心的距离的时候直接算的是两点之间的距离,而后将样本点划归为与之距离最近的一个质心.
在yolov3中样本点的数据是有具体的业务上的含义的,咱们其实最终目的是想知道最有可能的object对应的bounding box的形状是什么样子的. 因此这个距离的计算咱们并非直接算两点之间的距离,咱们计算两个box的iou,即2个box的类似程度.d=1-iou(box1,box_cluster). 这样d越小,说明box1与box_cluster越相似.将box划归为box_cluster.app
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)
看着一大段,其实重点就一句函数
w,h = line.split(' ')[3:] annotation_dims.append(tuple(map(float,(w,h))))
这里涉及到了python的语法,map用法https://www.runoob.com/python/python-func-map.html
这样就生成了一个N*2矩阵. N表明你的样本个数.ui
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: #box(c_w,c_h)彻底包含box(w,h) similarity = w*h/(c_w*c_h) elif c_w>=w and c_h<=h: #box(c_w,c_h)宽而扁平 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 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)) #距离矩阵 N个点,每一个点到k个质心 共计N*K个距离 while True: D = [] iter+=1 for i in range(N): d = 1 - IOU(X[i],centroids) #d是一个k维的 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) #返回每一行的最小值的下标.即当前样本应该归为k个质心中的哪个质心. if (assignments == prev_assignments).all() : #质心已经再也不变化 print("Centroids = ",centroids) write_anchors_to_file(centroids,X,anchor_file) return #calculate new centroids centroid_sums=np.zeros((k,dim),np.float) #(k,2) for i in range(N): centroid_sums[assignments[i]]+=X[i] #将每个样本划分到对应质心 for j in range(k): centroids[j] = centroid_sums[j]/(np.sum(assignments==j)) #更新质心 prev_assignments = assignments.copy() old_D = D.copy()
for i in range(N): centroid_sums[assignments[i]]+=X[i] #将每个样本划分到对应质心 for j in range(k): centroids[j] = centroid_sums[j]/(np.sum(assignments==j)) #更新质心
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()
因为yolo要求的label文件中,填写的是相对于width,height的比例.因此获得的anchor box的大小要乘以模型输入图片的尺寸.
上述代码里code
anchors[i][0]*=width_in_cfg_file/32. anchors[i][1]*=height_in_cfg_file/32.
这里除以32是yolov2的算法要求. yolov3实际上不须要.参见如下连接https://github.com/pjreddie/darknet/issues/911orm
for Yolo v2: width=704 height=576 in cfg-file
./darknet detector calc_anchors data/hand.data -num_of_clusters 5 -width 22 -height 18 -show
for Yolo v3: width=704 height=576 in cfg-file
./darknet detector calc_anchors data/hand.data -num_of_clusters 9 -width 704 -height 576 -show
And you can use any images with any sizes.
完整代码见https://github.com/AlexeyAB/darknet/tree/master/scripts 用法:python3 gen_anchors.py -filelist ../build/darknet/x64/data/park_train.txt