voc_eval.py 解析

参考：https://github.com/rbgirshick/py-faster-rcnn/blob/master/lib/datasets/voc_eval.py

代码块

# --------------------------------------------------------# Fast/er R-CNN# Licensed under The MIT License [see LICENSE for details]# Written by Bharath Hariharan# --------------------------------------------------------import xml.etree.ElementTree as ET #读取xml。import osimport cPickle #序列化存储模块。import numpy as npdef parse_rec(filename):#解析读取xml函数。    """ 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 objectsdef voc_ap(rec, prec, use_07_metric=False): #单个测量AP的函数。    """ 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:        # 11 point 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:        # correct AP calculation        # first append sentinel values at the end        mrec = np.concatenate(([0.], rec, [1.]))        mpre = np.concatenate(([0.], prec, [0.]))        # compute the precision envelope        for i in range(mpre.size - 1, 0, -1):            mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])        # to calculate area under PR curve, look for points        # where X axis (recall) changes value        i = np.where(mrec[1:] != mrec[:-1])[0]        # and sum (\Delta recall) * prec        ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])    return apdef voc_eval(detpath,  ######主函数             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: Path to detections        detpath.format(classname) should produce the detection results file. #产生的txt文件，里面是一张图片的各个detection。    annopath: Path to annotations        annopath.format(imagename) should be the xml annotations file. #xml 文件与对应的图像相呼应。    imagesetfile: Text file containing the list of images, one image per line. #一个txt文件，里面是每个图片的地址，每行一个地址。    classname: Category name (duh) #种类的名字，即类别。    cachedir: Directory for caching the annotations #缓存标注的目录。    [ovthresh]: Overlap threshold (default = 0.5) #重叠的多少大小。    [use_07_metric]: Whether to use VOC07's 11 point AP computation         (default False) #是否使用VOC07的11点AP计算。    """    # assumes detections are in detpath.format(classname)    # assumes annotations are in annopath.format(imagename)    # assumes imagesetfile is a text file with each line an image name    # cachedir caches the annotations in a pickle file    # first load gt 加载ground truth。    if not os.path.isdir(cachedir):        os.mkdir(cachedir)    cachefile = os.path.join(cachedir, 'annots.pkl') #即将新建文件的路径。    # read list of images    with open(imagesetfile, 'r') as f:        lines = f.readlines() #读取文本里的所以文本行，作为众多文图片的路径。    imagenames = [x.strip() for x in lines] #所有文件名字。    if not os.path.isfile(cachefile): #如果cachefile文件不存在，则        # load annots        recs = {}        for i, imagename in enumerate(imagenames):            recs[imagename] = parse_rec(annopath.format(imagename)) #这里的format不知道啥意思            if i % 100 == 0:                print 'Reading annotation for {:d}/{:d}'.format(                    i + 1, len(imagenames)) #进度条。        # save        print 'Saving cached annotations to {:s}'.format(cachefile)        with open(cachefile, 'w') as f:            cPickle.dump(recs, f) #写入cPickle文件里面。写入的是一个字典，左侧为xml文件名，右侧为文件里面个各个参数。    else:        # load        with open(cachefile, 'r') as f:            recs = cPickle.load(f) #如果已经有了这个cPickle文件，则加载一下。    # extract gt objects for this class #对每张图片的xml获取函数指定类的bbox等。    class_recs = {}    npos = 0    for imagename in imagenames:        R = [obj for obj in recs[imagename] if obj['name'] == classname] #获取每个文件中某种类别的物体。        bbox = np.array([x['bbox'] for x in R]) #抽取bbox        difficult = np.array([x['difficult'] for x in R]).astype(np.bool) #different基本都为0.        det = [False] * len(R) #list中形参len(R)个False。        npos = npos + sum(~difficult) #自增，sum求得的值基本都为0。        class_recs[imagename] = {'bbox': bbox,                                 'difficult': difficult,                                 'det': det}    # read dets     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] #图片index。    confidence = np.array([float(x[1]) for x in splitlines]) #类别置信度    BB = np.array([[float(z) for z in x[2:]] for x in splitlines]) #变为浮点型的bbox。    # sort by confidence    sorted_ind = np.argsort(-confidence) #对confidence的index根据值大小进行降序排列。    sorted_scores = np.sort(-confidence) #降序排列。    BB = BB[sorted_ind, :] #重排bbox，由大概率到小概率。    image_ids = [image_ids[x] for x in sorted_ind] 对图片进行重排。    # go down dets and mark TPs and FPs     nd = len(image_ids)    tp = np.zeros(nd)     fp = np.zeros(nd) #归零。    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:            # compute overlaps            # intersection            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            # union            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.    # compute precision recall    fp = np.cumsum(fp)    tp = np.cumsum(tp)    rec = tp / float(npos)    # avoid divide by zero in case the first detection matches a difficult    # ground truth    prec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps)    ap = voc_ap(rec, prec, use_07_metric)    return rec, prec, ap