1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208
|
import xml.etree.ElementTree as ET import os import cPickle import numpy as np
def parse_rec(filename): """ Parse a PASCAL VOC xml file """ tree = ET.parse(filename) objects = [] for obj in tree.findall('object'): obj_struct = {} obj_struct['name'] = obj.find('name').text obj_struct['pose'] = obj.find('pose').text obj_struct['truncated'] = int(obj.find('truncated').text) obj_struct['difficult'] = int(obj.find('difficult').text) bbox = obj.find('bndbox') obj_struct['bbox'] = [int(bbox.find('xmin').text), int(bbox.find('ymin').text), int(bbox.find('xmax').text), int(bbox.find('ymax').text)] objects.append(obj_struct)
return objects
def voc_ap(rec, prec, use_07_metric=False): """ ap = voc_ap(rec, prec, [use_07_metric]) Compute VOC AP given precision and recall. If use_07_metric is true, uses the VOC 07 11 point method (default:False). """ if use_07_metric: ap = 0. for t in np.arange(0., 1.1, 0.1): if np.sum(rec >= t) == 0: p = 0 else: p = np.max(prec[rec >= t]) ap = ap + p / 11. else: mrec = np.concatenate(([0.], rec, [1.])) mpre = np.concatenate(([0.], prec, [0.]))
for i in range(mpre.size - 1, 0, -1): mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])
i = np.where(mrec[1:] != mrec[:-1])[0]
ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1]) return ap
def voc_eval(detpath, annopath, imagesetfile, classname, cachedir, ovthresh=0.5, use_07_metric=False): """rec, prec, ap = voc_eval(detpath, annopath, imagesetfile, classname, [ovthresh], [use_07_metric]) Top level function that does the PASCAL VOC evaluation. detpath: 产生的txt文件,里面是一张图片的各个检测框结果。 annopath: xml 文件与对应的图像相呼应。 imagesetfile: 一个txt文件,里面是每个图片的地址,每行一个地址。 classname: 种类的名字,即类别。 cachedir: 缓存标注的目录。 [ovthresh]: IOU阈值,默认为0.5,即mAP50。 [use_07_metric]: 是否使用2007的计算AP的方法,默认为Fasle """
if not os.path.isdir(cachedir): os.mkdir(cachedir) cachefile = os.path.join(cachedir, 'annots.pkl') with open(imagesetfile, 'r') as f: lines = f.readlines() imagenames = [x.strip() for x in lines] if not os.path.isfile(cachefile): recs = {} for i, imagename in enumerate(imagenames): recs[imagename] = parse_rec(annopath.format(imagename)) if i % 100 == 0: print 'Reading annotation for {:d}/{:d}'.format( i + 1, len(imagenames)) print 'Saving cached annotations to {:s}'.format(cachefile) with open(cachefile, 'w') as f: cPickle.dump(recs, f) else: with open(cachefile, 'r') as f: recs = cPickle.load(f)
class_recs = {} npos = 0 for imagename in imagenames: R = [obj for obj in recs[imagename] if obj['name'] == classname] bbox = np.array([x['bbox'] for x in R]) difficult = np.array([x['difficult'] for x in R]).astype(np.bool) det = [False] * len(R) npos = npos + sum(~difficult) class_recs[imagename] = {'bbox': bbox, 'difficult': difficult, 'det': det}
detfile = detpath.format(classname) with open(detfile, 'r') as f: lines = f.readlines()
splitlines = [x.strip().split(' ') for x in lines] image_ids = [x[0] for x in splitlines] confidence = np.array([float(x[1]) for x in splitlines]) BB = np.array([[float(z) for z in x[2:]] for x in splitlines])
sorted_ind = np.argsort(-confidence) sorted_scores = np.sort(-confidence) BB = BB[sorted_ind, :] image_ids = [image_ids[x] for x in sorted_ind]
nd = len(image_ids) tp = np.zeros(nd) fp = np.zeros(nd) for d in range(nd): R = class_recs[image_ids[d]] bb = BB[d, :].astype(float) ovmax = -np.inf BBGT = R['bbox'].astype(float)
if BBGT.size > 0: ixmin = np.maximum(BBGT[:, 0], bb[0]) iymin = np.maximum(BBGT[:, 1], bb[1]) ixmax = np.minimum(BBGT[:, 2], bb[2]) iymax = np.minimum(BBGT[:, 3], bb[3]) iw = np.maximum(ixmax - ixmin + 1., 0.) ih = np.maximum(iymax - iymin + 1., 0.) inters = iw * ih
uni = ((bb[2] - bb[0] + 1.) * (bb[3] - bb[1] + 1.) + (BBGT[:, 2] - BBGT[:, 0] + 1.) * (BBGT[:, 3] - BBGT[:, 1] + 1.) - inters)
overlaps = inters / uni ovmax = np.max(overlaps) jmax = np.argmax(overlaps)
if ovmax > ovthresh: if not R['difficult'][jmax]: if not R['det'][jmax]: tp[d] = 1. R['det'][jmax] = 1 else: fp[d] = 1. else: fp[d] = 1.
fp = np.cumsum(fp) tp = np.cumsum(tp) rec = tp / float(npos) prec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps) ap = voc_ap(rec, prec, use_07_metric)
return rec, prec, ap
|