Faster-RCNN训练自己的样本
来源:互联网 发布:红帆oa软件 编辑:程序博客网 时间:2024/06/07 22:02
Faster-RCNN训练自己的样本
I0929 23:25:56.106283 9598 net.cpp:228] conv1 does not need backward computation.I0929 23:25:56.106286 9598 net.cpp:270] This network produces output bbox_predI0929 23:25:56.106287 9598 net.cpp:270] This network produces output cls_probI0929 23:25:56.106299 9598 net.cpp:283] Network initialization done.I0929 23:25:56.171612 9598 net.cpp:816] Ignoring source layer dataI0929 23:25:56.201792 9598 net.cpp:816] Ignoring source layer loss_clsI0929 23:25:56.201802 9598 net.cpp:816] Ignoring source layer loss_bboxI0929 23:25:56.202102 9598 net.cpp:816] Ignoring source layer silence_rpn_cls_scoreI0929 23:25:56.202107 9598 net.cpp:816] Ignoring source layer silence_rpn_bbox_predTraceback (most recent call last): File "./tools/test_net.py", line 85, in <module> imdb = get_imdb(args.imdb_name) File "/home/icalc/py-faster-rcnn/tools/../lib/datasets/factory.py", line 38, in get_imdb return __sets[name]() File "/home/icalc/py-faster-rcnn/tools/../lib/datasets/factory.py", line 20, in <lambda> __sets[name] = (lambda split=split, year=year: pascal_voc(split, year)) File "/home/icalc/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 38, in __init__ self._image_index = self._load_image_set_index() File "/home/icalc/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 82, in _load_image_set_index 'Path does not exist: {}'.format(image_set_file)AssertionError: Path does not exist: /home/icalc/py-faster-rcnn/data/VOCdevkit2007/VOC2007/ImageSets/Main/test.txt
解决:
ImageSets
Main文件需要trainval.txt和test.txt两个文件
train
val
test
Reading annotation for 3901/4952Reading annotation for 4001/4952Reading annotation for 4101/4952Reading annotation for 4201/4952Reading annotation for 4301/4952Reading annotation for 4401/4952Reading annotation for 4501/4952Reading annotation for 4601/4952Reading annotation for 4701/4952Reading annotation for 4801/4952Reading annotation for 4901/4952Saving cached annotations to /home/icalc/py-faster-rcnn/data/VOCdevkit2007/annotations_cache/annots.pklAP for aeroplane = 0.6114AP for bicycle = 0.6873AP for bird = 0.5735AP for boat = 0.4505AP for bottle = 0.3223AP for bus = 0.6750AP for car = 0.7491AP for cat = 0.7020AP for chair = 0.3622AP for cow = 0.6265AP for diningtable = 0.5938AP for dog = 0.6640AP for horse = 0.7727AP for motorbike = 0.6801AP for person = 0.6518AP for pottedplant = 0.3408AP for sheep = 0.5669AP for sofa = 0.5379AP for train = 0.6842AP for tvmonitor = 0.6016Mean AP = 0.5927~~~~~~~~Results:0.6110.6870.5740.4500.3220.6750.7490.7020.3620.6260.5940.6640.7730.6800.6520.3410.5670.5380.6840.6020.593~~~~~~~~--------------------------------------------------------------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--------------------------------------------------------------real2m36.431suser2m30.988ssys0m18.472s
#!/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}
阅读全文
0 0
- Faster-RCNN训练自己的样本
- ubuntu14.04+cuda8.0+caffe下使用自己的样本数据训练faster-rcnn
- Faster RCNN 训练自己的检测模型
- 用自己的数据训练Faster-RCNN
- faster-rcnn安装,训练自己的数据
- Faster RCNN 训练自己的数据集
- Faster-rcnn训练自己的数据库
- Faster-RCNN训练自己的数据集
- Faster-RCNN训练自己的数据集
- 使用faster rcnn训练自己的模型
- py-faster-rcnn训练自己的数据
- faster rcnn 训练自己的数据
- faster Rcnn训练自己的数据集
- 使用自己的数据训练Faster-RCNN
- Faster RCNN 训练自己的检测模型
- 使用faster-rcnn训练自己的模型
- Faster-Rcnn训练自己的数据集
- 使用Faster-RCNN训练自己的训练集
- http://blog.csdn.net/u012043391/article/details/54972127
- POJ 3683 Priest John's Busiest Day (2-SAT)
- 49 款人脸检测/识别的API、库和软件 .
- java单例设计模式
- 对于bresenham画圆算法的一点点理解
- Faster-RCNN训练自己的样本
- 用python画AR模型时序图
- 使用centos(linux)命令行常用命令
- C++类的静态数据成员及其用法
- 操作系统-管程、进程和线程之间的差别
- 深入浅出paddlepaddle
- IO操作——文件流(低级流,字节流)
- 超全面的JavaWeb笔记day12<Jsp&JavaBean&El表达式>
- 计算机如何开机