VOC中的xml文件
<annotation>
<folder>VOC2012</folder> //文件名
<filename>2007_000346.jpg</filename>
<source> //文件来源
<database>The VOC2007 Database</database>
<annotation>PASCAL VOC2007</annotation>
<image>flickr</image>
</source>
<size> //文件大小（宽度、高度、通道数）
<width>500</width>
<height>375</height>
<depth>3</depth>
</size>
<segmented>1</segmented> //是否用于分割
<object> //检测物体说明
<name>bottle</name> //所检测到的物体
<pose>Unspecified</pose> //拍摄角度（未详细说明）
<truncated>0</truncated> //是否被截断（0代表未被截断）
<difficult>0</difficult> //目标是否难以识别（0代表容易识别）
<bndbox> //左下和右上坐标
<xmin>124</xmin>
<ymin>107</ymin>
<xmax>230</xmax>
<ymax>343</ymax>
</bndbox>
</object>
<object> //所检测的另一物体
<name>person</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>137</xmin>
<ymin>78</ymin>
<xmax>497</xmax>
<ymax>375</ymax>
</bndbox>
</object>
<object>
<name>person</name>
<pose>Unspecified</pose>
<truncated>1</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>89</xmin>
<ymin>202</ymin>
<xmax>129</xmax>
<ymax>247</ymax>
</bndbox>
</object>
<object>
<name>person</name>
<pose>Frontal</pose>
<truncated>1</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>72</xmin>
<ymin>209</ymin>
<xmax>111</xmax>
<ymax>259</ymax>
</bndbox>
</object>
</annotation>
View Code
其中
<segmented>1</segmented> //是否用于分割
<object> //检测物体说明
<name>bottle</name> //所检测到的物体
<pose>Unspecified</pose> //拍摄角度（未详细说明）
<truncated>0</truncated> //是否被截断（0代表未被截断）
<difficult>0</difficult> //目标是否难以识别（0代表容易识别）
<bndbox> //左下和右上坐标
<xmin>124</xmin>
<ymin>107</ymin>
<xmax>230</xmax>
<ymax>343</ymax>
</bndbox>
difficult代表是否难以识别，0表示易识别，1表示难识别。通常读取时略过这类；
定制数据集计算mAP，需要根据数据集的属性，改写代码；
计算过程：
1) 选择一个类，做ap计算;
2) 对所有图片，中该类box的检测，按照预测得分从大到小排序;
3) 按照这个顺序，计算累计tp， fp， 进而计算累计precision, recall;
4) 然后按照0， 0.1， 0.2 ... 0.9 1.0 ，这11各点，10个区间，得到折线图，然后得到11个顶点，进而计算这11个顶点的平均值，就得到了，这个类的ap;
5) 对所有类，计算ap， 然后对这些ap加和，除以类别数，得到mAP;
import os
import numpy as np
# imagesetfile = "../tfluisee/valid.txt"
# annopath = ""
# imgfile = open(imagesetfile, 'r')
# lines = imgfile.readlines()
# imagename = lines[0].strip()
# print(imagename)
# imagenames = [x.strip() for x in lines]
# # annopath = '{}.xml'
# # annopath.format(imagename)
#
# # parse_tfluisee_anno
# annoname = imagename.replace('images', 'labels')
# annoname = annoname.replace('png', 'txt')
# annofile = open(annoname, 'r')
# annolines = annofile.readlines()
# annoline = annolines[0].strip().split(' ')
# clas = tuple(map(int, annoline[0]))
# bbox = tuple(map(float, annoline[1:]))
# det
img_w = 1280
img_h = 720
# tfl_label = {'circle_green':0, 'circle_red':1, 'circle_yellow':2, 'circle_off':3, 'left_green':4, 'left_red':5, 'left_yellow':6, 'left_off':7, 'nomotor_green':8, 'nomotor_red':9, 'nomotor_yellow':10, 'nomotor_off':11}
tfl_label = ['circle_green', 'circle_red', 'circle_yellow', 'circle_off', 'left_green', 'left_red', 'left_yellow', 'left_off', 'nomotor_green', 'nomotor_red', 'nomotor_yellow', 'nomotor_off']
def parse_tfluisee(filename):
"""
Parse a TFL uisee txt file
anno bbox: xc, yc, w, h
"""
objects = []
annofile = open(filename, 'r')
annolines = annofile.readlines()
for i, annoline in enumerate(annolines):
obj_struct = {}
annoline = annoline.strip().split(' ')
obj_struct['name'] = tfl_label[tuple(map(int, annoline[0]))[0]]
bbox = tuple(map(float, annoline[1:]))
# (xc, yc, w, h) ---> (xmin, ymin, xmax, ymax)
xmin = (bbox[0] - bbox[2]*0.5) * img_w
xmax = (bbox[0] + bbox[2]*0.5) * img_w
ymin = (bbox[1] - bbox[3]*0.5) * img_h
ymax = (bbox[1] + bbox[3]*0.5) * img_h
if xmin < 0:
xmin = 0
if ymin < 0:
ymin = 0
