All Projects → xmojiao → Deeplab_v2

xmojiao / Deeplab_v2

基于v2版本的deeplab,使用VGG16模型,在VOC2012,Pascal-context,NYU-v2等多个数据集上进行训练

Projects that are alternatives of or similar to Deeplab v2

Tensorflow
Tensorflow相关教程
Stars: ✭ 148 (-0.67%)
Mutual labels:  jupyter-notebook
Covid19 inference forecast
Stars: ✭ 148 (-0.67%)
Mutual labels:  jupyter-notebook
Project kojak
Training a Neural Network to Detect Gestures and Control Smart Home Devices with OpenCV in Python
Stars: ✭ 147 (-1.34%)
Mutual labels:  jupyter-notebook
Qa With Tensorflow
Stars: ✭ 148 (-0.67%)
Mutual labels:  jupyter-notebook
Refer
Referring Expression Datasets API
Stars: ✭ 148 (-0.67%)
Mutual labels:  jupyter-notebook
Covid19
Analyses about the COVID-19 virus
Stars: ✭ 149 (+0%)
Mutual labels:  jupyter-notebook
Vde
Variational Autoencoder for Dimensionality Reduction of Time-Series
Stars: ✭ 148 (-0.67%)
Mutual labels:  jupyter-notebook
Machine Learning
python,机器学习笔记,machine learning,nlp
Stars: ✭ 149 (+0%)
Mutual labels:  jupyter-notebook
Cpndet
Corner Proposal Network for Anchor-free, Two-stage Object Detection
Stars: ✭ 149 (+0%)
Mutual labels:  jupyter-notebook
Predicting Stock Prices With Linear Regression
Stars: ✭ 149 (+0%)
Mutual labels:  jupyter-notebook
Nyc Transport
A Unified Database of NYC transport (subway, taxi/Uber, and citibike) data.
Stars: ✭ 148 (-0.67%)
Mutual labels:  jupyter-notebook
Animatedpythonpatterns
Animated GIF patterns made in Python Matplotlib.
Stars: ✭ 148 (-0.67%)
Mutual labels:  jupyter-notebook
Practicaldl
A Practical Guide to Deep Learning with TensorFlow 2.0 and Keras materials for Frontend Masters course
Stars: ✭ 149 (+0%)
Mutual labels:  jupyter-notebook
Tensorflow center loss
Center Loss implementation with TensorFlow
Stars: ✭ 148 (-0.67%)
Mutual labels:  jupyter-notebook
Machine Learning
🌎 machine learning tutorials (mainly in Python3)
Stars: ✭ 1,924 (+1191.28%)
Mutual labels:  jupyter-notebook
Stock Price Predictor
This project seeks to utilize Deep Learning models, Long-Short Term Memory (LSTM) Neural Network algorithm, to predict stock prices.
Stars: ✭ 146 (-2.01%)
Mutual labels:  jupyter-notebook
Covid 19 Eda Tutorial
This tutorial's purpose is to introduce people to the [2019 Novel Coronavirus COVID-19 (2019-nCoV) Data Repository by Johns Hopkins CSSE](https://github.com/CSSEGISandData/COVID-19) and how to explore it using some foundational packages in the Scientific Python Data Science stack.
Stars: ✭ 149 (+0%)
Mutual labels:  jupyter-notebook
Pytorch Tutorials Kr
🇰🇷PyTorch에서 제공하는 튜토리얼의 한국어 번역을 위한 저장소입니다. (Translate PyTorch tutorials in Korean🇰🇷)
Stars: ✭ 148 (-0.67%)
Mutual labels:  jupyter-notebook
Forecasting
Time Series Forecasting Best Practices & Examples
Stars: ✭ 2,123 (+1324.83%)
Mutual labels:  jupyter-notebook
Machinehack
Stars: ✭ 149 (+0%)
Mutual labels:  jupyter-notebook

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:


1.建立deeplab文件夹, 并下载deeplab源代码

cd ~
mkdir deeplab
cd deeplab
git clone https://bitbucket.org/aquariusjay/deeplab-public-ver2.git

2.依次建立存放设置文件夹,预测结果文件夹,数据集txt文件夹,log文件夹,model文件夹,evaluation文件夹

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

3.下载官方给的txt文件夹,以及预训练的model和网络结构文件,如上所示。

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: 这里写图片描述


这里写图片描述


这里写图片描述


4. 把下载解压后的相应文件移动到相应文件夹

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

5.数据集处理

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】 这里写图片描述

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nyu v2数据集的数据处理说明。

6.脚本文件解析与修改方法

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 这里写图片描述


deeplab2的script文件run_pascal.sh 解析

#!/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


Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].