YOLO-目标检测中计算AP、MAP方法
根据这个代码就可以计算到出各类别的AP/MAP值
# --------------------------------------------------------
# YOLOv4
# 2020.11.05
# --------------------------------------------------------
from __future__ import print_function
import argparse
import xml.etree.ElementTree as ET
import os,sys
import pickle
import numpy as np
import pdb
def parse_args():
"""
Parse input arguments
"""
parser = argparse.ArgumentParser(description='Re-evaluate results')
parser.add_argument('output_dir', nargs=1, help='results directory',type=str)
parser.add_argument('--voc_dir', dest='voc_dir', default='/home/sxl/Data/voc/VOCtrainval/', type=str)
parser.add_argument('--year', dest='year', default='2017', type=str)
parser.add_argument('--image_set', dest='image_set', default='voc_test', type=str)
parser.add_argument('--classes', dest='class_file', default='/home/sxl/Module/DarknetAB1022/data/voc.names', type=str)
parser.add_argument('--ovthresh', dest='ovthresh', default=0.5, type=float)
if len(sys.argv) == 1:
parser.print_help()
sys.exit(1)
args = parser.parse_args()
return args
def get_voc_results_file_template(image_set, out_dir = 'results'):
#filename = 'comp4_det_' + image_set + '_{:s}.txt'
#filename = image_set + '_{:s}.txt'
filename = '{:s}.txt'
path = os.path.join(out_dir, filename)
return path
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).
"""
# VOC在2010之后换了评价方法，所以在这里决定是否用07年的方法
if use_07_metric:
# 11 point metric
ap = 0.
for t in np.arange(0., 1.1, 0.1): #07年采用的是11插值法，平分recall计算得来
if np.sum(rec >= t) == 0:
p = 0
else:
p = np.max(prec[rec >= t]) # 取一个recall阈值之后最大的precision
ap = ap + p / 11. # 将11 个precision加和平均
else: # 使用2010年后的方法，取所有不同的recall对应的点处的精度值做平均
# correct AP calculation
# first append sentinel values at the end
mrec = np.concatenate(([0.], rec, [1.])) # recall和precision前后分别加了一个值，因为recall最后是1，所以
mpre = np.concatenate(([0.], prec, [0.])) # 右边加了1，precision加的是0
# compute the precision envelope
for i in range(mpre.size - 1, 0, -1):
mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i]) # 从后往前，排除之前局部增加的precison情况
# to calculate area under PR curve, look for points
# where X axis (recall) changes value
i = np.where(mrec[1:] != mrec[:-1])[0] # 这里巧妙的错位，返回刚好TP的位置，
# and sum (\Delta recall) * prec 用recall 的间隔对精度作加权平均
ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])
return ap
def voc_eval(detpath,
annopath,
imagesetfile,
classname,
cachedir,
ovthresh,
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.
annopath: Path to annotations
annopath.format(imagename) should be the xml annotations file.
imagesetfile: Text file containing the list of images, one image per line.
classname: Category name (duh)
cachedir: Directory for caching the annotations
[ovthresh]: Overlap threshold (default = 0.5)
[use_07_metric]: Whether to use VOC07's 11 point AP computation
(default False)
"""
# 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
if not os.path.isdir(cachedir):
os.mkdir(cachedir)
cachefile = os.path.join(cachedir, 'annots.pkl')
# read list of images
with open(imagesetfile, 'r') as f:
lines = f.readlines()
imagenames = [x.strip() for x in lines]
#pdb.set_trace()
if not os.path.isfile(cachefile):
# load annots
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)))
# save
print('Saving cached annotations to {:s}'.format(cachefile))
with open(cachefile, 'wb') as f:
pickle.dump(recs, f)
else:
# load
with open(cachefile, 'rb') as f:
recs = pickle.load(f)
# extract gt objects for this class
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) # npos=TP+FN
class_recs[imagename] = {'bbox': bbox,
'difficult': difficult,
'det': det}
# read dets
detfile = detpath.format(classname)
#pdb.set_trace()
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])
# sort by confidence
sorted_ind = np.argsort(-confidence)
sorted_scores = np.sort(-confidence)
BB = BB[sorted_ind, :]
image_ids = [image_ids[x] for x in sorted_ind]
# go down dets and mark TPs and FPs
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:
# 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
def do_python_eval(devkit_path, year, image_set, classes, ovthresh, output_dir = 'results'):
"""
Parse input arguments
"""
# parser = argparse.ArgumentParser(description='Re-evaluate results')
# parser.add_argument('output_dir', nargs=1, help='results directory',
# type=str)
# parser.add_argument('--voc_dir', dest='voc_dir', default='data/VOCdevkit', type=str)
# parser.add_argument('--year', dest='year', default='2017', type=str)
# parser.add_argument('--image_set', dest='image_set', default='test', type=str)
# parser.add_argument('--classes', dest='class_file', default='data/voc.names', type=str)
annopath = os.path.join(
devkit_path,
'VOC' + year,
'Annotations',
'{:s}.xml')
imagesetfile = os.path.join(
devkit_path,
'VOC' + year,
'ImageSets',
'Main',
image_set+'.txt')
cachedir = os.path.join(devkit_path, 'annotations_cache')
aps = []
# The PASCAL VOC metric changed in 2010
# use_07_metric = True if int(_year) < 2010 else False
use_07_metric = False
print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No'))
if not os.path.isdir(output_dir):
os.mkdir(output_dir)
# i -index cls- category
for i, cls in enumerate(classes):
if cls == '__background__':
continue
filename = get_voc_results_file_template(image_set).format(cls)
rec, prec, ap = voc_eval(
filename, annopath, imagesetfile, cls, cachedir, ovthresh,
use_07_metric=use_07_metric)
aps += [ap]
print('AP for {} = {:.4f}'.format(cls, ap))
with open(os.path.join(output_dir, cls + '_pr.pkl'), 'wb') as f:
pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f)
print('Mean AP = {:.4f}'.format(np.mean(aps)))
print('~~~~~~~~')
print('Results:')
for ap in aps:
print('{:.3f}'.format(ap))
print('{:.3f}'.format(np.mean(aps)))
print('~~~~~~~~')
if __name__ == '__main__':
args = parse_args()
output_dir = os.path.abspath(args.output_dir[0])
with open(args.class_file, 'r') as f:
lines = f.readlines()
classes = [t.strip('\n') for t in lines]
print ('Evaluating detections')
do_python_eval(args.voc_dir, args.year, args.image_set, classes, args.ovthresh, output_dir)