#coding=utf-8 import xml.etree.ElementTree as ET import numpy as np
def iou(box, clusters): """ 计算一个ground truth边界盒和k个先验框(Anchor)的交并比(IOU)值。 参数box: 元组或者数据，代表ground truth的长宽。 参数clusters: 形如(k,2)的numpy数组，其中k是聚类Anchor框的个数 返回：ground truth和每个Anchor框的交并比。 """ x = np.minimum(clusters[:, 0], box[0]) y = np.minimum(clusters[:, 1], box[1]) if np.count_nonzero(x == 0) > 0 or np.count_nonzero(y == 0) > 0: raise ValueError("Box has no area") intersection = x * y box_area = box[0] * box[1] cluster_area = clusters[:, 0] * clusters[:, 1] iou_ = intersection / (box_area + cluster_area - intersection) return iou_
def avg_iou(boxes, clusters): """ 计算一个ground truth和k个Anchor的交并比的均值。 """ return np.mean([np.max(iou(boxes[i], clusters)) for i in range(boxes.shape[0])])
def kmean_anchors(path='./2007_train.txt', n=5, img_size=(416, 416)): # from utils.utils import *; _ = kmean_anchors() # Produces a list of target kmeans suitable for use in *.cfg files from utils.datasets import LoadImagesAndLabels thr = 0.20 # IoU threshold
def print_results(thr, wh, k): k = k[np.argsort(k.prod(1))] # sort small to large iou = wh_iou(torch.Tensor(wh), torch.Tensor(k)) max_iou, min_iou = iou.max(1)[0], iou.min(1)[0] bpr, aat = (max_iou > thr).float().mean(), ( iou > thr).float().mean() * n # best possible recall, anch > thr print('%.2f iou_thr: %.3f best possible recall, %.2f anchors > thr' % (thr, bpr, aat)) print( 'kmeans anchors (n=%g, img_size=%s, IoU=%.3f/%.3f/%.3f-min/mean/best): ' % (n, img_size, min_iou.mean(), iou.mean(), max_iou.mean()), end='') for i, x in enumerate(k): print('%i,%i' % (round(x[0]), round(x[1])), end=', ' if i < len(k) - 1 else '\n') # use in *.cfg return k
def fitness(thr, wh, k): # mutation fitness iou = wh_iou(wh, torch.Tensor(k)).max(1)[0] # max iou bpr = (iou > thr).float().mean() # best possible recall return iou.mean() * bpr # product
# Get label wh wh = [] dataset = LoadImagesAndLabels(path, augment=True, rect=True, cache_labels=True) nr = 1 if img_size[0] == img_size[1] else 10 # number augmentation repetitions for s, l in zip(dataset.shapes, dataset.labels): wh.append(l[:, 3:5] * (s / s.max())) # image normalized to letterbox normalized wh wh = np.concatenate(wh, 0).repeat(nr, axis=0) # augment 10x wh *= np.random.uniform(img_size[0], img_size[1], size=(wh.shape[0], 1)) # normalized to pixels (multi-scale)
# Darknet yolov3.cfg anchors use_darknet = False if use_darknet: k = np.array([[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]]) else: # Kmeans calculation from scipy.cluster.vq import kmeans print('Running kmeans for %g anchors on %g points...' % (n, len(wh))) s = wh.std(0) # sigmas for whitening k, dist = kmeans(wh / s, n, iter=30) # points, mean distance k *= s k = print_results(thr, wh, k) # Evolve wh = torch.Tensor(wh) f, ng = fitness(thr, wh, k), 2000 # fitness, generations for _ in tqdm(range(ng), desc='Evolving anchors'): kg = ( k.copy() * (1 + np.random.random() * np.random.randn(*k.shape) * 0.30)).clip( min=2.0) fg = fitness(thr, wh, kg) if fg > f: f, k = fg, kg.copy() print_results(thr, wh, k) k = print_results(thr, wh, k)
这种做法来自当时比较新的论文《Augmentation for small object detection》,文中最好的结果是复制了1-2次。实际我们项目中也试过1次、2次、3次到多次的结果，都不尽如人意，结果太差就没有记录下来。。（话说论文中展示的效果最佳组合是原图+增强后的图，并且最好的结果也就提高了1个百分点）╮(╯﹏╰）╭
# 去除以#开头的，属于注释部分的内容 # lines = [x for x in lines if x and not x.startswith('#')] # lines = [x.rstrip().lstrip() for x in lines]
lines_nums = [] layers_nums = []
layer_cnt = -1
for num, line in enumerate(lines): if line.startswith('['): layer_cnt += 1 layers_nums.append(layer_cnt) lines_nums.append(num+layer_cnt) print(line) # s = s.join("") # s = s.join(line) for i,num in enumerate(layers_nums): print(lines_nums[i], num) lines.insert(lines_nums[i]-1, '# layer-%d\n' % (num-1)) fo = open(new_save_name, 'w') fo.write(''.join(lines)) fo.close() f.close()
