faster rcnn 训练与测试

 faster rcnn 训练

./experiments/scripts/faster_rcnn_alt_opt.sh 0 ZF pascal_voc

#!/bin/bash# Usage:# ./experiments/scripts/faster_rcnn_alt_opt.sh GPU NET DATASET [options args to {train,test}_net.py]# DATASET is only pascal_voc for now## Example:# ./experiments/scripts/faster_rcnn_alt_opt.sh 0 VGG_CNN_M_1024 pascal_voc \#   --set EXP_DIR foobar RNG_SEED 42 TRAIN.SCALES "[400, 500, 600, 700]"set -xset -eexport PYTHONUNBUFFERED="True"GPU_ID=$1NET=$2NET_lc=${NET,,}DATASET=$3array=( $@ )len=${#array[@]}EXTRA_ARGS=${array[@]:3:$len}EXTRA_ARGS_SLUG=${EXTRA_ARGS// /_}case $DATASET in  pascal_voc)    TRAIN_IMDB="voc_2007_trainval"    TEST_IMDB="voc_2007_test"    PT_DIR="pascal_voc"    ITERS=40000    ;;  coco)    echo "Not implemented: use experiments/scripts/faster_rcnn_end2end.sh for coco"    exit    ;;  *)    echo "No dataset given"    exit    ;;esacLOG="experiments/logs/faster_rcnn_alt_opt_${NET}_${EXTRA_ARGS_SLUG}.txt.`date +'%Y-%m-%d_%H-%M-%S'`"exec &> >(tee -a "$LOG")echo Logging output to "$LOG"time ./tools/train_faster_rcnn_alt_opt.py --gpu ${GPU_ID} \  --net_name ${NET} \  --weights data/imagenet_models/${NET}.v2.caffemodel \  --imdb ${TRAIN_IMDB} \  --cfg experiments/cfgs/faster_rcnn_alt_opt.yml \  ${EXTRA_ARGS}set +xNET_FINAL=`grep "Final model:" ${LOG} | awk '{print $3}'`set -xtime ./tools/test_net.py --gpu ${GPU_ID} \  --def models/${PT_DIR}/${NET}/faster_rcnn_alt_opt/faster_rcnn_test.pt \  --net ${NET_FINAL} \  --imdb ${TEST_IMDB} \  --cfg experiments/cfgs/faster_rcnn_alt_opt.yml \  ${EXTRA_ARGS}

Reading annotation for 4801/4952Reading annotation for 4901/4952Saving cached annotations to /home//py-faster-rcnn/data/VOCdevkit2007/annotations_cache/annots.pklAP for aeroplane = 0.6104AP for bicycle = 0.7060AP for bird = 0.5401AP for boat = 0.4113AP for bottle = 0.3118AP for bus = 0.6708AP for car = 0.7407AP for cat = 0.7074AP for chair = 0.3632AP for cow = 0.6420AP for diningtable = 0.6072AP for dog = 0.6806AP for horse = 0.7654AP for motorbike = 0.6794AP for person = 0.6553AP for pottedplant = 0.3238AP for sheep = 0.5597AP for sofa = 0.5185AP for train = 0.6880AP for tvmonitor = 0.6110Mean AP = 0.5896~~~~~~~~Results:0.6100.7060.5400.4110.3120.6710.7410.7070.3630.6420.6070.6810.7650.6790.6550.3240.5600.5180.6880.6110.590~~~~~~~~--------------------------------------------------------------Results computed with the **unofficial** Python eval code.Results should be very close to the official MATLAB eval code.Recompute with `./tools/reval.py --matlab ...` for your paper.-- Thanks, The Management--------------------------------------------------------------real2m44.858suser2m41.012ssys0m18.440s:~/py-faster-rcnn$ 

测试

./tools/demo.py --net zf