if xmax > img_w-1:
xmax = img_w-1
if ymax > img_h-1:
ymax = img_h-1
obj_struct['bbox'] = [int(xmin), int(ymin), int(xmax), int(ymax)]
obj_struct['difficult'] = 0 # 0-easy, 1-difficult
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:
# 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 ap
def tfl_eval(detpath, annopath, datasetfile, classname, ovthresh, use_07_metric=False):
print('tfl eval of class: ', classname)
imgfile = open(datasetfile, 'r')
imglines = imgfile.readlines()
imagenames = [x.strip() for x in imglines]
# load annots
recs = {}
for i, filename in enumerate(imagenames):
imagename = filename.split('/')[-1].split('.')[-2]
annofile = filename.replace('images', 'labels')
annofile = annofile.replace('png', 'txt')
recs[imagename] = parse_tfluisee(annofile)
# extra gt object for this class
class_recs = {}
npos = 0
for i, filename in enumerate(imagenames):
imagename = filename.split('/')[-1].split('.')[-2]
R = [obj for obj in recs[imagename] if obj['name'] == classname]
# print('R: ', R)
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)
# print('det: {} \t bbox: {}'.format(det, bbox))
class_recs[imagename] = {'bbox': bbox, 'difficult': difficult, 'det': det}
# read dets
detfile = detpath.format(classname)
# print('detfile: ', detfile)
with open(detfile, 'r') as f:
lines = f.readlines()
splitlines = [x.strip().split(' ') for x in lines]
print('det image len: ', len(splitlines))
if len(splitlines)==0:
return 0, 0, 0
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)
# print('BBGT: ', len(BBGT))
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
# print('inters: {} \t uni: {} \n'.format(inters, uni))
ovmax = np.max(overlaps)
jmax = np.argmax(overlaps)
# print('name: {} \n ---overlaps: {} \t ovmax: {} \t jmax: {}\n'.format(image_ids[d], overlaps, ovmax, jmax))
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
# print('before npos: {}\t fp: {}\t, tp: {}'.format(npos, fp, tp))
fp = np.cumsum(fp)
tp = np.cumsum(tp)
# print('npos: {}\t fp: {}\t, tp: {}'.format(npos, fp, tp))
if npos>0:
rec = tp / float(npos)
else:
print('********************************************classname: ', classname)
return 0, 0, 0
# 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
if __name__ == "__main__":
path = os.getcwd()
# single class
detpath = os.path.join(path, '..', 'results/{}.txt')
annopath = os.path.join(path, '..', 'tfluisee/valid.txt')
datasetfile = os.path.join(path, '..', 'tfluisee/valid.txt')
thresh = 0.5
classname = 'circle_green'
use_07_metric = True
recall, precision, ap = tfl_eval(detpath, annopath, datasetfile, classname, thresh, use_07_metric)
# print('use_07_metric: {}\tclassname: {}\t recall:{}\t precision: {}\t ap: {}\t'.format(use_07_metric, classname, recall, precision, ap))
# multi class
resultspath = os.path.join(path, '..', 'results')
subfiles = os.listdir(resultspath)
mAP = []
for i in range(len(subfiles)):
classname = subfiles[i].split('.txt')[0]
recall, precision, ap = tfl_eval(detpath, annopath, datasetfile, classname, thresh, use_07_metric)
# print('classname: {}\t recall:{}\t precision: {}\t ap: {}\t'.format(classname, recall, precision, ap))
mAP.append(ap)
mAP = tuple(mAP)
print('AP: {}\nmAP: {}'.format(mAP, float(sum(mAP)/len(mAP))))
print('***************FalseFalse**************************************************')
use_07_metric = False
recall, precision, ap = tfl_eval(detpath, annopath, datasetfile, classname, thresh, use_07_metric)
