YOLOv3 训练自己的数据集
1.VOC数据集准备
使用ImageLab软件数据标注产生与图片对应的.xml
Annotations存放xml文件，JPEGImages存放原图，labels存放annotation对应的txt文件，
deal.xml对xml文件修改（folder，filname，path，object的name），list.py划分train和val数据集产生train_0708.txt和val_0708.txt的原图路径列表，voc_label.py产生annotation对应的txt文件。
# coding=utf-8
import os
import xml.dom.minidom
import xml.etree.ElementTree as ET
xmlpath = "/media/ices/d171fa47-c64c-42f5-886e-92bc88e1f6a6/ices12/shiyou/Annotations/"
imgpath="/media/ices/d171fa47-c64c-42f5-886e-92bc88e1f6a6/ices12/shiyou/JPEGImages/"
newpath = "/media/ices/d171fa47-c64c-42f5-886e-92bc88e1f6a6/ices12/shiyou/Annotation/"
#files = os.listdir(path) 得到文件夹下所有文件名称
for xmlname in os.listdir(xmlpath): # 遍历文件夹
p = xmlpath+xmlname
dom = xml.dom.minidom.parse(p)
root = dom.documentElement
epath = root.getElementsByTagName('path')
folder = root.getElementsByTagName('folder')
epath[0].firstChild.data = imgpath+xmlname.split('.')[0]+'.jpg'
folder[0].firstChild.data = 'JPEGImages'
print epath[0].firstChild.data
with open(newpath+ xmlname, 'w') as fh:
dom.writexml(fh)
print '写入 '+xmlname+' OK!'2.配置文件的修改
(1) Makfile
GPU=1 #如果使用GPU设置为1，CPU设置为0
CUDNN=1 #如果使用CUDNN设置为1，否则为0
OPENCV=0 #如果调用摄像头，还需要设置OPENCV为1，否则为0
OPENMP=0 #如果使用OPENMP设置为1，否则为0
DEBUG=0 #如果使用DEBUG设置为1，否则为0
CC=gcc
NVCC=/usr/local/cuda/bin/nvcc #NVCC=nvcc 修改为自己的路径
AR=ar
ARFLAGS=rcs
OPTS=-Ofast
LDFLAGS= -lm -pthread
COMMON= -Iinclude/ -Isrc/
CFLAGS=-Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC
...
ifeq ($(GPU), 1)
COMMON+= -DGPU -I/usr/local/cuda/include/ #修改为自己的路径
CFLAGS+= -DGPU
LDFLAGS+= -L/home/hebao/cuda-9.0/lib64 -lcuda -lcudart -lcublas -lcurand #修改为自己的路径
endif(2) cfg（注意此处filters个数要修改三次！！！）
[net]
# Testing
# batch=1
# subdivisions=1
# Training
batch=64
subdivisions=8
......
[convolutional]
size=1
stride=1
pad=1
filters=30###(（类别数目+1）×5)
activation=linear
[yolo]
mask = 6,7,8
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=5###20
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=0###1
......
[convolutional]
size=1
stride=1
pad=1
filters=30###75
activation=linear
[yolo]
mask = 3,4,5
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=5###20
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=0###1
......
[convolutional]
size=1
stride=1
pad=1
filters=30###75
activation=linear
[yolo]
mask = 0,1,2
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=5###20
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=0###1（3） voc.data
classes= 5
train = /media/ices/d171fa47-c64c-42f5-886e-92bc88e1f6a6/ices12/shiyou/train_0708.txt
valid = /media/ices/d171fa47-c64c-42f5-886e-92bc88e1f6a6/ices12/shiyou/val_0708.txt
names = data/voc.names
backup = backup0708（4） voc.names
car
truck
building
collapse
river执行：sudo ./darknet detector train /home/ices/darknet/cfg/voc.data /home/ices/darknet/cfg/yolov3-voc0605.cfg /home/ices/darknet/backup0708/yolov3-voc0605.backup -gpus 0,1
3.测试
./darknet detector valid cfg/voc.data cfg/yolov3-voc0605.cfg backup3_1/yolov3-voc0605_final.weights -out g-
python 123.py /home/ices/darknet/results/g-1.txt /home/ices/darknet/V3/darknet/scripts/shiyou0605_val.txt 1123.py
# --------------------------------------------------------
# Fast/er R-CNN
# Licensed under The MIT License [see LICENSE for details]
# Written by Bharath Hariharan
# --------------------------------------------------------
import xml.etree.ElementTree as ET
import os
import pickle
import numpy as np
import sys
import re
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:
# 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 voc_eval(detpath,
annopath,
imagesetfile,
classname,
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.
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]
#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, 'w') as f:
# cPickle.dump(recs, f)
#else:
# load
# with open(cachefile, 'r') as f:
# recs = cPickle.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)
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]
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
if __name__ =='__main__':
if len(sys.argv)<4:
print('error!!!')
print('the argv must be python 123.py [detpath] [testfile] [testname]')
else:
detpath=sys.argv[1]
testfile=sys.argv[2]
testname=sys.argv[3]
name_id=re.compile('.*/(.*)\.jpg')
name_xml = re.compile('(.*/).*.jpg')
#print(re.findall(name_id,'456/123.jpg'))
with open(testfile, 'r') as f:
lines = f.readlines()
f=open('123_testname.txt','w')
for i in lines:
temp=re.findall(name_id,i)
f.write(temp[0]+'\n')
f.close()
testfilepath=os.getcwd()+'/123_testname.txt'
temp = re.findall(name_xml, lines[0])
temp[0] = temp[0].replace('JPEGImages','Annotation')
annopath=temp[0]+'{}.xml'
print(voc_eval(detpath,annopath,testfilepath,testname)[2])