最近一段时间主要是做目标检测的任务,在没接触DL之前,受到目标图像尺度、特征不明显等影响传统方法效果并不是很好。
一、跑通SSD-tensorflow Demo
这一步基本都可以复现,主要参考了参照github上 balancap 的过程:
https://github.com/balancap/SSD-Tensorflow
<https://github.com/balancap/SSD-Tensorflow>
中文翻译 https://blog.csdn.net/yexiaogu1104/article/details/77415990
<https://blog.csdn.net/yexiaogu1104/article/details/77415990>
二、实现单类目标的检测
跑通了上一步 该怎么做呢,Demo中实现了20类 的目标检测,但因需要,我只训练检测行人。
1、准备数据
(1)、提取原voc数据集里含有人的 xml 和 imge
参考网友的根据自己的目录修改(我的目录有点长,认真看)
bash xxx.sh #!bin/sh year="VOC2007" # mkdir ...where to store #mkdir
.././datasets/test2/test1/ mkdir .././datasets/VOCperson/${year}_Anno/ mkdir
.././datasets/VOCperson/${year}_Image/ cd .././datasets/VOCtrainval_06-Nov-2007
/VOCdevkit/VOC2007/Annotations/ grep -H -R"<name>person</name>" > /media/xd/
000398040009
E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCperson/temp.txt
#找到有关键字的行,并把这些行存到临时文档 #grep -H -R "<name>person</name>" > temp.txt
#找到有关键字的行,并把这些行存到临时文档 cd /media/xd/000398040009
E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCperson cat
temp.txt | sort | uniq >$year.txt #根据名字排序,并把相邻的内容完全一样的多余行删除。 find -name $year
.txt | xargs perl -pi-e 's|.xml:\t\t<name>person</name>||g'
#把文档中后缀名和其他无用信息删掉,只保留没后缀名的文件名 cat $year.txt | xargs -i cp /media/xd/000398040009
E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCtrainval_06-Nov-
2007/VOCdevkit/VOC2007/Annotations/{}.xml /media/xd/000398040009
E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCperson/${year}
_Anno/ cat$year.txt | xargs -i cp /media/xd/000398040009
E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCtrainval_06-Nov-
2007/VOCdevkit/VOC2007/JPEGImages/{}.jpg /media/xd/000398040009
E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCperson/${year}
_Image/ rm temp.txt
这样就得到了含有人的 imge和相应的xml文件,如下
(2)、修改xml 文件
由于提取的xml文件中可能还有其他物体的 object 信息,需要进一步去除
bash xxx.sh #!/usr/bin/env python2 # -*- coding: utf-8 -*- """ Created on Tue
Oct 31 10:03:03 2017 @author: hans """ import os import xml.etree.ElementTree as
ET origin_ann_dir ='Annotations_old/' new_ann_dir = 'Annotations/' for
dirpaths, dirnames, filenamesin os.walk(origin_ann_dir): for filename in
filenames:if os.path.isfile(r'%s%s' %(origin_ann_dir, filename)):
origin_ann_path = os.path.join(r'%s%s' %(origin_ann_dir, filename))
new_ann_path = os.path.join(r'%s%s' %(new_ann_dir, filename)) tree =
ET.parse(origin_ann_path) root = tree.getroot()for object in root.findall(
'object'): name = str(object.find('name').text) if not (name == "person"): #去除
不是 person的 object root.remove(object) tree.write(new_ann_path)
(3)、训练集、测试集 划分
通过修改自己的相关目录,注意这里是 运行 .py 文件 ,
import os import random xmlfilepath=
r'/media/xd/000398040009E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCperson/VOC2007_Anno'
saveBasePath=
r"/media/xd/000398040009E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCperson"
trainval_percent=0.8 train_percent=0.7 total_xml = os.listdir(xmlfilepath)
num=len(total_xml) list=range(num) tv=int(num*trainval_percent)
tr=int(tv*train_percent) trainval= random.sample(list,tv)
train=random.sample(trainval,tr) print("train and val size",tv) print("traub
size",tr) ftrainval = open(os.path.join(saveBasePath,
'/media/xd/000398040009E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCperson/ImageSets/Main/trainval.txt'
),'w') ftest = open(os.path.join(saveBasePath,
'/media/xd/000398040009E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCperson/ImageSets/Main/test.txt'
),'w') ftrain = open(os.path.join(saveBasePath,
'/media/xd/000398040009E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCperson/ImageSets/Main/train.txt'
),'w') fval = open(os.path.join(saveBasePath,
'/media/xd/000398040009E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCperson/ImageSets/Main/val.txt'
),'w') for i in list: name=total_xml[i][:-4]+'\n' if i in trainval:
ftrainval.write(name)if i in train: ftrain.write(name) else: fval.write(name)
else: ftest.write(name) ftrainval.close() ftrain.close() fval.close() ftest
.close()
(4)、转 tfrecord
这一步没有太多修改,没多大问题
三、训练网络(fine-tune)
(1)修改 pascalvoc_common.py文件
(2)注意这里是微调的,才开始搞的时候我把 CHECKPOINT_PATH 注释了,直接导致 loss 30~50
,训练出来的模型也识别不出任何结果。(困了 好几天,呵呵)。用VGG-16 模型进行训练效果也同样(参数有问题?)
set files are stored.
DATASET_DIR=/media/xd/000398040009E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/datasets/VOCperson/tfrecord/
#../../../../common/dataset/VOC2007/VOCtrainval_06-Nov-2007/VOCdevkit/VOC2007_tfrecord/
#Directory where checkpoints and event logs are written to.
TRAIN_DIR=.././log_files/log_person/ #The path to a checkpoint from which to
fine-tune
CHECKPOINT_PATH=/media/xd/000398040009E3B2/txh_ubuntu/hands_on_ml/SSD-Tensorflow-master/checkpoints/VGG_VOC0712_SSD_300x300_iter_120000/VGG_VOC0712_SSD_300x300_iter_120000.ckpt
python3 ../train_ssd_network.py \ --train_dir=${TRAIN_DIR} \ --dataset_dir=${
DATASET_DIR} \ --dataset_name=pascalvoc_2007 \ --dataset_split_name=train \ -
-model_name=ssd_300_vgg \ --checkpoint_path=${CHECKPOINT_PATH} \ -
-save_summaries_secs=60 \ --save_interval_secs=600 \ --weight_decay=0.0005 \
--optimizer=adam \ --learning_rate=0.001 \ --batch_size=32 \
最后,上张效果图(有点不理想),调参、调参
四、遥感图像检测
见下一篇中 要 解决高分辨率遥感图像检测中图像太大检测不出来的问题
,也就是把图像放大后再截取图像又可以重新检测出来了。
热门工具 换一换