# print('use_07_metric: {}\tclassname: {}\t recall:{}\t precision: {}\t ap: {}\t'.format(use_07_metric, classname, recall, precision, ap))
# multi class
resultspath = os.path.join(path, '..', 'results')
subfiles = os.listdir(resultspath)
mAP = []
for i in range(len(subfiles)):
classname = subfiles[i].split('.txt')[0]
recall, precision, ap = tfl_eval(detpath, annopath, datasetfile, classname, thresh, use_07_metric)
# print('classname: {}\t recall:{}\t precision: {}\t ap: {}\t'.format(classname, recall, precision, ap))
mAP.append(ap)
mAP = tuple(mAP)
print('AP: {}\nmAP: {}'.format(mAP, float(sum(mAP)/len(mAP))))
View Code
对红绿灯的颜色进行评估
import os
import numpy as np
# imagesetfile = "../tfluisee/valid.txt"
# annopath = ""
# imgfile = open(imagesetfile, 'r')
# lines = imgfile.readlines()
# imagename = lines[0].strip()
# print(imagename)
# imagenames = [x.strip() for x in lines]
# # annopath = '{}.xml'
# # annopath.format(imagename)
#
# # parse_tfluisee_anno
# annoname = imagename.replace('images', 'labels')
# annoname = annoname.replace('png', 'txt')
# annofile = open(annoname, 'r')
# annolines = annofile.readlines()
# annoline = annolines[0].strip().split(' ')
# clas = tuple(map(int, annoline[0]))
# bbox = tuple(map(float, annoline[1:]))
# det
img_w = 1280
img_h = 720
# tfl_label = {'circle_green':0, 'circle_red':1, 'circle_yellow':2, 'circle_off':3, 'left_green':4, 'left_red':5, 'left_yellow':6, 'left_off':7, 'nomotor_green':8, 'nomotor_red':9, 'nomotor_yellow':10, 'nomotor_off':11}
tfl_label = ['circle_green', 'circle_red', 'circle_yellow', 'circle_off', 'left_green', 'left_red', 'left_yellow', 'left_off', 'nomotor_green', 'nomotor_red', 'nomotor_yellow', 'nomotor_off']
def parse_tfluisee(filename):
"""
Parse a TFL uisee txt file
anno bbox: xc, yc, w, h
"""
objects = []
annofile = open(filename, 'r')
annolines = annofile.readlines()
for i, annoline in enumerate(annolines):
obj_struct = {}
annoline = annoline.strip().split(' ')
obj_struct['name'] = tfl_label[tuple(map(int, annoline[0]))[0]]
bbox = tuple(map(float, annoline[1:]))
# (xc, yc, w, h) ---> (xmin, ymin, xmax, ymax)
xmin = (bbox[0] - bbox[2]*0.5) * img_w
xmax = (bbox[0] + bbox[2]*0.5) * img_w
ymin = (bbox[1] - bbox[3]*0.5) * img_h
ymax = (bbox[1] + bbox[3]*0.5) * img_h
if xmin < 0:
xmin = 0
if ymin < 0:
ymin = 0
if xmax > img_w-1:
xmax = img_w-1
if ymax > img_h-1:
ymax = img_h-1
obj_struct['bbox'] = [int(xmin), int(ymin), int(xmax), int(ymax)]
obj_struct['difficult'] = 0 # 0-easy, 1-difficult
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:
# 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 ap
def tfl_eval(detpath, annopath, datasetfile, classname, ovthresh, use_07_metric=False):
# print('tfl eval of class: ', classname)
imgfile = open(datasetfile, 'r')
imglines = imgfile.readlines()
imagenames = [x.strip() for x in imglines]
# load annots
recs = {}
for i, filename in enumerate(imagenames):
imagename = filename.split('/')[-1].split('.')[-2]
annofile = filename.replace('images', 'labels')
annofile = annofile.replace('png', 'txt')
recs[imagename] = parse_tfluisee(annofile)
# extra gt object for this class
class_recs = {}
npos = 0
if classname=='red':
subname = ['circle_red', 'left_red', 'nomotor_red']
elif classname=='green':
subname = ['circle_green', 'left_green', 'nomotor_green']
elif classname=='yellow':
subname = ['circle_yellow', 'left_yellow', 'nomotor_yellow']
for i, filename in enumerate(imagenames):
imagename = filename.split('/')[-1].split('.')[-2]
R = [obj for obj in recs[imagename] if obj['name'] in subname]
