faster_rcnn_end2end.sh源码分析

#!/bin/bash
# Usage:
# ./experiments/scripts/faster_rcnn_end2end.sh GPU NET DATASET [options args to {train,test}_net.py]
# DATASET is either pascal_voc or coco.
#
# Example:
# ./experiments/scripts/faster_rcnn_end2end.sh 0 VGG_CNN_M_1024 pascal_voc \
#   --set EXP_DIR foobar RNG_SEED 42 TRAIN.SCALES "[400, 500, 600, 700]"

set -x    #将后面执行的命令输出到屏幕
set -e    #如果命令的返回值不是0 则退出shell

export PYTHONUNBUFFERED="True"   #和缓存有关系的一个变量，使得按顺序输出

GPU_ID=$1     #这一部分是读取命令信息，包括GPU的编号，网络类型，以及数据集类型等       
NET=$2
NET_lc=${NET,,}
DATASET=$3

array=( $@ )           
len=${#array[@]}
EXTRA_ARGS=${array[@]:3:$len}
EXTRA_ARGS_SLUG=${EXTRA_ARGS// /_}

case $DATASET in #根据输入数据类型，进行不同的处理，分为3种情况pascal_voc; coco; 错误类型
  pascal_voc)
    TRAIN_IMDB="voc_2007_trainval"  #定义相应的变量
    TEST_IMDB="voc_2007_test"
    PT_DIR="pascal_voc"
    ITERS=70000              #定义迭代次数
    ;;
  coco)
    # This is a very long and slow training schedule
    # You can probably use fewer iterations and reduce the
    # time to the LR drop (set in the solver to 350,000 iterations).
    TRAIN_IMDB="coco_2014_train"     #定义相应的变量
    TEST_IMDB="coco_2014_minival"
    PT_DIR="coco"
    ITERS=490000                     #定义迭代次数
    ;;
  *)
    echo "No dataset given"
    exit
    ;;
esac

LOG="experiments/logs/faster_rcnn_end2end_${NET}_${EXTRA_ARGS_SLUG}.txt.`date +'%Y-%m-%d_%H-%M-%S'`"  #训练日志的存储路径
exec &> >(tee -a "$LOG")
echo Logging output to "$LOG"

time ./tools/train_net.py --gpu ${GPU_ID} \     #加载网络训练的相关参数并进行训练
  --solver models/${PT_DIR}/${NET}/faster_rcnn_end2end/solver.prototxt \
  --weights data/imagenet_models/${NET}.v2.caffemodel \
  --imdb ${TRAIN_IMDB} \
  --iters ${ITERS} \
  --cfg experiments/cfgs/faster_rcnn_end2end.yml \
  ${EXTRA_ARGS}

set +x
NET_FINAL=`grep -B 1 "done solving" ${LOG} | grep "Wrote snapshot" | awk '{print $4}'`   
set -x

time ./tools/test_net.py --gpu ${GPU_ID} \    #测试过程
  --def models/${PT_DIR}/${NET}/faster_rcnn_end2end/test.prototxt \
  --net ${NET_FINAL} \
  --imdb ${TEST_IMDB} \
  --cfg experiments/cfgs/faster_rcnn_end2end.yml \
  ${EXTRA_ARGS}