訓練tiny-yolov3和yolov3一樣。只不過需要重新寫一個權重文件。
１．準備權重文件
./darknet partial cfg/yolov3-tiny.cfg yolov3-tiny.weights yolov3-tiny.conv.15 15
先是獲得訓練好的yolov3-tiny的權重用來test：
yolov3-tiny.weights這個文件需要自己下，下載地址如下。
wget https://pjreddie.com/media/files/yolov3-tiny.weights
然後獲得卷積層的權重用來訓練自己的數據：這一步是配置權重文件，理論上並沒有說提取多少層的特徵合適，這裏我們提取前15層當作與訓練模型
２．開始訓練
./darknet detector train data/voc.data yolov3-tiny.cfg yolov3-tiny.conv.15 -gpu 0
３．保存測試結果
運行darknet官方代碼中的detector valid指令，生成對測試集的檢測結果。
.\darknet detector valid <voc.data文件路徑> <cfg文件路徑> <weights文件路徑> -out ""
４．下載檢測用腳本文件 reval_voc_py.py和voc_eval_py.py
reval_voc_py3.py
#!/usr/bin/env python
# Adapt from ->
# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------
# <- Written by Yaping Sun
"""Reval = re-eval. Re-evaluate saved detections."""
import os, sys, argparse
import numpy as np
import _pickle as cPickle
#import cPickle
from voc_eval_py3 import voc_eval
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='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)
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'
path = os.path.join(out_dir, filename)
return path
def do_python_eval(devkit_path, year, image_set, classes, output_dir = 'results'):
annopath = os.path.join(
devkit_path,
'VOC' + year,
'Annotations',
'{}.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
print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No'))
print('devkit_path=',devkit_path,', year = ',year)
if not os.path.isdir(output_dir):
os.mkdir(output_dir)
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=0.5,
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:
cPickle.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('~~~~~~~~')
print('')
print('--------------------------------------------------------------')
print('Results computed with the **unofficial** Python eval code.')
print('Results should be very close to the official MATLAB eval code.')
print('-- Thanks, The Management')
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, output_dir)
reval_voc_py.py
#!/usr/bin/env python
# Adapt from ->
# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------
# <- Written by Yaping Sun
"""Reval = re-eval. Re-evaluate saved detections."""
import os, sys, argparse
import numpy as np
import cPickle
from voc_eval import voc_eval
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='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)
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'
path = os.path.join(out_dir, filename)
return path
def do_python_eval(devkit_path, year, image_set, classes, output_dir = 'results'):
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
print 'VOC07 metric? ' + ('Yes' if use_07_metric else 'No')
if not os.path.isdir(output_dir):
os.mkdir(output_dir)
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=0.5,
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'), 'w') as f:
cPickle.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('~~~~~~~~')
print('')
print('--------------------------------------------------------------')
print('Results computed with the **unofficial** Python eval code.')
print('Results should be very close to the official MATLAB eval code.')
