deeplab_v2
好记性不如烂笔头, 最近用Deeplab v2跑的图像分割,现记录如下。 官方源码地址如下:https://bitbucket.org/aquariusjay/deeplab-public-ver2/overview但是此源码只是为deeplab网络做相应变形的caffe,如果需要fine tuning微调网络,还需要准备以下文件:
txt文件:文件中有数据集的名字列表的txt文件,训练测试集列表
训练好的init.caffemodel: 针对deeplab v2,作者有已经预训练好的两个模型参数:DeepLabv2_VGG16 和DeepLabv2_ResNet101
网络结构prototxt文件: train.prototxt和solver.prototxt,分别在:DeepLabv2_VGG16 和 DeepLabv2_ResNet101
官网脚本文件: 三个sh文件,建议使用脚本文件,初看虽不懂,但是比python版本的运行简单很多 注:本博客只涉及脚本版本的训练
cd ~ mkdir deeplab cd deeplab git clone https://bitbucket.org/aquariusjay/deeplab-public-ver2.git
mkdir -p ~/deeplab/exper/voc12/config/deeplab_largeFOV mkdir -p ~/deeplab/exper/voc12/features/labels mkdir -p ~/deeplab/exper/voc12/features2/labels mkdir -p ~/deeplab/exper/voc12/list mkdir -p ~/deeplab/exper/voc12/log mkdir -p ~/deeplab/exper/voc12/model/deeplab_largeFOV mkdir -p ~/deeplab/exper/voc12/res
有时候可能会打不开网页,无法访问,也可以在我的资源中下载,我已经原资料打包上传,无法在官网下载就点这里如下:
以prototxt为后缀的网络结构文件train.prototxt 、test.prototxt 以及solver.prototxt文件移动到~/deeplab/exper/voc12/config/deeplab_largeFOV 文件夹下.
unzip prototxt_and_model.zip mv *.prototxt ~/deeplab/exper/voc12/config/deeplab_largeFOV mv *.caffemodel ~/deeplab/exper/voc12/model/deeplab_largeFOV unzip link.zip cd link mv * ~/deeplab/exper/voc12 unzip list.zip cd list mv * ~/deeplab/exper/voc12/list
论文中提到的pascal voc训练,其使用的数据不只是官网下载的pascal-voc2012源数据,而是由voc2012和另外一个pascal voc2012增强数据集合并而成 。 具体数据整理步骤请看另一篇博客从头开始训练deeplab v2系列之二【VOC2012数据集】
对于其他图像分割的数据集,我们也可以处理成类似voc2012数据集的格式,进行fine tuning, 这里分别有对pascal context数据集和nyu v2数据集的数据处理说明。
deeplab v2源码直接第一次使用的话确实有很多坑,其中除了数据集要注意的地方,大部分的坑在脚本文件。不过运行成功之后再换其他数据集,真的很方便,不需要改网络文件和文本文件,只需要修改脚本文件script,就会自动生成相应的网络结构文件和txt文件,所以学会修改脚本文件至关重要训练速度相对于某些图像分割的网络超快,而且即使你的分类数超过255类,也没关系。 上图我选的459类的数据集训练结果
#!/bin/sh ## MODIFY PATH for YOUR SETTING ROOT_DIR= CAFFE_DIR=../code #你的caffe路径,clone作者的deeplab v2得到deeplab-public-ver2文件夹,即为此处caffe路径, 注意:此处caffe要编译 CAFFE_BIN=${CAFFE_DIR}/.build_release/tools/caffe.bin EXP=voc12 #此目录路径~/deeplab/exper/voc12 if [ "${EXP}" = "voc12" ]; then NUM_LABELS=21 DATA_ROOT=${ROOT_DIR}/rmt/data/pascal/VOCdevkit/VOC2012 #VOC数据目录,修改为你的数据目录 else NUM_LABELS=0 echo "Wrong exp name" fi ## Specify which model to train ########### voc12 ################ NET_ID=deelab_largeFOV ##此处文件名有问题应该改为deeplab_largeFOV ## Variables used for weakly or semi-supervisedly training #TRAIN_SET_SUFFIX= #TRAIN_SET_SUFFIX=_aug #此处应该取消注释,当你run training 1时 #TRAIN_SET_STRONG=train #TRAIN_SET_STRONG=train200 #TRAIN_SET_STRONG=train500 #TRAIN_SET_STRONG=train1000 #TRAIN_SET_STRONG=train750 #TRAIN_SET_WEAK_LEN=5000 DEV_ID=0 ##### ## Create dirs CONFIG_DIR=${EXP}/config/${NET_ID} #此处目录为/voc12/config/deeplab_largeFOV MODEL_DIR=${EXP}/model/${NET_ID} mkdir -p ${MODEL_DIR} #创建MODEL_DIR目录为/voc12/model/deeplab_largeFOV LOG_DIR=${EXP}/log/${NET_ID} mkdir -p ${LOG_DIR} export GLOG_log_dir=${LOG_DIR} ## Run RUN_TRAIN=1 #为1说明执行train RUN_TEST=1 #为1说明执行test RUN_TRAIN2=0 RUN_TEST2=0 ## Training #1 (on train_aug) if [ ${RUN_TRAIN} -eq 1 ]; then #r如果RUN_TRAIN为1 # LIST_DIR=${EXP}/list TRAIN_SET=train${TRAIN_SET_SUFFIX} if [ -z ${TRAIN_SET_WEAK_LEN} ]; then #如果TRAIN_SET_WEAK_LEN长度为零则为真 TRAIN_SET_WEAK=${TRAIN_SET}_diff_${TRAIN_SET_STRONG} comm -3 ${LIST_DIR}/${TRAIN_SET}.txt ${LIST_DIR}/${TRAIN_SET_STRONG}.txt > ${LIST_DIR}/${TRAIN_SET_WEAK}.txt #comm -3 指令为不输出两个文件共有的行,此处即为除去train.txt文件中train_aug.txt的数据,其他都输出到train_aud_diff_train.txt else TRAIN_SET_WEAK=${TRAIN_SET}_diff_${TRAIN_SET_STRONG}_head${TRAIN_SET_WEAK_LEN} comm -3 ${LIST_DIR}/${TRAIN_SET}.txt ${LIST_DIR}/${TRAIN_SET_STRONG}.txt | head -n ${TRAIN_SET_WEAK_LEN} > ${LIST_DIR}/${TRAIN_SET_WEAK}.txt fi # MODEL=${EXP}/model/${NET_ID}/init.caffemodel #下载的vgg16或者ResNet101中的 model # echo Training net ${EXP}/${NET_ID} for pname in train solver; do sed "$(eval echo $(cat sub.sed))" ${CONFIG_DIR}/${pname}.prototxt > ${CONFIG_DIR}/${pname}_${TRAIN_SET}.prototxt #复制文件train.prototxt到train_train_train_aug.prototxt,slove同理 done #此部分运行时如以下命令 CMD="${CAFFE_BIN} train --solver=${CONFIG_DIR}/solver_${TRAIN_SET}.prototxt --gpu=${DEV_ID}" if [ -f ${MODEL} ]; then CMD="${CMD} --weights=${MODEL}" fi echo Running ${CMD} && ${CMD} fi #train部分运行时,即以下运行命令 ../deeplab-public-ver2/.build_release/tools/caffe.bin train --solver=volab_largeFOV/solver_train_aug.prototxt --gpu=0 --weights=voc12/model/deeplab_largeFOV/init.caf femodel #上述命令中,solver_train_aug.prototxt由solve.prototxt文件复制而来,init.caffemodel为原始下载了的VGG16的model ## Test #1 specification (on val or test) if [ ${RUN_TEST} -eq 1 ]; then # for TEST_SET in val; do TEST_ITER=`cat ${EXP}/list/${TEST_SET}.txt | wc -l` #此处计算val.txt文件中测试图片个数,共1449个 MODEL=${EXP}/model/${NET_ID}/test.caffemodel if [ ! -f ${MODEL} ]; then MODEL=`ls -t ${EXP}/model/${NET_ID}/train_iter_*.caffemodel | head -n 1` fi # echo Testing net ${EXP}/${NET_ID} FEATURE_DIR=${EXP}/features/${NET_ID} mkdir -p ${FEATURE_DIR}/${TEST_SET}/fc8 mkdir -p ${FEATURE_DIR}/${TEST_SET}/fc9 mkdir -p ${FEATURE_DIR}/${TEST_SET}/seg_score sed "$(eval echo $(cat sub.sed))" ${CONFIG_DIR}/test.prototxt > ${CONFIG_DIR}/test_${TEST_SET}.prototxt CMD="${CAFFE_BIN} test --model=${CONFIG_DIR}/test_${TEST_SET}.prototxt --weights=${MODEL} --gpu=${DEV_ID} --iterations=${TEST_ITER}" echo Running ${CMD} && ${CMD} done fi #test部分运行时,即以下运行命令../deeplab-public-ver2/.build_release/tools/caffe.bin test --model=voc12/config/deeplab_largeFOV/test_val.prototxt --weights=voc12/model/deeplab_largeFOV/train_iter_20000.caffemodel --gpu=0 --iterations=1449 #上述命令中,test_val.prototxt由test.prototxt文件复制而来,train_iter_20000.caffemode由第一部分train得到的model ## Training #2 (finetune on trainval_aug) if [ ${RUN_TRAIN2} -eq 1 ]; then # LIST_DIR=${EXP}/list TRAIN_SET=trainval${TRAIN_SET_SUFFIX} if [ -z ${TRAIN_SET_WEAK_LEN} ]; then TRAIN_SET_WEAK=${TRAIN_SET}_diff_${TRAIN_SET_STRONG} comm -3 ${LIST_DIR}/${TRAIN_SET}.txt ${LIST_DIR}/${TRAIN_SET_STRONG}.txt > ${LIST_DIR}/${TRAIN_SET_WEAK}.txt else TRAIN_SET_WEAK=${TRAIN_SET}_diff_${TRAIN_SET_STRONG}_head${TRAIN_SET_WEAK_LEN} comm -3 ${LIST_DIR}/${TRAIN_SET}.txt ${LIST_DIR}/${TRAIN_SET_STRONG}.txt | head -n ${TRAIN_SET_WEAK_LEN} > ${LIST_DIR}/${TRAIN_SET_WEAK}.txt fi # MODEL=${EXP}/model/${NET_ID}/init2.caffemodel if [ ! -f ${MODEL} ]; then MODEL=`ls -t ${EXP}/model/${NET_ID}/train_iter_*.caffemodel | head -n 1` fi # echo Training2 net ${EXP}/${NET_ID} for pname in train solver2; do sed "$(eval echo $(cat sub.sed))" ${CONFIG_DIR}/${pname}.prototxt > ${CONFIG_DIR}/${pname}_${TRAIN_SET}.prototxt done CMD="${CAFFE_BIN} train --solver=${CONFIG_DIR}/solver2_${TRAIN_SET}.prototxt --weights=${MODEL} --gpu=${DEV_ID}" echo Running ${CMD} && ${CMD} fi ## Test #2 on official test set if [ ${RUN_TEST2} -eq 1 ]; then # for TEST_SET in val test; do TEST_ITER=`cat ${EXP}/list/${TEST_SET}.txt | wc -l` MODEL=${EXP}/model/${NET_ID}/test2.caffemodel if [ ! -f ${MODEL} ]; then MODEL=`ls -t ${EXP}/model/${NET_ID}/train2_iter_*.caffemodel | head -n 1` fi # echo Testing2 net ${EXP}/${NET_ID} FEATURE_DIR=${EXP}/features2/${NET_ID} mkdir -p ${FEATURE_DIR}/${TEST_SET}/fc8 mkdir -p ${FEATURE_DIR}/${TEST_SET}/crf sed "$(eval echo $(cat sub.sed))" ${CONFIG_DIR}/test.prototxt > ${CONFIG_DIR}/test_${TEST_SET}.prototxt CMD="${CAFFE_BIN} test --model=${CONFIG_DIR}/test_${TEST_SET}.prototxt --weights=${MODEL} --gpu=${DEV_ID} --iterations=${TEST_ITER}" echo Running ${CMD} && ${CMD} done fi
还没有评论,说两句吧!
热门资源
Keras-ResNeXt
Keras ResNeXt Implementation of ResNeXt models...
seetafaceJNI
项目介绍 基于中科院seetaface2进行封装的JAVA...
spark-corenlp
This package wraps Stanford CoreNLP annotators ...
capsnet-with-caps...
CapsNet with capsule-wise convolution Project ...
inferno-boilerplate
This is a very basic boilerplate example for pe...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com