# print('R: ', R)
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)
# print('det: {} \t bbox: {}'.format(det, bbox))
class_recs[imagename] = {'bbox': bbox, 'difficult': difficult, 'det': det}
# read dets
splitlines = []
for i in range(len(subname)):
detfile = detpath.format(subname[i])
# print('detfile: ', detfile)
with open(detfile, 'r') as f:
lines = f.readlines()
splitlines += [x.strip().split(' ') for x in lines]
# print('det image len: ', len(splitlines))
# print('det image len all**********************: ', len(splitlines))
if len(splitlines)==0:
return 0, 0, 0
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)
# print('BBGT: ', len(BBGT))
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
# print('inters: {} \t uni: {} \n'.format(inters, uni))
ovmax = np.max(overlaps)
jmax = np.argmax(overlaps)
# print('name: {} \n ---overlaps: {} \t ovmax: {} \t jmax: {}\n'.format(image_ids[d], overlaps, ovmax, jmax))
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
# print('before npos: {}\t fp: {}\t, tp: {}'.format(npos, fp, tp))
fp = np.cumsum(fp)
tp = np.cumsum(tp)
# print('npos: {}\t fp: {}\t, tp: {}'.format(npos, fp, tp))
if npos>0:
rec = tp / float(npos)
else:
# print('********************************************classname: ', classname)
return 0, 0, 0
# 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
if __name__ == "__main__":
path = os.getcwd()
# single class
detpath = os.path.join(path, '..', 'results/{}.txt')
annopath = os.path.join(path, '..', 'tfluisee/valid.txt')
datasetfile = os.path.join(path, '..', 'tfluisee/valid.txt')
thresh = 0.45
classname = 'red'
use_07_metric = True
print('thresh: {}\t use_07_metric: {}'.format(thresh, use_07_metric))
recall, precision, ap = tfl_eval(detpath, annopath, datasetfile, classname, thresh, use_07_metric)
# print('use_07_metric: {}\tclassname: {}\t recall:{}\t precision: {}\t ap: {}\t'.format(use_07_metric, classname, recall, precision, ap))
# multi class
resultspath = os.path.join(path, '..', 'results')
subfiles = os.listdir(resultspath)
mAP = []
color = ['red', 'green', 'yellow']
for i in range(len(color)):
# classname = subfiles[i].split('.txt')[0]
classname = color[i]
recall, precision, ap = tfl_eval(detpath, annopath, datasetfile, classname, thresh, use_07_metric)
# print('classname: {}\t recall:{}\t precision: {}\t ap: {}\t'.format(classname, recall, precision, ap))
mAP.append(ap)
mAP = tuple(mAP)
print('AP: {}\nmAP: {}'.format(mAP, float(sum(mAP)/len(mAP))))
# use_07_metric = False
# print('thresh: {}\t use_07_metric: {}'.format(thresh, use_07_metric))
# recall, precision, ap = tfl_eval(detpath, annopath, datasetfile, classname, thresh, use_07_metric)
# # print('use_07_metric: {}\tclassname: {}\t recall:{}\t precision: {}\t ap: {}\t'.format(use_07_metric, classname, recall, precision, ap))
#
# # multi class
# resultspath = os.path.join(path, '..', 'results')
# subfiles = os.listdir(resultspath)
# mAP = []
# for i in range(len(subfiles)):
# classname = subfiles[i].split('.txt')[0]
# recall, precision, ap = tfl_eval(detpath, annopath, datasetfile, classname, thresh, use_07_metric)
# # print('classname: {}\t recall:{}\t precision: {}\t ap: {}\t'.format(classname, recall, precision, ap))
# mAP.append(ap)
# mAP = tuple(mAP)
# print('AP: {}\nmAP: {}'.format(mAP, float(sum(mAP)/len(mAP))))
View Code
需要更改类别相关的代码；
Interplolated AP（Pascal Voc 2008 的AP计算方式）
Area under curve
COCO mAP
参考
1. Yolov3-Darknet版本计算mAP；
2. 深度学习中的AP和mAP总结；
3. voc2012中xml文档代码简单说明；
4. 目标检测中的AP，mAP;
5. voc_eval;
完