print('-- Thanks, The Management')
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, output_dir)
voc_eval_py.py
voc_eval_py.py
# --------------------------------------------------------
# Fast/er R-CNN
# Licensed under The MIT License [see LICENSE for details]
# Written by Bharath Hariharan
# --------------------------------------------------------
import xml.etree.ElementTree as ET #讀取xml。
import os
import cPickle #序列化存儲模塊。
import numpy as np
def parse_rec(filename):#解析讀取xml函數。
""" 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): #單個測量AP的函數。
""" 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, ######主函數
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. #產生的txt文件，裏面是一張圖片的各個detection。
annopath: Path to annotations
annopath.format(imagename) should be the xml annotations file. #xml 文件與對應的圖像相呼應。
imagesetfile: Text file containing the list of images, one image per line. #一個txt文件，裏面是每個圖片的地址，每行一個地址。
classname: Category name (duh) #種類的名字，即類別。
cachedir: Directory for caching the annotations #緩存標註的目錄。
[ovthresh]: Overlap threshold (default = 0.5) #重疊的多少大小。
[use_07_metric]: Whether to use VOC07's 11 point AP computation
(default False) #是否使用VOC07的11點AP計算。
"""
# 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 加載ground truth。
if not os.path.isdir(cachedir):
os.mkdir(cachedir)
cachefile = os.path.join(cachedir, 'annots.pkl') #即將新建文件的路徑。
# read list of images
with open(imagesetfile, 'r') as f:
lines = f.readlines() #讀取文本里的所以文本行，作爲衆多文圖片的路徑。
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，則
# load annots
recs = {}
for i, imagename in enumerate(imagenames):
recs[imagename] = parse_rec(annopath.format(imagename)) #這裏的format不知道啥意思
if i % 100 == 0:
print 'Reading annotation for {:d}/{:d}'.format(
i + 1, len(imagenames)) #進度條。
# save
print 'Saving cached annotations to {:s}'.format(cachefile)
with open(cachefile, 'w') as f:
cPickle.dump(recs, f) #寫入cPickle文件裏面。寫入的是一個字典，左側爲xml文件名，右側爲文件裏面個各個參數。
else:
# load
with open(cachefile, 'r') as f:
recs = cPickle.load(f) #如果已經有了這個cPickle文件，則加載一下。
# extract gt objects for this class #對每張圖片的xml獲取函數指定類的bbox等。
class_recs = {}
npos = 0
for imagename in imagenames:
R = [obj for obj in recs[imagename] if obj['name'] == classname] #獲取每個文件中某種類別的物體。
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基本都爲0.
det = [False] * len(R) #list中形參len(R)個False。
npos = npos + sum(~difficult) #自增，sum求得的值基本都爲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] #圖片index。
confidence = np.array([float(x[1]) for x in splitlines]) #類別置信度
BB = np.array([[float(z) for z in x[2:]] for x in splitlines]) #變爲浮點型的bbox。
# sort by confidence
sorted_ind = np.argsort(-confidence) #對confidence的index根據值大小進行降序排列。
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] 對圖片進行重排。
# go down dets and mark TPs and FPs
nd = len(image_ids)
tp = np.zeros(nd)
fp = np.zeros(nd) #歸零。
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
５．使用reval_voc_py.py計算出mAP值並且生成pkl文件
python reval_voc_py3.py --voc_dir <voc文件路徑> --year <年份> --image_set <驗證集文件名> --classes <類名文件路徑> <輸出文件夾名
先將第三部生成的results文件夾移動到當前腳本文件所在的位置，然後執行上述指令。
首先python表示運行python代碼
reval_voc_py3.py表示當前運行的腳本文件名，python3的話就用這個，python2的話用reval_voc.py。
voc文件路徑就是當時訓練用的VOC數據集的路徑，比如windows下 d:\darknet\scripts\VOCdevkit，linux就是 \home\xxx\darknet\scripts\VOCdevkit,這裏只是打個比方，讀者請替換成自己需要的路徑
年份就是VOC數據集裏VOC文件名裏的時間，比如2007、2012這樣的。
驗證集文件名一般是VOCdevkit\VOC2017\ImageSets\Main中的文件中txt文件名，比如train.txt，把需要測試的圖片名全部塞進去就可以了，如果沒有的話自行創建（不過沒有的話怎麼訓練的呢）。注意:這裏只需要填文件名，txt後綴都不需要的。
類名文件路徑就是voc.names文件的路徑，在voc.data文件裏面是有的，第4行names那裏。
輸出文件夾名就自己隨便寫了，比如我這裏寫的testForCsdn。
參數全部替換好就可以跑了，大概畫風如下所示：
這時會在腳本當前目錄生成一個存放了pkl文件的文件夾，名字就是剛纔輸入的輸出文件夾名。（這裏的名字不需要和我的一樣，如果你有多個類的話，就會生成多個文件，文件名就是你的類名）
注意，這時已經能看到mAP值了。（我這裏的驗證集較小，目標較簡單，所以mAP大了些，不用在意）
６ 用matplotlib繪製PR曲線