計算voc數據集MAP
1、首先下載voc數據集
wget https://pjreddie.com/media/files/VOCtrainval_11-May-2012.tar
wget https://pjreddie.com/media/files/VOCtrainval_06-Nov-2007.tar
wget https://pjreddie.com/media/files/VOCtest_06-Nov-2007.tar
tar xf VOCtrainval_11-May-2012.tar
tar xf VOCtrainval_06-Nov-2007.tar
tar xf VOCtest_06-Nov-2007.tar
會在當前路徑下生成VOCdevkit文件夾
2、將voc的xml標籤格式轉爲coco的txt格式
yolov3中scripts中的_label.py腳本
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
def convert(size, box):
dw = 1./(size[0])
dh = 1./(size[1])
x = (box[0] + box[1])/2.0 - 1
y = (box[2] + box[3])/2.0 - 1
w = box[1] - box[0]
h = box[3] - box[2]
x = x*dw
w = w*dw
y = y*dh
h = h*dh
return (x,y,w,h)
def convert_annotation(year, image_id):
in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year, image_id), 'w')
tree=ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult)==1:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
bb = convert((w,h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
wd = getcwd()
for year, image_set in sets:
if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)):
os.makedirs('VOCdevkit/VOC%s/labels/'%(year))
image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
list_file = open('%s_%s.txt'%(year, image_set), 'w')
for image_id in image_ids:
list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n'%(wd, year, image_id))
convert_annotation(year, image_id)
list_file.close()
os.system("cat 2007_train.txt 2007_val.txt 2012_train.txt 2012_val.txt > train.txt")
os.system("cat 2007_train.txt 2007_val.txt 2007_test.txt 2012_train.txt 2012_val.txt > train.all.txt")
3、運行腳本之後，ls查看當前路徑，有以下文件：
ls
2007_test.txt VOCdevkit
2007_train.txt voc_label.py
2007_val.txt VOCtest_06-Nov-2007.tar
2012_train.txt VOCtrainval_06-Nov-2007.tar
2012_val.txt VOCtrainval_11-May-2012.tar
4、將2007與2012數據集合並
cat 2007_train.txt 2007_val.txt 2012_*.txt > train.txt
2007+2012作爲訓練集train，2007test作爲測試集2007_test。
5、修改voc.data文件
1 classes= 20
2 train = <path-to-voc>/train.txt
3 valid = <path-to-voc>2007_test.txt
4 names = data/voc.names
5 backup = backup
6、在測試集上測試
./darknet detector valid cfg/voc.data cfg/yolov3-voc.cfg backup/yolov3-voc_final.weights -out "" -gpu 0 -thresh .5
在darknet/results目錄下生成20個類別txt文件，包含測試結果。
7、計算類別map
注意修改文件路徑 ，運行腳本，輸出單個類別ap及總的map。 並在當前路徑下生成annots.pkl文件。若後續需要重新運行腳本計算map，要先將annots.pkl文件刪除。
#coding=utf-8
from voc_eval import voc_eval
import os
current_path = os.getcwd()
results_path = current_path+"/results"
sub_files = os.listdir(results_path)
mAP = []
for i in range(len(sub_files)):
class_name = sub_files[i].split(".txt")[0]
rec, prec, ap = voc_eval('/.../darknet-master/results/{}.txt', '/.../darknet-master/vocdata/VOCdevkit/VOC2007/Annotations/{}.xml', '/.../darknet-master/vocdata/VOCdevkit/VOC2007/ImageSets/Main/test.txt', class_name, '.')
print("{} :\t {} ".format(class_name, ap))
mAP.append(ap)
mAP = tuple(mAP)
print("***************************")
print("mAP :\t {}".format( float( sum(mAP)/len(mAP)) ))
計算單個類別的ap值
# encoding: utf-8
from voc_eval import voc_eval
rec,prec,ap=voc_eval('/.../darknet-master/results/{}.txt', '/.../VOCdevkit/VOC2007/Annotations/{}.xml', '/.../VOCdevkit/VOC2007/ImageSets/Main/test.txt', 'person', '.')
print('rec',rec)
print('prec',prec)
print('ap',ap)
https://blog.csdn.net/amusi1994/article/details/81564504
https://pjreddie.com/darknet/yolo/
計算coco數據集MAP
1、首先下載coco數據集
darknet-master目錄下打開終端
cp scripts/get_coco_dataset.sh data
cd data
bash get_coco_dataset.sh
在darknet-master/data下會生成coco文件夾，包含所有數據。大概29G
2、修改cfg/coco.data文件
1 classes= 80
2 train = data/coco/trainvalno5k.txt
3 valid = data/coco/5k.txt
4 names = data/coco.names
5 backup = backup
3、測試，生成json文件
./darknet detector valid cfg/coco.data cfg/yolov3.cfg yolov3.weights
測試5000張圖片，在results文件夾下生成coco_results.json文件。
4、運行python腳本計算map
#-*- coding:utf-8 -*-
import matplotlib.pyplot as plt
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
import numpy as np
import skimage.io as io
import pylab,json
pylab.rcParams['figure.figsize'] = (10.0, 8.0)
def get_img_id(file_name):
ls = []
myset = []
annos = json.load(open(file_name, 'r'))
for anno in annos:
ls.append(anno['image_id'])
myset = {}.fromkeys(ls).keys()
return myset
if __name__ == '__main__':
annType = ['segm', 'bbox', 'keypoints']#set iouType to 'segm', 'bbox' or 'keypoints'
annType = annType[1] # specify type here
cocoGt_file = '/.../data/coco2014/annotations/instances_val2014.json'
cocoGt = COCO(cocoGt_file)#取得標註集中coco json對象
cocoDt_file = '/.../darknet/results/coco_results.json'
imgIds = get_img_id(cocoDt_file)
print len(imgIds)
cocoDt = cocoGt.loadRes(cocoDt_file)#取得結果集中image json對象
imgIds = sorted(imgIds)#按順序排列coco標註集image_id
imgIds = imgIds[0:5000]#標註集中的image數據
cocoEval = COCOeval(cocoGt, cocoDt, annType)
cocoEval.params.imgIds = imgIds#參數設置
cocoEval.evaluate()#評價
cocoEval.accumulate()#積累
cocoEval.summarize()#總結
將腳本中的路徑改稱自己數據的對應路徑。
報錯：ImportError: No module named pycocotools.coco
解決：即沒有安裝該包， pip install pycocotools即可。
報錯：ImportError: No module named skimage.io
解決：pip install scikit-image
5、結果 608x608
$ python calcocomap.py
loading annotations into memory...
Done (t=3.49s)
creating index...
index created!
4991
Loading and preparing results...
DONE (t=2.42s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=29.24s).
Accumulating evaluation results...
DONE (t=3.07s).
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.334
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.585
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.345
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.194
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.365
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.439
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.291
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.446
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.470
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.304
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.502
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.593
https://blog.csdn.net/qq_33074561/article/details/81944897
參考鏈接：